@jtalk22/slack-mcp 4.1.2 → 4.2.1

package/README.md

@@ -4,7 +4,7 @@
 [![MCP Registry](https://img.shields.io/badge/MCP_Registry-listed-blue)](https://registry.modelcontextprotocol.io)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
 
-Give your AI agent full Slack access. No app registration, no admin approval, no OAuth. One command, 16 tools, works with any MCP client.
+Give your AI agent full Slack access — and structured workflow output the AI can actually use. No app registration, no admin approval, no OAuth. One command, 21 tools, works with any MCP client.
 
 ```bash
 npx -y @jtalk22/slack-mcp --setup
@@ -39,9 +39,29 @@ This server uses your browser's session tokens instead. If you can see it in Sla
 | Works with Gemini CLI | No | **Yes** |
 | Works with Codex CLI | No | **Yes** |
 | Setup time | ~30 min | **~2 min** |
-| Tools | Limited | **16** |
+| Tools | Limited | **21** |
 | Visible to admins | Yes | **No — session-token transport** |
 
+## Workflow Primitives (new in 4.2)
+
+Save a workflow profile that binds a `workflow_kind` to channels + priority people + retention + cadence. Stored locally at `~/.slack-mcp-workflows.json`. The hosted brain at [mcp.revasserlabs.com](https://mcp.revasserlabs.com) reads these profiles and returns **structured JSON per workflow_kind** — downstream automation (Linear, Notion, status dashboards) consumes the JSON directly.
+
+| `workflow_kind` | Returns (structured JSON) |
+|---|---|
+| `incident_room` | `{incident_summary, timeline, open_risks, owner_gaps, next_actions}` |
+| `exec_brief` | `{summary, decisions, risks, asks, action_items}` |
+| `support_inbox` | `{open_threads, ack_lag, owner_gaps, escalations, next_actions}` |
+| `product_launch_watch` | `{launch_signals, feedback_themes, blockers, metrics, next_actions}` |
+| `custom` | `{summary, highlights, open_questions, next_actions}` |
+
+Six prebuilt templates ship with the package:
+
+```bash
+npx -y @jtalk22/slack-mcp --apply-template oncall-handoff --channels C012345,C067890
+```
+
+Available templates: `oncall-handoff`, `support-triage`, `exec-monday`, `sprint-tracker`, `customer-feedback`, `incident-room`. The structural primitives (`slack_workflow_save`, `slack_workflows`) are free forever in OSS; the hosted brain is `$0` to start (no card) and `$9/mo` Pro for unlimited AI tools (scheduled morning catch-up DM rolling out Q2 2026).
+
 ## Quick Start per Client
 
 <details>
@@ -129,11 +149,18 @@ Or via CLI: `codex mcp add slack -- npx -y @jtalk22/slack-mcp`
 | `slack_add_reaction` | Add an emoji reaction to a message | **destructive** |
 | `slack_remove_reaction` | Remove an emoji reaction from a message | **destructive** |
 | `slack_conversations_mark` | Mark a conversation as read | **destructive** |
+| `slack_workflow_save` | Save a workflow profile (channels, kind, retention, cadence) to `~/.slack-mcp-workflows.json` | local-write |
+| `slack_workflows` | List saved workflow profiles | read-only |
+| `slack_smart_search` | Semantic search across indexed channels — hosted brain | hosted-stub† |
+| `slack_catch_me_up` | AI-summarized digest of unreads + priority threads — hosted brain | hosted-stub† |
+| `slack_triage` | Prioritized action queue across channels — hosted brain | hosted-stub† |
 
-12 read-only, 4 write-path. All carry [MCP safety annotations](https://modelcontextprotocol.io/specification/2025-03-26/server/tools#annotations).
+21 tools total: 12 read-only Slack, 4 write-path Slack, 2 workflow profile primitives (1 local-write, 1 read-only), 3 hosted stubs. All carry [MCP safety annotations](https://modelcontextprotocol.io/specification/2025-03-26/server/tools#annotations).
 
 \* `slack_refresh_tokens` modifies local token file only.
 
+† Hosted stubs return a structured upgrade payload (`signup_url`, `free_tier_quota`, `pro_value_prop`) — no Slack write occurs from OSS. Activate the brain at [mcp.revasserlabs.com](https://mcp.revasserlabs.com) (free tier, no card).
+
 ## Install
 
 **Node.js 20+**
@@ -234,11 +261,11 @@ Hosted tiers at [mcp.revasserlabs.com](https://mcp.revasserlabs.com):
 
 | Tier | Price | What it owns |
 |------|-------|-------------|
-| Self-host | Free | Local stdio, all 16 tools, MIT licensed |
-| Solo | $19/mo | Managed endpoint + OAuth 2.1 bridge (required for Claude.ai web) + encrypted storage |
-| Team | $49/mo | Solo features + multi-seat routing |
-| Turnkey Team Launch | from $2,500+ | Dedicated instance + 30-day setup support |
-| Managed Reliability | from $800/mo+ | SLA-backed instance + incident response |
+| Self-host | Free (MIT) | Local stdio, all 21 tools (16 read/write Slack + 2 workflow profile primitives + 3 discoverable upgrade stubs to hosted brain) |
+| Hosted Free | $0 (no card) | Email signup, 1 workspace, 10 smart_search/mo + 3 catch_me_up/mo + 5 triage/day. All 5 workflow profile types. 7-day index retention. |
+| Pro | $9/mo | Unlimited AI tools, **scheduled morning catch-up DM** *(rolling out Q2 2026, 8am workspace tz)*, permanent OAuth, 90-day Vectorize, 2 workspaces |
+| Team | $49/mo flat | Pro + shared workflow profiles + audit log + 24h support + scheduled catch-up to channel + 5 workspaces |
+| Ops | from $199/mo (custom) | SLA, custom retention, SOC2 evidence path, multi-tenant isolation, 10+ workspaces, dedicated workflow tuning |
 
 </details>
 
@@ -278,13 +305,15 @@ Session tokens (`xoxc-` + `xoxd-`) from your browser. If you can see it in Slack
 
 Tokens expire. The server notices before you do — proactive health monitoring, automatic refresh on macOS, warnings when tokens age out. File writes are atomic (temp file → chmod → rename) to prevent corruption. Concurrent refresh attempts are mutex-locked.
 
-## What's New in 4.1.2
+## What's New in 4.2.0
 
-- **LevelDB extraction** — reads tokens directly from Chrome's LevelDB store. No live Slack tab required, no AppleScript flag dependency.
-- **Multi-profile enumeration** — automatically picks the freshest Chrome profile. Override with `SLACK_MCP_CHROME_USER_DATA_DIR`, `SLACK_MCP_CHROME_PROFILE`, or `SLACK_MCP_EXTRACTION_MODE`.
-- **Explicit shutdown handlers** — SIGTERM/SIGINT/SIGHUP/stdin EOF/stdin error all exit cleanly. Zero zombie processes.
+- **Workflow primitives** — `slack_workflow_save` + `slack_workflows` bind a `workflow_kind` (`incident_room`, `exec_brief`, `support_inbox`, `product_launch_watch`, `custom`) to channels, priority people, retention, and cadence. The hosted brain returns structured JSON per kind — `incident_room` returns `{incident_summary, timeline, open_risks, owner_gaps, next_actions}`, `exec_brief` returns `{summary, decisions, risks, asks, action_items}`. Downstream automation (Linear, Notion, dashboards) consumes the JSON directly.
+- **Discoverable upgrade stubs** — `slack_smart_search`, `slack_catch_me_up`, `slack_triage` appear in OSS as upgrade payloads pointing at the hosted brain. Response shape is `{signup_url, free_tier_quota, pro_value_prop}` — no interruptions, the AI routes the user cleanly.
+- **Six prebuilt templates** — apply with `npx -y @jtalk22/slack-mcp --apply-template <name> --channels C012,C034`. Names: `oncall-handoff`, `support-triage`, `exec-monday`, `sprint-tracker`, `customer-feedback`, `incident-room`. Read them, fork them, edit them — they're JSON profiles.
+- **Setup wizard hosted bridge** — six in-wizard moments surface the hosted free tier (no card) where it matches the user's pain. Stays out of the way otherwise.
+- **Prior reliability fixes carried forward** — LevelDB token extraction, multi-profile enumeration, and explicit SIGTERM/SIGINT/SIGHUP/stdin shutdown handlers ship in 4.2.0 too.
 
-Full release notes in [docs/INDEX.md](docs/INDEX.md) and on [GitHub releases/latest](https://github.com/jtalk22/slack-mcp-server/releases/latest).
+Full release notes on [GitHub releases/latest](https://github.com/jtalk22/slack-mcp-server/releases/latest).
 
 ## Hosted HTTP Mode
 
@@ -342,4 +371,4 @@ Not affiliated with Slack Technologies, Inc. Uses browser session credentials
 
 ---
 
-Hosted tiers live at [mcp.revasserlabs.com](https://mcp.revasserlabs.com): Solo $19/mo, Team $49/mo, Turnkey Team Launch from $2,500+, Managed Reliability from $800/mo+. Hosted owns the managed MCP endpoint, the OAuth 2.1 bridge into Claude.ai, encrypted credential storage, and the structural absence of the zombie-process class. It does not replace Chrome — the user still pastes `xoxc-`/`xoxd-` at setup.
+Hosted version live at [mcp.revasserlabs.com](https://mcp.revasserlabs.com): Free tier (no card), $9/mo Pro, $49/mo Team flat, Ops from $199/mo. Hosted owns the AI brain (smart_search, catch_me_up, triage), the scheduled morning catch-up DM at 8am workspace time *(rolling out Q2 2026)*, permanent OAuth (no 2-week token rotation), 90-day Vectorize retention, and shared workflow profiles. The OSS package owns local stdio + all 16 read/write Slack tools + workflow profile primitives (slack_workflow_save, slack_workflows). The 3 paid stubs (slack_smart_search, slack_catch_me_up, slack_triage) appear in OSS as discoverable upgrade prompts.

package/docs/DEPLOYMENT-MODES.md

@@ -0,0 +1,56 @@
+# Deployment Modes
+
+Use this guide to choose the right operating mode before rollout.
+
+## Quick Chooser
+
+- Choose `stdio` for personal self-hosted use in Claude Desktop/Claude Code.
+- Choose local `web` for browser workflows and manual Slack browsing.
+- Choose hosted HTTP only when you need remote execution and can handle token operations.
+- Choose Smithery/Worker only when your consumers require registry-hosted MCP transport.
+- A managed **Hosted** version is live at [mcp.revasserlabs.com](https://mcp.revasserlabs.com) — Free tier (no card), Pro $9/mo, Team $49/mo flat, Ops from $199/mo. See [pricing](https://mcp.revasserlabs.com/pricing).
+
+## Mode Matrix
+
+| Mode | Start Command | Best For | Auth Material | Exposure | Notes |
+|------|---------------|----------|---------------|----------|-------|
+| Local MCP (`stdio`) | `npx -y @jtalk22/slack-mcp` | Individual daily usage in Claude | `SLACK_TOKEN` + `SLACK_COOKIE` via token file/env | Local process | Lowest ops burden. Free. 21 tools (16 read/write + 2 workflow profile primitives + 3 discoverable upgrade stubs to hosted). |
+| Local Web UI (`web`) | `npx -y @jtalk22/slack-mcp web` | Browser-first usage, manual search/send | Same as above + generated API key | `localhost` by default | Useful when MCP is not available |
+| Hosted MCP (`http`) | `node src/server-http.js` | Controlled hosted integration | Env-injected Slack token/cookie + HTTP bearer token | Remote endpoint | `/mcp` is bearer-protected by default; configure CORS allowlist |
+| Smithery/Worker | `wrangler deploy` + Smithery publish flow | Registry distribution for hosted consumers | Query/env token handoff | Remote endpoint | Keep worker version parity with npm release |
+
+## Team Deployment Guidance
+
+If you are deploying for more than one operator:
+
+1. Start with one maintainer on local `stdio`.
+2. Document token lifecycle and rotation ownership.
+3. Define support window and incident contact before enabling hosted mode.
+4. Validate `/health` and MCP initialize responses on every release.
+
+## Release Checklist by Mode
+
+### Local `stdio`
+
+1. `npx -y @jtalk22/slack-mcp --status`
+2. `npx -y @jtalk22/slack-mcp --help`
+3. Confirm tool list in Claude client.
+
+### Local `web`
+
+1. `npx -y @jtalk22/slack-mcp web`
+2. Verify API key generation at `~/.slack-mcp-api-key`.
+3. Verify `/health`, `/conversations`, and `/search` endpoints.
+
+### Hosted (`http` or Worker)
+
+1. Verify `version` parity across `package.json`, server metadata, and health responses.
+2. Verify HTTP auth behavior:
+   - missing `SLACK_MCP_HTTP_AUTH_TOKEN` returns `503`
+   - bad bearer token returns `401`
+   - valid bearer token succeeds
+3. Verify CORS behavior:
+   - denied by default
+   - allowed origins work when listed in `SLACK_MCP_HTTP_ALLOWED_ORIGINS`
+4. Confirm `slack_get_thread`, `slack_search_messages`, and `slack_users_info` behavior.
+5. Confirm token handling mode (ephemeral vs env persistence) is documented.

package/docs/TROUBLESHOOTING.md

@@ -31,7 +31,9 @@ If `--version` fails here, the issue is install/runtime path, not Slack credenti
 
 ## Hosted Version
 
-A hosted version with permanent OAuth tokens, semantic search, and AI summaries is coming soon at [mcp.revasserlabs.com](https://mcp.revasserlabs.com). The current release is self-hosted only.
+The hosted version is live at [mcp.revasserlabs.com](https://mcp.revasserlabs.com). Free tier (no card) ships 10 smart_search/mo + 3 catch_me_up/mo + 5 triage/day + all 5 workflow profile types. Pro at $9/mo unlocks unlimited AI tools, the scheduled morning catch-up DM at 8am workspace time *(rolling out Q2 2026)*, permanent OAuth (no 2-week token rotation), and 90-day Vectorize retention. Team at $49/mo flat covers 5 workspaces with shared workflow profiles and audit log. Ops engagement starts at $199/mo (custom) for 10+ workspace organizations with SLA, custom retention, SOC2 evidence, or multi-tenant isolation.
+
+The OSS package keeps the local-machine path. The hosted version adds the AI brain (smart_search, catch_me_up, triage) — these tools also appear in the OSS package as discoverable upgrade stubs that point at the hosted signup.
 
 ---
 

package/lib/handlers.js

@@ -16,6 +16,11 @@ import {
   getLastExtractionError
 } from "./token-store.js";
 import { slackAPI, resolveUser, formatTimestamp, sleep, checkTokenHealth, getUserCacheStats } from "./slack-client.js";
+import {
+  saveProfile as workflowSaveProfile,
+  listProfiles as workflowListProfiles,
+  ALLOWED_WORKFLOW_KINDS_LIST,
+} from "./workflow-store.js";
 
 // ============ Utilities ============
 
@@ -773,3 +778,90 @@ export async function handleUsersSearch(args) {
     users: allUsers.slice(0, limit)
   });
 }
+
+// ============ Workflow Profile Primitives (OSS) ============
+
+/**
+ * Save (or update) a workflow profile to ~/.slack-mcp-workflows.json
+ * Profile binds a workflow_kind to channels + priority_people + retention + cadence.
+ */
+export async function handleWorkflowSave(args) {
+  const safeArgs = args || {};
+  const result = workflowSaveProfile({
+    profile_name: safeArgs.profile_name,
+    workflow_kind: safeArgs.workflow_kind,
+    channels: safeArgs.channels,
+    priority_people: safeArgs.priority_people,
+    retention_mode: safeArgs.retention_mode,
+    summary_cadence: safeArgs.summary_cadence,
+  });
+  if (!result.ok) {
+    return asMcpJson({ error: "invalid_workflow_profile", errors: result.errors }, true);
+  }
+  return asMcpJson({
+    ok: true,
+    profile_name: result.profile_name,
+    profile: result.profile,
+    note: "Profile saved locally. Hosted free tier syncs profiles automatically when you connect your account; OSS-only mode keeps them on your machine.",
+  });
+}
+
+/**
+ * List saved workflow profiles, optionally filtered by workflow_kind.
+ */
+export async function handleWorkflows(args) {
+  const result = workflowListProfiles({ workflow_kind: args && args.workflow_kind });
+  if (!result.ok) {
+    return asMcpJson({ error: "invalid_workflow_filter", errors: result.errors }, true);
+  }
+  return asMcpJson({
+    ok: true,
+    count: result.profiles.length,
+    workflow_kinds: ALLOWED_WORKFLOW_KINDS_LIST,
+    profiles: result.profiles,
+  });
+}
+
+// ============ Hosted-Only AI Tool Stubs ============
+// These three tools appear in the OSS package's MCP tool list so users
+// discover them. The handlers return a structured upgrade message —
+// actual execution happens on the hosted worker (mcp.revasserlabs.com).
+
+const HOSTED_UPGRADE_PAYLOAD = {
+  error: "tool_requires_hosted",
+  message: "This tool needs hosted mode (Vectorize + Workers AI). Get free monthly credits at mcp.revasserlabs.com — no card required.",
+  signup_url: "https://mcp.revasserlabs.com/signup",
+  upgrade_url: "https://mcp.revasserlabs.com/pricing",
+  free_tier_quota: "10 smart_search + 3 catch_me_up per month, 5 triage per day",
+  pro_value_prop: "Pro $9/mo unlocks unlimited AI tools (scheduled morning catch-up DM at 8am workspace time rolling out Q2 2026).",
+};
+
+export async function handleSmartSearch(args) {
+  return asMcpJson(
+    {
+      ...HOSTED_UPGRADE_PAYLOAD,
+      requested: { tool: "slack_smart_search", args: args || {} },
+    },
+    true
+  );
+}
+
+export async function handleCatchMeUp(args) {
+  return asMcpJson(
+    {
+      ...HOSTED_UPGRADE_PAYLOAD,
+      requested: { tool: "slack_catch_me_up", args: args || {} },
+    },
+    true
+  );
+}
+
+export async function handleTriage(args) {
+  return asMcpJson(
+    {
+      ...HOSTED_UPGRADE_PAYLOAD,
+      requested: { tool: "slack_triage", args: args || {} },
+    },
+    true
+  );
+}

package/lib/public-metadata.js

@@ -18,5 +18,5 @@ export const PUBLIC_METADATA = Object.freeze({
   cloudSupportUrl: "https://mcp.revasserlabs.com/support",
   cloudStatusUrl: "https://mcp.revasserlabs.com/status",
   supportEmail: "support@revasserlabs.com",
-  selfHostedToolCount: 16,
+  selfHostedToolCount: 21,
 });

package/lib/public-pages.js

@@ -63,7 +63,7 @@ function shareLinks() {
 }
 
 function shareNote() {
-  return `<strong>Verify in 30 seconds:</strong> <code>--version</code>, <code>--doctor</code>, <code>--status</code>. Self-host gives ${PUBLIC_METADATA.selfHostedToolCount} tools with session-based auth. Works with any MCP client — Claude, ChatGPT, Cursor, Copilot, Gemini, Windsurf. Hosted version coming soon at <a href="${PUBLIC_METADATA.canonicalSiteUrl}">mcp.revasserlabs.com</a>.`;
+  return `<strong>Verify in 30 seconds:</strong> <code>--version</code>, <code>--doctor</code>, <code>--status</code>. Self-host gives ${PUBLIC_METADATA.selfHostedToolCount} tools with session-based auth. Works with any MCP client — Claude, ChatGPT, Cursor, Copilot, Gemini, Windsurf. Hosted free tier (no card) live at <a href="${PUBLIC_METADATA.canonicalSiteUrl}">mcp.revasserlabs.com</a> — Pro $9/mo unlocks unlimited AI tools (scheduled morning catch-up DM rolling out Q2 2026).`;
 }
 
 function demoLinks() {
@@ -75,7 +75,7 @@ function demoLinks() {
 }
 
 function demoNote() {
-  return `Self-host free for ${PUBLIC_METADATA.selfHostedToolCount} tools with session-based auth. Works with Claude, ChatGPT, Cursor, Copilot, Gemini, Windsurf, and any other MCP client. No OAuth app, no admin approval. Hosted version coming soon at <a href="${PUBLIC_METADATA.canonicalSiteUrl}" target="_blank" rel="noopener noreferrer">mcp.revasserlabs.com</a>.`;
+  return `Self-host free for ${PUBLIC_METADATA.selfHostedToolCount} tools with session-based auth. Works with Claude, ChatGPT, Cursor, Copilot, Gemini, Windsurf, and any other MCP client. No OAuth app, no admin approval. Hosted free tier (no card) live at <a href="${PUBLIC_METADATA.canonicalSiteUrl}" target="_blank" rel="noopener noreferrer">mcp.revasserlabs.com</a> — Pro $9/mo unlocks unlimited AI tools (scheduled morning catch-up DM rolling out Q2 2026).`;
 }
 
 function demoFooterLinks() {
@@ -113,8 +113,8 @@ function commonTokens() {
     SELF_HOSTED_TOOL_COUNT: String(PUBLIC_METADATA.selfHostedToolCount),
     CLOUD_MANAGED_TOOL_COUNT: "15",
     TEAM_AI_WORKFLOW_COUNT: "3",
-    CLOUD_SOLO_PRICE: "coming soon",
-    CLOUD_TEAM_PRICE: "coming soon",
+    CLOUD_SOLO_PRICE: "$9/mo",
+    CLOUD_TEAM_PRICE: "$49/mo",
     CLOUD_TURNKEY_LAUNCH_PRICE: "contact us",
     CLOUD_MANAGED_RELIABILITY_PRICE: "contact us",
     SUPPORT_EMAIL: PUBLIC_METADATA.supportEmail,

package/lib/tools.js

@@ -399,5 +399,165 @@ export const TOOLS = [
       idempotentHint: true,
       openWorldHint: true
     }
+  },
+  // ============ Workflow Profile Primitives (OSS) ============
+  // Local JSON storage at ~/.slack-mcp-workflows.json. Defines the
+  // structural primitive that the hosted AI brain (smart_search,
+  // catch_me_up, triage) consumes to return structured JSON.
+  {
+    name: "slack_workflow_save",
+    description: "Save or update a workflow profile that binds a workflow_kind (support_inbox | incident_room | exec_brief | product_launch_watch | custom) to channels, priority people, retention mode, and summary cadence. Stored locally at ~/.slack-mcp-workflows.json. Hosted brain reads these to return structured JSON per the workflow_kind.",
+    inputSchema: {
+      type: "object",
+      properties: {
+        profile_name: {
+          type: "string",
+          description: "Unique name for this workflow profile (e.g. 'morning-exec-brief', 'on-call-rotation')"
+        },
+        workflow_kind: {
+          type: "string",
+          enum: ["support_inbox", "incident_room", "exec_brief", "product_launch_watch", "custom"],
+          description: "Workflow kind. Determines structured JSON output shape from the hosted AI brain."
+        },
+        channels: {
+          type: "array",
+          items: { type: "string" },
+          description: "Slack channel IDs to read (e.g. ['C012345', 'C067890'])"
+        },
+        priority_people: {
+          type: "array",
+          items: { type: "string" },
+          description: "Slack user IDs whose messages get extra weight in summaries"
+        },
+        retention_mode: {
+          type: "string",
+          enum: ["ephemeral", "persistent"],
+          description: "Token retention mode for hosted execution. Default ephemeral."
+        },
+        summary_cadence: {
+          type: "string",
+          enum: ["on_demand", "daily_8am", "weekly_monday"],
+          description: "When the hosted brain auto-runs slack_catch_me_up against this profile. on_demand only on hosted free; daily_8am and weekly_monday require Pro or Team."
+        }
+      },
+      required: ["profile_name", "workflow_kind"]
+    },
+    annotations: {
+      title: "Save Workflow Profile",
+      readOnlyHint: false,
+      destructiveHint: false,
+      idempotentHint: true,
+      openWorldHint: false
+    }
+  },
+  {
+    name: "slack_workflows",
+    description: "List all saved workflow profiles from ~/.slack-mcp-workflows.json. Optionally filter by workflow_kind. Returns profile_name, channels, priority_people, retention_mode, summary_cadence, structured_keys, created_at, updated_at.",
+    inputSchema: {
+      type: "object",
+      properties: {
+        workflow_kind: {
+          type: "string",
+          enum: ["support_inbox", "incident_room", "exec_brief", "product_launch_watch", "custom"],
+          description: "Optional filter — return only profiles of this workflow_kind"
+        }
+      }
+    },
+    annotations: {
+      title: "List Workflow Profiles",
+      readOnlyHint: true,
+      idempotentHint: true,
+      openWorldHint: false
+    }
+  },
+  // ============ Hosted-Only AI Tools (OSS = upgrade stubs) ============
+  // These tool definitions appear in every MCP client's tool list so users
+  // discover them. The OSS handlers return a structured upgrade message
+  // pointing at mcp.revasserlabs.com — the hosted worker actually runs them.
+  {
+    name: "slack_smart_search",
+    description: "Semantic + lexical hybrid search across your indexed Slack history. Returns ranked results with relevance scores, channel context, thread context, and matched terms. Hosted-only (requires Vectorize + Workers AI). Free tier ships 10 calls/month; upgrade to Pro $9/mo for unlimited at mcp.revasserlabs.com/pricing.",
+    inputSchema: {
+      type: "object",
+      properties: {
+        query: {
+          type: "string",
+          description: "Natural language or keyword query (semantic + lexical hybrid)"
+        },
+        channel_ids: {
+          type: "array",
+          items: { type: "string" },
+          description: "Optional — restrict search to these channel IDs"
+        },
+        days_back: {
+          type: "number",
+          description: "Optional — restrict search to the last N days (max 90 on Pro+, 7 on Free)"
+        },
+        limit: {
+          type: "number",
+          description: "Maximum results to return (default 10, max 50)"
+        }
+      },
+      required: ["query"]
+    },
+    annotations: {
+      title: "Smart Search (hosted)",
+      readOnlyHint: true,
+      idempotentHint: true,
+      openWorldHint: true
+    }
+  },
+  {
+    name: "slack_catch_me_up",
+    description: "Run a structured catch-up against a saved workflow profile. Returns structured JSON per the profile's workflow_kind: support_inbox returns {open_threads, ack_lag, owner_gaps, escalations, next_actions}; incident_room returns {incident_summary, timeline, open_risks, owner_gaps, next_actions}; exec_brief returns {summary, decisions, risks, asks, action_items}; product_launch_watch returns {launch_signals, feedback_themes, blockers, metrics, next_actions}; custom returns {summary, highlights, open_questions, next_actions}. Hosted-only. Free tier ships 3 calls/month; Pro $9/mo unlocks unlimited (scheduled morning DM at 8am workspace tz rolling out Q2 2026).",
+    inputSchema: {
+      type: "object",
+      properties: {
+        profile_name: {
+          type: "string",
+          description: "Name of a workflow profile saved via slack_workflow_save (or use --apply-template at install time to seed one)"
+        },
+        since: {
+          type: "string",
+          description: "Optional ISO8601 timestamp — only consider Slack messages newer than this. Default: 24 hours ago for daily-cadence profiles, 7 days for weekly."
+        }
+      },
+      required: ["profile_name"]
+    },
+    annotations: {
+      title: "Catch Me Up (hosted)",
+      readOnlyHint: true,
+      idempotentHint: false,
+      openWorldHint: true
+    }
+  },
+  {
+    name: "slack_triage",
+    description: "Classify and route Slack threads against a workflow profile. Returns triage decisions per thread: priority (low|medium|high|urgent), suggested owner, escalation flag, time-sensitivity, and a routing recommendation. Hosted-only. Free tier ships 5 triage runs per day; Pro $9/mo unlocks unlimited.",
+    inputSchema: {
+      type: "object",
+      properties: {
+        profile_name: {
+          type: "string",
+          description: "Name of a workflow profile saved via slack_workflow_save"
+        },
+        channel_ids: {
+          type: "array",
+          items: { type: "string" },
+          description: "Optional — restrict triage to these channels (defaults to profile's channels)"
+        },
+        thread_ts: {
+          type: "string",
+          description: "Optional — triage a specific thread instead of the full inbox"
+        }
+      },
+      required: ["profile_name"]
+    },
+    annotations: {
+      title: "Triage (hosted)",
+      readOnlyHint: true,
+      idempotentHint: false,
+      openWorldHint: true
+    }
   }
 ];

package/lib/workflow-store.js

@@ -0,0 +1,188 @@
+/**
+ * Workflow Profile Store (local JSON, OSS-only)
+ *
+ * Stores user-defined workflow profiles that bind a workflow_kind
+ * (support_inbox | incident_room | exec_brief | product_launch_watch | custom)
+ * to a set of channels, priority people, retention mode, and summary cadence.
+ *
+ * The hosted AI brain (smart_search, catch_me_up, triage) consumes these
+ * profiles and returns structured JSON per the workflow_kind. The OSS
+ * package ships the profile primitives but not the AI brain — it's
+ * hosted-only because it needs Vectorize + Workers AI.
+ *
+ * File: ~/.slack-mcp-workflows.json (chmod 600)
+ * Atomic write pattern (temp → chmod → rename) prevents corruption from
+ * concurrent writes by multiple slack-mcp-server instances.
+ */
+
+import { writeFileSync, readFileSync, existsSync, renameSync, unlinkSync, chmodSync } from "fs";
+import { homedir, platform } from "os";
+import { join } from "path";
+
+const STORE_FILE = join(homedir(), ".slack-mcp-workflows.json");
+const STORE_VERSION = 1;
+
+const ALLOWED_WORKFLOW_KINDS = new Set([
+  "support_inbox",
+  "incident_room",
+  "exec_brief",
+  "product_launch_watch",
+  "custom",
+]);
+
+const ALLOWED_RETENTION_MODES = new Set(["ephemeral", "persistent"]);
+const ALLOWED_SUMMARY_CADENCES = new Set(["on_demand", "daily_8am", "weekly_monday"]);
+
+const STRUCTURED_KEYS_BY_KIND = {
+  support_inbox: ["open_threads", "ack_lag", "owner_gaps", "escalations", "next_actions"],
+  incident_room: ["incident_summary", "timeline", "open_risks", "owner_gaps", "next_actions"],
+  exec_brief: ["summary", "decisions", "risks", "asks", "action_items"],
+  product_launch_watch: ["launch_signals", "feedback_themes", "blockers", "metrics", "next_actions"],
+  custom: ["summary", "highlights", "open_questions", "next_actions"],
+};
+
+function emptyStore() {
+  return { version: STORE_VERSION, profiles: {} };
+}
+
+function atomicWriteSync(filePath, content) {
+  const tempPath = `${filePath}.${process.pid}.tmp`;
+  try {
+    writeFileSync(tempPath, content);
+    if (platform() === "darwin" || platform() === "linux") {
+      try { chmodSync(tempPath, 0o600); } catch {}
+    }
+    renameSync(tempPath, filePath);
+  } catch (e) {
+    try { unlinkSync(tempPath); } catch {}
+    throw e;
+  }
+}
+
+export function loadStore() {
+  if (!existsSync(STORE_FILE)) return emptyStore();
+  let raw;
+  try {
+    raw = readFileSync(STORE_FILE, "utf-8");
+  } catch {
+    return emptyStore();
+  }
+  try {
+    const data = JSON.parse(raw);
+    if (!data || typeof data !== "object" || !data.profiles) {
+      backupCorruptStore(raw, "shape-invalid");
+      return emptyStore();
+    }
+    if (data.version !== STORE_VERSION) {
+      // Future: migration logic. For now, back up the unrecognized version
+      // before falling back to empty so the old data is recoverable.
+      backupCorruptStore(raw, `version-${data.version}`);
+      return emptyStore();
+    }
+    return data;
+  } catch {
+    backupCorruptStore(raw, "json-parse-error");
+    return emptyStore();
+  }
+}
+
+function backupCorruptStore(raw, reasonTag) {
+  try {
+    const stamp = new Date().toISOString().replace(/[:.]/g, "-");
+    const backupPath = `${STORE_FILE}.bak.${reasonTag}.${stamp}`;
+    writeFileSync(backupPath, raw);
+    if (platform() === "darwin" || platform() === "linux") {
+      try { chmodSync(backupPath, 0o600); } catch {}
+    }
+  } catch {
+    // Backup is best-effort; do not throw on backup failure.
+  }
+}
+
+export function saveStore(store) {
+  atomicWriteSync(STORE_FILE, JSON.stringify(store, null, 2));
+}
+
+export function structuredKeysFor(workflowKind) {
+  return STRUCTURED_KEYS_BY_KIND[workflowKind] || STRUCTURED_KEYS_BY_KIND.custom;
+}
+
+export function validateProfile(input) {
+  const errors = [];
+  if (!input || typeof input !== "object") {
+    return { valid: false, errors: ["profile must be an object"] };
+  }
+  if (!input.profile_name || typeof input.profile_name !== "string" || !input.profile_name.trim()) {
+    errors.push("profile_name is required (non-empty string)");
+  }
+  if (!input.workflow_kind || !ALLOWED_WORKFLOW_KINDS.has(input.workflow_kind)) {
+    errors.push(`workflow_kind must be one of: ${Array.from(ALLOWED_WORKFLOW_KINDS).join(", ")}`);
+  }
+  if (input.channels && (!Array.isArray(input.channels) || input.channels.some((c) => typeof c !== "string"))) {
+    errors.push("channels must be an array of strings (Slack channel IDs)");
+  }
+  if (input.priority_people && (!Array.isArray(input.priority_people) || input.priority_people.some((p) => typeof p !== "string"))) {
+    errors.push("priority_people must be an array of strings (Slack user IDs)");
+  }
+  if (input.retention_mode && !ALLOWED_RETENTION_MODES.has(input.retention_mode)) {
+    errors.push(`retention_mode must be one of: ${Array.from(ALLOWED_RETENTION_MODES).join(", ")}`);
+  }
+  if (input.summary_cadence && !ALLOWED_SUMMARY_CADENCES.has(input.summary_cadence)) {
+    errors.push(`summary_cadence must be one of: ${Array.from(ALLOWED_SUMMARY_CADENCES).join(", ")}`);
+  }
+  return { valid: errors.length === 0, errors };
+}
+
+export function saveProfile(input) {
+  const { valid, errors } = validateProfile(input);
+  if (!valid) {
+    return { ok: false, errors };
+  }
+  const store = loadStore();
+  const now = new Date().toISOString();
+  const existing = store.profiles[input.profile_name];
+  const profile = {
+    workflow_kind: input.workflow_kind,
+    channels: Array.isArray(input.channels) ? [...input.channels] : [],
+    priority_people: Array.isArray(input.priority_people) ? [...input.priority_people] : [],
+    retention_mode: input.retention_mode || "ephemeral",
+    summary_cadence: input.summary_cadence || "on_demand",
+    structured_keys: structuredKeysFor(input.workflow_kind),
+    created_at: existing && existing.created_at ? existing.created_at : now,
+    updated_at: now,
+  };
+  store.profiles[input.profile_name] = profile;
+  saveStore(store);
+  return { ok: true, profile_name: input.profile_name, profile };
+}
+
+export function listProfiles({ workflow_kind } = {}) {
+  const store = loadStore();
+  const entries = Object.entries(store.profiles).map(([name, profile]) => ({ profile_name: name, ...profile }));
+  if (workflow_kind) {
+    if (!ALLOWED_WORKFLOW_KINDS.has(workflow_kind)) {
+      return { ok: false, errors: [`workflow_kind filter must be one of: ${Array.from(ALLOWED_WORKFLOW_KINDS).join(", ")}`] };
+    }
+    return { ok: true, profiles: entries.filter((p) => p.workflow_kind === workflow_kind) };
+  }
+  return { ok: true, profiles: entries };
+}
+
+export function deleteProfile(profile_name) {
+  const store = loadStore();
+  if (!store.profiles[profile_name]) {
+    return { ok: false, errors: [`profile_name "${profile_name}" not found`] };
+  }
+  delete store.profiles[profile_name];
+  saveStore(store);
+  return { ok: true, profile_name };
+}
+
+export function getProfile(profile_name) {
+  const store = loadStore();
+  const profile = store.profiles[profile_name];
+  if (!profile) return null;
+  return { profile_name, ...profile };
+}
+
+export const ALLOWED_WORKFLOW_KINDS_LIST = Array.from(ALLOWED_WORKFLOW_KINDS);

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "@jtalk22/slack-mcp",
   "mcpName": "io.github.jtalk22/slack-mcp-server",
-  "version": "4.1.2",
-  "description": "Slack MCP without OAuth — no app registration, no admin approval. Works with Claude Code, Cursor, Copilot (where the official server doesn't). 16 tools, one command.",
+  "version": "4.2.1",
+  "description": "Slack MCP without OAuth. 21 tools (16 read/write Slack + 2 workflow profile primitives + 3 hosted-brain upgrade stubs). Free OSS or hosted (free tier no card; $9/mo Pro = unlimited; morning DM rolling out Q2 2026).",
   "type": "module",
   "main": "src/server.js",
   "bin": {
@@ -90,7 +90,7 @@
   },
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.27.0",
-    "express": "^4.18.2"
+    "express": "^5.2.1"
   },
   "files": [
     "src/",
@@ -99,9 +99,12 @@
     "public/share.html",
     "scripts/setup-wizard.js",
     "scripts/token-cli.js",
+    "scripts/apply-template.js",
+    "templates/workflow-profiles/",
     "docs/SETUP.md",
     "docs/API.md",
     "docs/TROUBLESHOOTING.md",
+    "docs/DEPLOYMENT-MODES.md",
     "docs/assets/icon.svg",
     "docs/assets/icon-512.png",
     "README.md",

package/public/index.html

@@ -4,9 +4,10 @@
   <meta charset="UTF-8">
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   <title>Slack MCP Server — Web Dashboard</title>
+  <link rel="preconnect" href="https://fonts.googleapis.com">
+  <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+  <link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=IBM+Plex+Sans:wght@400;500;600&family=Space+Grotesk:wght@500;600;700&display=swap">
   <style>
-    @import url('https://fonts.googleapis.com/css2?family=IBM+Plex+Sans:wght@400;500;600&family=Space+Grotesk:wght@500;600;700&display=swap');
-
     :root {
       --font-heading: "Space Grotesk", "Avenir Next", "Segoe UI", sans-serif;
       --font-body: "IBM Plex Sans", "Inter", "Segoe UI", sans-serif;

package/public/share.html

@@ -4,17 +4,17 @@
   <meta charset="utf-8">
   <meta name="viewport" content="width=device-width, initial-scale=1">
   <title>Slack MCP Server</title>
-  <meta name="description" content="No OAuth. No admin. 16 Slack tools for Claude, Cursor, Copilot, Gemini, and any MCP client. One command: npx -y @jtalk22/slack-mcp --setup">
+  <meta name="description" content="No OAuth. No admin. 21 Slack tools for Claude, Cursor, Copilot, Gemini, and any MCP client. One command: npx -y @jtalk22/slack-mcp --setup">
   <meta property="og:type" content="website">
   <meta property="og:title" content="Slack MCP Server — No OAuth, no admin, just your browser session">
-  <meta property="og:description" content="Slack's official MCP needs OAuth + admin. This one uses your browser session. 16 tools, works with Claude, Cursor, Copilot, Gemini.">
+  <meta property="og:description" content="Slack's official MCP needs OAuth + admin. This one uses your browser session. 21 tools, works with Claude, Cursor, Copilot, Gemini.">
   <meta property="og:url" content="https://jtalk22.github.io/slack-mcp-server/public/share.html">
   <meta property="og:image" content="https://jtalk22.github.io/slack-mcp-server/docs/images/social-preview-v3.png">
   <meta property="og:image:width" content="1280">
   <meta property="og:image:height" content="640">
   <meta name="twitter:card" content="summary_large_image">
   <meta name="twitter:title" content="Slack MCP Server — No OAuth, no admin, just your browser session">
-  <meta name="twitter:description" content="16 tools for Claude, Cursor, Copilot, Gemini. npx -y @jtalk22/slack-mcp --setup">
+  <meta name="twitter:description" content="21 tools for Claude, Cursor, Copilot, Gemini. npx -y @jtalk22/slack-mcp --setup">
   <meta name="twitter:image" content="https://jtalk22.github.io/slack-mcp-server/docs/images/social-preview-v3.png">
   <link rel="icon" href="https://jtalk22.github.io/slack-mcp-server/docs/assets/icon-512.png" type="image/png">
   <style>
@@ -107,7 +107,7 @@
 <body>
   <main class="wrap">
     <h1>Slack MCP Server</h1>
-    <p class="sub">Give Claude full access to your Slack. Self-host 16 tools for free. Hosted version with semantic search, AI summaries, and permanent OAuth coming soon.</p>
+    <p class="sub">Give Claude full access to your Slack. Self-host 21 tools for free (16 read/write + 2 workflow profile primitives + 3 paid stubs that point at hosted). Hosted free tier — workflow continuity + AI catch-up. Sign up no card at <a href="https://mcp.revasserlabs.com">mcp.revasserlabs.com</a>.</p>
 
     <a class="preview" href="https://github.com/jtalk22/slack-mcp-server" rel="noopener">
       <img src="https://jtalk22.github.io/slack-mcp-server/docs/images/social-preview-v3.png" alt="Slack MCP Server social preview card">
@@ -123,7 +123,7 @@
       <a href="https://mcp.revasserlabs.com" rel="noopener" style="background:rgba(240,194,70,0.18);border-color:rgba(240,194,70,0.45);color:#f0c246">Hosted</a>
     </div>
 
-    <p class="note"><strong>Verify in 30 seconds:</strong> <code>--version</code>, <code>--doctor</code>, <code>--status</code>. Self-host gives 16 tools with session-based auth. Works with any MCP client — Claude, ChatGPT, Cursor, Copilot, Gemini, Windsurf. Hosted version coming soon at <a href="https://mcp.revasserlabs.com">mcp.revasserlabs.com</a>.</p>
+    <p class="note"><strong>Verify in 30 seconds:</strong> <code>--version</code>, <code>--doctor</code>, <code>--status</code>. Self-host gives 21 tools with session-based auth. Works with any MCP client — Claude, ChatGPT, Cursor, Copilot, Gemini, Windsurf. Hosted free tier (no card) live at <a href="https://mcp.revasserlabs.com">mcp.revasserlabs.com</a> — Pro $9/mo unlocks unlimited AI tools (scheduled morning catch-up DM rolling out Q2 2026).</p>
   </main>
 </body>
 </html>

package/scripts/apply-template.js

@@ -0,0 +1,117 @@
+#!/usr/bin/env node
+/**
+ * Apply a workflow profile template to ~/.slack-mcp-workflows.json
+ *
+ * Usage:
+ *   slack-mcp --apply-template <template-name>
+ *   slack-mcp --apply-template <template-name> --channels C012,C067 [--priority-people U0PRIME]
+ *
+ * Templates ship in templates/workflow-profiles/. Available templates:
+ *   oncall-handoff, support-triage, exec-monday, sprint-tracker,
+ *   customer-feedback, incident-room
+ *
+ * If --channels is not provided, the template is applied with empty
+ * channels — you can add them later via slack_workflow_save.
+ */
+
+import { readFileSync, existsSync, readdirSync } from "fs";
+import { dirname, join } from "path";
+import { fileURLToPath } from "url";
+import { saveProfile } from "../lib/workflow-store.js";
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const TEMPLATES_DIR = join(__dirname, "..", "templates", "workflow-profiles");
+
+const args = process.argv.slice(2);
+
+function listTemplates() {
+  if (!existsSync(TEMPLATES_DIR)) return [];
+  return readdirSync(TEMPLATES_DIR)
+    .filter((f) => f.endsWith(".json"))
+    .map((f) => f.replace(/\.json$/, ""));
+}
+
+function printUsage() {
+  console.log("Usage: slack-mcp --apply-template <template-name> [--channels C012,C067] [--priority-people U0PRIME,U0SECONDARY] [--profile-name custom-name]");
+  console.log("");
+  console.log("Available templates:");
+  for (const t of listTemplates()) {
+    console.log("  " + t);
+  }
+  console.log("");
+  console.log("Example:");
+  console.log("  slack-mcp --apply-template support-triage --channels C012345,C067890");
+  console.log("");
+  console.log("Templates write to ~/.slack-mcp-workflows.json. The hosted AI brain at");
+  console.log("mcp.revasserlabs.com (free tier or Pro $9/mo) reads these profiles and");
+  console.log("returns structured JSON per the workflow_kind. The OSS package ships the");
+  console.log("profile primitives + 3 discoverable upgrade stubs (slack_smart_search,");
+  console.log("slack_catch_me_up, slack_triage). The brain is hosted-only.");
+}
+
+function parseFlag(flag) {
+  const idx = args.indexOf(flag);
+  if (idx === -1) return null;
+  return args[idx + 1];
+}
+
+const templateName = args[0];
+if (!templateName || templateName === "--help" || templateName === "-h") {
+  printUsage();
+  process.exit(templateName ? 0 : 1);
+}
+
+if (templateName.startsWith("--") || templateName.startsWith("-")) {
+  console.error(`Missing template name. Got "${templateName}" as the first positional argument.`);
+  console.error("");
+  printUsage();
+  process.exit(1);
+}
+
+const templatePath = join(TEMPLATES_DIR, `${templateName}.json`);
+if (!existsSync(templatePath)) {
+  console.error(`Template "${templateName}" not found at ${templatePath}`);
+  console.error("");
+  console.error("Available templates: " + listTemplates().join(", "));
+  process.exit(1);
+}
+
+let template;
+try {
+  template = JSON.parse(readFileSync(templatePath, "utf-8"));
+} catch (err) {
+  console.error(`Failed to parse template "${templateName}": ${err.message}`);
+  process.exit(1);
+}
+
+const channelsArg = parseFlag("--channels");
+const priorityArg = parseFlag("--priority-people");
+const profileNameOverride = parseFlag("--profile-name");
+
+const profile = {
+  profile_name: profileNameOverride || template.profile_name,
+  workflow_kind: template.workflow_kind,
+  channels: channelsArg ? channelsArg.split(",").map((s) => s.trim()).filter(Boolean) : (template.channels || []),
+  priority_people: priorityArg ? priorityArg.split(",").map((s) => s.trim()).filter(Boolean) : (template.priority_people || []),
+  retention_mode: template.retention_mode || "ephemeral",
+  summary_cadence: template.summary_cadence || "on_demand",
+};
+
+const result = saveProfile(profile);
+if (!result.ok) {
+  console.error("Failed to save profile:");
+  for (const err of result.errors) console.error("  " + err);
+  process.exit(1);
+}
+
+console.log(`Saved workflow profile "${result.profile_name}" to ~/.slack-mcp-workflows.json`);
+console.log(JSON.stringify(result.profile, null, 2));
+console.log("");
+if (!profile.channels.length) {
+  console.log("Note: no channels set. Add channels with:");
+  console.log(`  slack-mcp --apply-template ${templateName} --channels C012345,C067890`);
+  console.log("Or call slack_workflow_save from your MCP client to update.");
+} else {
+  console.log("Profile is ready. Run slack_catch_me_up against it from your MCP client.");
+  console.log(`(Free tier: 3 catch_me_up calls/month. Pro $9/mo unlocks unlimited; scheduled morning DM rolling out Q2 2026.)`);
+}

package/scripts/setup-wizard.js

@@ -148,6 +148,9 @@ async function runMacOSSetup(rl) {
       print("  1. Chrome is running");
       print("  2. You have a Slack tab open (app.slack.com)");
       print("  3. You're logged into that workspace");
+      print();
+      print(`${colors.dim}Chrome-free or non-macOS? Hosted tier bypasses Chrome entirely:${colors.reset}`);
+      print(`${colors.dim}  https://mcp.revasserlabs.com${colors.reset}`);
     }
     print();
 
@@ -283,6 +286,9 @@ async function runManualSetup(rl) {
     print("  • Tokens expired - try refreshing Slack and copying again");
     print("  • Wrong workspace - make sure you copied from the right tab");
     print("  • Incomplete copy - ensure you got the full token/cookie");
+    print();
+    print(`${colors.dim}Tired of paste-the-token loops? Hosted tier uses OAuth:${colors.reset}`);
+    print(`${colors.dim}  https://mcp.revasserlabs.com${colors.reset}`);
     return false;
   }
 
@@ -402,6 +408,9 @@ async function runDoctor() {
     print();
     print("Next action:");
     print("  npx -y @jtalk22/slack-mcp --setup");
+    print();
+    print(`${colors.dim}Prefer no local tokens? Hosted tier uses OAuth:${colors.reset}`);
+    print(`${colors.dim}  https://mcp.revasserlabs.com${colors.reset}`);
     process.exit(1);
   }
 
@@ -424,6 +433,9 @@ async function runDoctor() {
     print("Next action:");
     if (exitCode === 2) {
       print("  npx -y @jtalk22/slack-mcp --setup");
+      print();
+      print(`${colors.dim}Tokens expire every 1-2 weeks. Hosted tier has permanent OAuth:${colors.reset}`);
+      print(`${colors.dim}  https://mcp.revasserlabs.com${colors.reset}`);
     } else {
       print("  Check network connectivity and retry:");
       print("  npx -y @jtalk22/slack-mcp --doctor");
@@ -460,6 +472,10 @@ async function showHelp() {
   print();
   print(`${colors.bold}More info:${colors.reset}`);
   print("  https://github.com/jtalk22/slack-mcp-server");
+  print();
+  print(`${colors.bold}Hosted tier:${colors.reset}`);
+  print("  https://mcp.revasserlabs.com — $9/mo Pro, permanent OAuth,");
+  print("  semantic search, workflow continuity across channels.");
 }
 
 async function main() {
@@ -530,6 +546,9 @@ async function main() {
       print("  • Verify: npx -y @jtalk22/slack-mcp --status");
       print("  • Start server: npx -y @jtalk22/slack-mcp");
       print("  • Or add to Claude Desktop config");
+      print();
+      print(`${colors.dim}Want permanent tokens, semantic search, and workflow continuity?${colors.reset}`);
+      print(`${colors.dim}Hosted tier: https://mcp.revasserlabs.com — $9/mo Pro, 10 free paid calls.${colors.reset}`);
     } else {
       print(`${colors.red}Setup failed.${colors.reset} See errors above.`);
       process.exit(1);

package/server.json

@@ -2,7 +2,7 @@
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
   "name": "io.github.jtalk22/slack-mcp-server",
   "title": "Slack MCP Server",
-  "description": "Slack MCP without OAuth — no app registration, no admin approval. Works with Claude Code, Cursor, Copilot (where the official server doesn't). 16 tools, one command.",
+  "description": "Slack MCP without OAuth. 21 tools (16 read/write Slack + 2 workflow profile primitives + 3 hosted-brain upgrade stubs). Free OSS or hosted (free tier no card; $9/mo Pro = unlimited; morning DM rolling out Q2 2026).",
   "websiteUrl": "https://mcp.revasserlabs.com",
   "icons": [
     {
@@ -17,7 +17,7 @@
     "url": "https://github.com/jtalk22/slack-mcp-server",
     "source": "github"
   },
-  "version": "4.1.2",
+  "version": "4.2.1",
   "remotes": [
     {
       "type": "streamable-http",
@@ -28,7 +28,7 @@
     {
       "registryType": "npm",
       "identifier": "@jtalk22/slack-mcp",
-      "version": "4.1.2",
+      "version": "4.2.1",
       "transport": {
         "type": "stdio"
       },

package/smithery.yaml

@@ -1,5 +1,7 @@
 # Smithery configuration for slack-mcp-server
 # https://smithery.ai/docs/build/project-config/smithery-yaml
+# Slack MCP — free OSS or hosted (free tier + $9/mo Pro). 21 tools:
+# read/write Slack + workflow profile primitives + AI brain via hosted upgrade.
 
 startCommand:
   type: stdio

package/src/cli.js

@@ -34,6 +34,9 @@ if (firstArg === "web") {
 } else if (firstArg === "http") {
   scriptPath = join(__dirname, "server-http.js");
   scriptArgs = args.slice(1);
+} else if (firstArg === "--apply-template" || firstArg === "apply-template") {
+  scriptPath = join(__dirname, "../scripts/apply-template.js");
+  scriptArgs = args.slice(1);
 } else if (WIZARD_ARGS.has(firstArg)) {
   scriptPath = join(__dirname, "../scripts/setup-wizard.js");
   scriptArgs = args;

package/src/server.js

@@ -46,6 +46,11 @@ import {
   handleConversationsMark,
   handleConversationsUnreads,
   handleUsersSearch,
+  handleWorkflowSave,
+  handleWorkflows,
+  handleSmartSearch,
+  handleCatchMeUp,
+  handleTriage,
 } from "../lib/handlers.js";
 
 // Background refresh interval (4 hours)
@@ -275,6 +280,23 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
       case "slack_users_search":
         return await handleUsersSearch(args);
 
+      // Workflow profile primitives (OSS local JSON store)
+      case "slack_workflow_save":
+        return await handleWorkflowSave(args);
+
+      case "slack_workflows":
+        return await handleWorkflows(args);
+
+      // Hosted-only AI tools (OSS = upgrade stubs)
+      case "slack_smart_search":
+        return await handleSmartSearch(args);
+
+      case "slack_catch_me_up":
+        return await handleCatchMeUp(args);
+
+      case "slack_triage":
+        return await handleTriage(args);
+
       default:
         return {
           content: [{

package/templates/workflow-profiles/customer-feedback.json

@@ -0,0 +1,10 @@
+{
+  "profile_name": "customer-feedback",
+  "workflow_kind": "product_launch_watch",
+  "channels": [],
+  "priority_people": [],
+  "retention_mode": "persistent",
+  "summary_cadence": "daily_8am",
+  "structured_keys": ["launch_signals", "feedback_themes", "blockers", "metrics", "next_actions"],
+  "_template_notes": "Apply with: slack-mcp --apply-template customer-feedback --channels C0FEEDBACK,C0CUSTOMERS,C0SUPPORT. retention_mode=persistent so feedback themes accumulate across days. Weekly synthesis becomes more valuable as the index grows."
+}

package/templates/workflow-profiles/exec-monday.json

@@ -0,0 +1,10 @@
+{
+  "profile_name": "exec-monday",
+  "workflow_kind": "exec_brief",
+  "channels": [],
+  "priority_people": [],
+  "retention_mode": "ephemeral",
+  "summary_cadence": "weekly_monday",
+  "structured_keys": ["summary", "decisions", "risks", "asks", "action_items"],
+  "_template_notes": "Apply with: slack-mcp --apply-template exec-monday --channels C0EXEC,C0PRODUCT,C0OPS --priority-people U0CEO,U0CTO. Weekly Monday cadence requires Pro or Team. Posts a structured brief to your DM at 8am workspace time on Mondays."
+}

package/templates/workflow-profiles/incident-room.json

@@ -0,0 +1,10 @@
+{
+  "profile_name": "incident-room",
+  "workflow_kind": "incident_room",
+  "channels": [],
+  "priority_people": [],
+  "retention_mode": "persistent",
+  "summary_cadence": "on_demand",
+  "structured_keys": ["incident_summary", "timeline", "open_risks", "owner_gaps", "next_actions"],
+  "_template_notes": "Apply with: slack-mcp --apply-template incident-room --channels C0INCIDENTS --priority-people U0ONCALL. on_demand cadence — call slack_catch_me_up at handoff or before stakeholder updates. retention_mode=persistent so post-incident review has the timeline."
+}

package/templates/workflow-profiles/oncall-handoff.json

@@ -0,0 +1,10 @@
+{
+  "profile_name": "oncall-handoff",
+  "workflow_kind": "incident_room",
+  "channels": [],
+  "priority_people": [],
+  "retention_mode": "persistent",
+  "summary_cadence": "on_demand",
+  "structured_keys": ["incident_summary", "timeline", "open_risks", "owner_gaps", "next_actions"],
+  "_template_notes": "Apply with: slack-mcp --apply-template oncall-handoff --channels C012345,C067890 --priority-people U0PRIME,U0SECONDARY. retention_mode=persistent so the next responder can see prior incident context. Run slack_catch_me_up against this profile before each handoff."
+}

package/templates/workflow-profiles/sprint-tracker.json

@@ -0,0 +1,10 @@
+{
+  "profile_name": "sprint-tracker",
+  "workflow_kind": "product_launch_watch",
+  "channels": [],
+  "priority_people": [],
+  "retention_mode": "ephemeral",
+  "summary_cadence": "daily_8am",
+  "structured_keys": ["launch_signals", "feedback_themes", "blockers", "metrics", "next_actions"],
+  "_template_notes": "Apply with: slack-mcp --apply-template sprint-tracker --channels C0SPRINT,C0BUGS,C0LAUNCHES. Use during active release cycles. Returns structured JSON so downstream automation (Linear, Notion, status dashboards) can consume directly."
+}

package/templates/workflow-profiles/support-triage.json

@@ -0,0 +1,10 @@
+{
+  "profile_name": "support-triage",
+  "workflow_kind": "support_inbox",
+  "channels": [],
+  "priority_people": [],
+  "retention_mode": "ephemeral",
+  "summary_cadence": "daily_8am",
+  "structured_keys": ["open_threads", "ack_lag", "owner_gaps", "escalations", "next_actions"],
+  "_template_notes": "Apply with: slack-mcp --apply-template support-triage --channels C0SUPPORT,C0ESCALATIONS. summary_cadence=daily_8am needs Pro or Team for the scheduled morning DM (rolling out Q2 2026). Free tier can run on_demand."
+}