memory-journal-mcp 7.3.0 → 7.5.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +97 -72
- package/dist/{chunk-ZJJD2F5T.js → chunk-VHA46GLM.js} +487 -44
- package/dist/{chunk-CHWIPVQN.js → chunk-XNOUTCRV.js} +809 -164
- package/dist/cli.js +17 -4
- package/dist/index.d.ts +24 -3
- package/dist/index.js +2 -2
- package/dist/{tools-MNMGDTQI.js → tools-HTE4YXMW.js} +1 -1
- package/package.json +2 -1
- package/skills/README.md +7 -1
- package/skills/docker/SKILL.md +262 -0
- package/skills/github-actions/SKILL.md +315 -0
- package/skills/github-commander/SKILL.md +1 -0
- package/skills/github-commander/workflows/copilot-audit.md +48 -0
- package/skills/github-copilot-cli/SKILL.md +64 -0
- package/skills/package.json +6 -1
- package/skills/python/SKILL.md +257 -0
- package/skills/tailwind-css/SKILL.md +268 -0
package/README.md
CHANGED
|
@@ -10,7 +10,7 @@
|
|
|
10
10
|
[](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.neverinfamous/memory-journal-mcp)
|
|
11
11
|
[](SECURITY.md)
|
|
12
12
|
[](https://github.com/neverinfamous/memory-journal-mcp)
|
|
13
|
-
|
|
14
14
|
|
|
15
15
|
|
|
16
16
|
[](https://github.com/neverinfamous/memory-journal-mcp/actions/workflows/gatekeeper.yml)
|
|
@@ -24,57 +24,57 @@
|
|
|
24
24
|
- **[npm Package](https://www.npmjs.com/package/memory-journal-mcp)** - `npm install -g memory-journal-mcp`
|
|
25
25
|
- **[Docker Hub](https://hub.docker.com/r/writenotenow/memory-journal-mcp)** - Alpine-based with full semantic search
|
|
26
26
|
|
|
27
|
-
##
|
|
28
|
-
|
|
29
|
-
### What Sets Us Apart
|
|
30
|
-
|
|
31
|
-
**67 MCP Tools** · **17 Workflow Prompts** · **34 Resources** · **10 Tool Groups** · **Code Mode** · **GitHub Commander** (Issue Triage, PR Review, Milestone Sprints, Security/Quality/Perf Audits) · **GitHub Integration** (Issues, PRs, Actions, Kanban, Milestones, Insights) · **Team Collaboration** (Shared DB, Vector Search, Cross-Project Insights)
|
|
32
|
-
|
|
33
|
-
| Feature | Description |
|
|
34
|
-
| ----------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
35
|
-
| **Session Intelligence** | Agents auto-query project history, create entries at checkpoints, and hand off context between sessions via `/session-summary` and `team-session-summary` |
|
|
36
|
-
| **GitHub Integration** | 18 tools for Issues, PRs, Actions, Kanban, Milestones (%), Copilot Reviews, and 14-day Insights |
|
|
37
|
-
| **Dynamic Project Routing** | Seamlessly switch contexts and access CI/Issue tracking across multiple repositories using a single server instance via `PROJECT_REGISTRY` |
|
|
38
|
-
| **Knowledge Graphs** | 8 relationship types linking specs → implementations → tests → PRs with Mermaid visualization |
|
|
39
|
-
| **Hybrid Search** | Reciprocal Rank Fusion combining FTS5 keywords, semantic vector similarity, auto-heuristics, and date-range filters |
|
|
40
|
-
| **Code Mode** | Execute multi-step operations in a secure sandbox — up to 90% token savings via `mj.*` API |
|
|
41
|
-
| **Configurable Briefing** | 14 env vars / CLI flags control `memory://briefing` content — entries, team, GitHub detail, skills awareness |
|
|
42
|
-
| **Reports & Analytics** | Standups, retrospectives, PR summaries, digests, period analyses, and milestone tracking |
|
|
43
|
-
| **Team Collaboration** | 22 tools with full parity — CRUD, vector search, relationship graphs, cross-project insights, author attribution |
|
|
44
|
-
| **Data Interoperability** | Bidirectional Markdown roundtripping, unified IO namespace, and schema-safe JSON exports with hard bounds-checked path traversal defenses |
|
|
45
|
-
| **Backup & Restore** | One-command backup/restore with automated scheduling, retention policies, and safety-net auto-backups |
|
|
46
|
-
| **Security & Transport** | OAuth 2.1 (RFC 9728/8414, JWT/JWKS, scopes), Streamable HTTP + SSE, rate limiting, CORS, SQL injection prevention, non-root Docker |
|
|
47
|
-
| **Structured Error Handling** | Every tool returns `{success, error, code, category, suggestion, recoverable}` — agents get classification, remediation hints, and recoverability signals |
|
|
48
|
-
| **Agent Collaboration** | IDE agents and Copilot share context; review findings become searchable knowledge; agents suggest reusable rules and skills ([setup](docs/copilot-setup.md)) |
|
|
49
|
-
| **Native Agent Skills** | Bundled foundational coding paradigms (`autonomous-dev`, `bun`, `gitlab`, `golang`, `mysql`, `playwright-standard`, `postgres`, `react-best-practices`, `rust`, `shadcn-ui`, `skill-builder`, `sqlite`, `typescript`, `vitest-standard`) establishing permanent AI behavior and architecture rules |
|
|
50
|
-
| **GitHub Commander** | Pipeline skills for issue triage, PR reviews, sprint milestones, and security/quality/performance audits with journal trails ([docs](skills/github-commander/SKILL.md)) |
|
|
51
|
-
|
|
52
|
-
---
|
|
53
|
-
|
|
54
|
-
## 🎯 Why Memory Journal?
|
|
27
|
+
## 🧠 Stop Experiencing AI Amnesia
|
|
55
28
|
|
|
56
29
|
When managing large projects with AI assistance, you face a critical challenge:
|
|
57
30
|
|
|
58
|
-
- **Thread Amnesia** - Each new AI conversation starts from zero, unaware of previous work
|
|
59
|
-
- **Lost Context** - Decisions, implementations, and learnings scattered across disconnected threads
|
|
60
|
-
- **Repeated Work** - AI suggests solutions you've already tried or abandoned
|
|
61
|
-
- **Context Overload** - Manually copying project history into every new conversation
|
|
31
|
+
- **Thread Amnesia** - Each new AI conversation starts from zero, unaware of previous work.
|
|
32
|
+
- **Lost Context** - Decisions, implementations, and learnings scattered across disconnected threads.
|
|
33
|
+
- **Repeated Work** - AI suggests solutions you've already tried or abandoned.
|
|
34
|
+
- **Context Overload** - Manually copying project history into every new conversation.
|
|
62
35
|
|
|
63
36
|
Memory Journal solves this by acting as your project's **long-term memory**, bridging the gap between fragmented AI sessions.
|
|
64
37
|
|
|
65
38
|
---
|
|
66
39
|
|
|
67
|
-
**
|
|
40
|
+
**Experience true context-aware development:**
|
|
68
41
|
|
|
69
|
-
- "
|
|
70
|
-
- "
|
|
71
|
-
- "
|
|
72
|
-
- "
|
|
42
|
+
- _"Why did we choose SQLite over Postgres for this service last month?"_ (Semantic search)
|
|
43
|
+
- _"Run the `/issue-triage` workflow on the top priority ticket in the Kanban board."_ (GitHub operations)
|
|
44
|
+
- _"Who has been touching the auth module recently, and what's our team collaboration density?"_ (Team analytics)
|
|
45
|
+
- _"Close issue #42 and log an entry explaining our architectural fix for the parsing bug."_ (Context lifecycles)
|
|
46
|
+
- _"Draw a visual graph showing how my last 10 architectural decisions relate to each other."_ (Knowledge graph)
|
|
73
47
|
|
|
74
48
|
**[See complete examples & prompts →](https://github.com/neverinfamous/memory-journal-mcp/wiki/Examples)**
|
|
75
49
|
|
|
76
50
|
---
|
|
77
51
|
|
|
52
|
+
## 🎯 What Sets Us Apart
|
|
53
|
+
|
|
54
|
+
**70 MCP Tools** · **17 Workflow Prompts** · **36 Resources** · **10 Tool Groups** · **Code Mode** · **GitHub Commander** (Issue Triage, PR Review, Milestone Sprints, Security/Quality/Perf Audits) · **GitHub Integration** (Issues, PRs, Actions, Kanban, Milestones, Insights) · **Team Collaboration** (Shared DB, Vector Search, Cross-Project Insights, Hush Protocol Flags)
|
|
55
|
+
|
|
56
|
+
| Feature | Description |
|
|
57
|
+
| ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
58
|
+
| **Session Intelligence** | Agents auto-query project history, create entries at checkpoints, and hand off context between sessions via `/session-summary` and `team-session-summary` |
|
|
59
|
+
| **GitHub Integration** | 18 tools for Issues, PRs, Actions, Kanban, Milestones (%), Copilot Reviews, and 14-day Insights |
|
|
60
|
+
| **Dynamic Project Routing** | Seamlessly switch contexts and access CI/Issue tracking across multiple repositories using a single server instance via `PROJECT_REGISTRY` |
|
|
61
|
+
| **Knowledge Graphs** | 8 relationship types linking specs → implementations → tests → PRs with Mermaid visualization |
|
|
62
|
+
| **Hybrid Search** | Reciprocal Rank Fusion combining FTS5 keywords, semantic vector similarity, auto-heuristics, and date-range filters |
|
|
63
|
+
| **Code Mode** | Execute multi-step operations in a secure sandbox — up to 90% token savings via `mj.*` API |
|
|
64
|
+
| **Configurable Briefing** | 15 env vars / CLI flags control `memory://briefing` content — entries, team, GitHub detail, skills awareness, chronological grounding |
|
|
65
|
+
| **Reports & Analytics** | Standups, retrospectives, PR summaries, digests, period analyses, and milestone tracking |
|
|
66
|
+
| **Hush Protocol (Flags)** | Replace Slack/Teams noise with structured, actionable, and searchable AI flags (blockers, reviews) that automatically surface in session briefings |
|
|
67
|
+
| **Team Collaboration** | 25 tools with full parity — CRUD, vector search, relationship graphs, cross-project insights, author attribution, Hush Protocol flags |
|
|
68
|
+
| **Data Interoperability** | Bidirectional Markdown roundtripping, unified IO namespace, and schema-safe JSON exports with hard bounds-checked path traversal defenses |
|
|
69
|
+
| **Backup & Restore** | One-command backup/restore with automated scheduling, retention policies, and safety-net auto-backups |
|
|
70
|
+
| **Security & Transport** | OAuth 2.1 (RFC 9728/8414, JWT/JWKS, scopes), Streamable HTTP + SSE, rate limiting, CORS, SQL injection prevention, non-root Docker |
|
|
71
|
+
| **Structured Error Handling** | Every tool returns `{success, error, code, category, suggestion, recoverable}` — agents get classification, remediation hints, and recoverability signals |
|
|
72
|
+
| **Agent Collaboration** | IDE agents and Copilot share context; review findings become searchable knowledge; agents suggest reusable rules and skills ([setup](docs/copilot-setup.md)) |
|
|
73
|
+
| **Native Agent Skills** | Bundled foundational coding paradigms (`autonomous-dev`, `python`, `docker`, `tailwind-css`, `golang`, `playwright-standard`, etc.) establishing permanent AI behavior and architecture rules |
|
|
74
|
+
| **GitHub Commander** | Pipeline skills for issue triage, PR reviews, sprint milestones, and security/quality/performance audits with journal trails ([docs](skills/github-commander/SKILL.md)) |
|
|
75
|
+
|
|
76
|
+
---
|
|
77
|
+
|
|
78
78
|
```mermaid
|
|
79
79
|
flowchart TB
|
|
80
80
|
subgraph Session["🤖 AI Session Start"]
|
|
@@ -117,9 +117,12 @@ flowchart TB
|
|
|
117
117
|
|
|
118
118
|
---
|
|
119
119
|
|
|
120
|
-
|
|
120
|
+
<details>
|
|
121
|
+
<summary><strong>🤖 Recommended AI Agent Instructions/Rule</strong></summary>
|
|
121
122
|
|
|
122
|
-
|
|
123
|
+
_Suggested Rule (Add to AGENTS.md, GEMINI.md, system prompts, etc.)_
|
|
124
|
+
|
|
125
|
+
**🛑 MANDATORY SESSION START ROUTINE**
|
|
123
126
|
|
|
124
127
|
Execute BEFORE fulfilling any user request in a new session:
|
|
125
128
|
|
|
@@ -132,8 +135,12 @@ Execute BEFORE fulfilling any user request in a new session:
|
|
|
132
135
|
- **REQUIRED GROUPS**:
|
|
133
136
|
- **GitHub**: Combine Repo, Branch, CI, PRs, and Insights.
|
|
134
137
|
- **GitHub Issues**: List every issue, one per line.
|
|
135
|
-
-
|
|
136
|
-
|
|
138
|
+
- **Active Flags (Hush Protocol)**: If the briefing JSON contains an `activeFlags` object (with `count > 0`), render each flag in a dedicated row using format: `🚩 {flag_type} → @{target_user}: {preview}`. If `count` is 0 or the field is absent, omit the row entirely.
|
|
139
|
+
- Also include Entry Counts (Journal/Team), Latest Entries/Summaries (titles only), Proactive Analytics/Team Density, Milestones, and Workspaces.
|
|
140
|
+
- **FLAG PROMINENCE**: When `activeFlags.count > 0`, prepend a bold callout line **above** the table: `⚠️ **{count} active flag(s)** — review before proceeding.` This ensures blockers and review requests are impossible to miss.
|
|
141
|
+
4. **STOP & WAIT**: Do NOT autonomously resume past tasks or start work on new issues mentioned in the session summary. The briefing is strictly for context.
|
|
142
|
+
|
|
143
|
+
</details>
|
|
137
144
|
|
|
138
145
|
---
|
|
139
146
|
|
|
@@ -146,12 +153,12 @@ Control which tools are exposed via `MEMORY_JOURNAL_MCP_TOOL_FILTER` (or CLI: `-
|
|
|
146
153
|
|
|
147
154
|
| Filter | Tools | Use Case |
|
|
148
155
|
| -------------------- | ----- | ------------------------ |
|
|
149
|
-
| `full` |
|
|
156
|
+
| `full` | 70 | All tools (default) |
|
|
150
157
|
| `starter` | ~11 | Core + search + codemode |
|
|
151
158
|
| `essential` | ~7 | Minimal footprint |
|
|
152
|
-
| `readonly` |
|
|
153
|
-
| `-github` |
|
|
154
|
-
| `-github,-analytics` |
|
|
159
|
+
| `readonly` | 18 | Disable all mutations |
|
|
160
|
+
| `-github` | 52 | Exclude a group |
|
|
161
|
+
| `-github,-analytics` | 48 | Exclude multiple groups |
|
|
155
162
|
|
|
156
163
|
**Filter Syntax:** `shortcut` or `group` or `tool_name` (whitelist mode) · `-group` (disable group) · `-tool` (disable tool) · `+tool` (re-enable after group disable)
|
|
157
164
|
|
|
@@ -165,20 +172,20 @@ Control which tools are exposed via `MEMORY_JOURNAL_MCP_TOOL_FILTER` (or CLI: `-
|
|
|
165
172
|
|
|
166
173
|
## 📋 Core Capabilities
|
|
167
174
|
|
|
168
|
-
### 🛠️ **
|
|
169
|
-
|
|
170
|
-
| Group | Tools | Description
|
|
171
|
-
| --------------- | ----- |
|
|
172
|
-
| `codemode` | 1 | Code Mode (sandboxed code execution) 🌟 **Recommended**
|
|
173
|
-
| `core` | 6 | Entry CRUD, tags, test
|
|
174
|
-
| `search` | 4 | Text search, date range, semantic, vector stats
|
|
175
|
-
| `analytics` | 2 | Statistics, cross-project insights
|
|
176
|
-
| `relationships` | 2 | Link entries, visualize graphs
|
|
177
|
-
| `io` | 3 | JSON/Markdown export and File-level Markdown Data Integration Interoperability (Import/Export)
|
|
178
|
-
| `admin` | 5 | Update, delete, rebuild/add to vector index, merge tags
|
|
179
|
-
| `github` | 18 | Issues, PRs, context, Kanban, **Milestones**, **Insights**, **issue lifecycle**, **Copilot Reviews**
|
|
180
|
-
| `backup` | 4 | Backup, list, restore, cleanup
|
|
181
|
-
| `team` |
|
|
175
|
+
### 🛠️ **70 MCP Tools** (10 Groups)
|
|
176
|
+
|
|
177
|
+
| Group | Tools | Description |
|
|
178
|
+
| --------------- | ----- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
179
|
+
| `codemode` | 1 | Code Mode (sandboxed code execution) 🌟 **Recommended** |
|
|
180
|
+
| `core` | 6 | Entry CRUD, tags, test |
|
|
181
|
+
| `search` | 4 | Text search, date range, semantic, vector stats |
|
|
182
|
+
| `analytics` | 2 | Statistics, cross-project insights |
|
|
183
|
+
| `relationships` | 2 | Link entries, visualize graphs |
|
|
184
|
+
| `io` | 3 | JSON/Markdown export and File-level Markdown Data Integration Interoperability (Import/Export) |
|
|
185
|
+
| `admin` | 5 | Update, delete, rebuild/add to vector index, merge tags |
|
|
186
|
+
| `github` | 18 | Issues, PRs, context, Kanban, **Milestones**, **Insights**, **issue lifecycle**, **Copilot Reviews** |
|
|
187
|
+
| `backup` | 4 | Backup, list, restore, cleanup |
|
|
188
|
+
| `team` | 25 | CRUD, search, stats, relationships, IO (Markdown import/export), backup, vector search, cross-project insights, matrix, **Hush Protocol flags** (requires `TEAM_DB_PATH`) |
|
|
182
189
|
|
|
183
190
|
**[Complete tools reference →](https://github.com/neverinfamous/memory-journal-mcp/wiki/Tools)**
|
|
184
191
|
|
|
@@ -201,14 +208,15 @@ Control which tools are exposed via `MEMORY_JOURNAL_MCP_TOOL_FILTER` (or CLI: `-
|
|
|
201
208
|
- `confirm-briefing` - Acknowledge session context to user
|
|
202
209
|
- `session-summary` - Create a session summary entry with accomplishments, pending items, and next-session context
|
|
203
210
|
- `team-session-summary` - Create a retrospective team session summary entry securely isolated to the team database
|
|
211
|
+
- `load-project-kanban` - Dynamic project board injection
|
|
204
212
|
|
|
205
213
|
**[Complete prompts guide →](https://github.com/neverinfamous/memory-journal-mcp/wiki/Prompts)**
|
|
206
214
|
|
|
207
|
-
### 📡 **
|
|
215
|
+
### 📡 **36 Resources** (27 Static + 9 Template)
|
|
208
216
|
|
|
209
217
|
**Static Resources** (appear in resource lists):
|
|
210
218
|
|
|
211
|
-
- `memory://briefing` - **Session initialization**: compact context for AI agents (~300 tokens)
|
|
219
|
+
- `memory://briefing` - **Session initialization**: compact context for AI agents (~300 tokens) — includes `localTime` and optional `activeFlags`
|
|
212
220
|
- `memory://instructions` - **Behavioral guidance**: complete server instructions for AI agents
|
|
213
221
|
- `memory://recent` - 10 most recent entries
|
|
214
222
|
- `memory://significant` - Significant milestones and breakthroughs
|
|
@@ -233,6 +241,8 @@ Control which tools are exposed via `MEMORY_JOURNAL_MCP_TOOL_FILTER` (or CLI: `-
|
|
|
233
241
|
- `memory://metrics/system` - Process-level metrics: memory (MB), uptime (s), Node.js version, platform — MEDIUM priority
|
|
234
242
|
- `memory://metrics/users` - Per-user call counts (populated when OAuth user identifiers are present) — LOW priority
|
|
235
243
|
- `memory://audit` - Last 50 write/admin tool call entries from the JSONL audit log (requires `AUDIT_LOG_PATH`)
|
|
244
|
+
- `memory://flags` - Active (unresolved) team flags dashboard (requires `TEAM_DB_PATH`)
|
|
245
|
+
- `memory://flags/vocabulary` - Configured flag vocabulary terms
|
|
236
246
|
|
|
237
247
|
**Template Resources** (require parameters, fetch directly by URI):
|
|
238
248
|
|
|
@@ -250,21 +260,21 @@ _Note: The `memory://github/status`, `memory://github/insights`, `memory://githu
|
|
|
250
260
|
|
|
251
261
|
---
|
|
252
262
|
|
|
253
|
-
## Code Mode: Maximum Efficiency
|
|
263
|
+
## ⚡ Code Mode: Maximum Efficiency (90% Token Savings)
|
|
254
264
|
|
|
255
|
-
Code Mode (`mj_execute_code`) dramatically reduces token usage
|
|
265
|
+
Code Mode (`mj_execute_code`) is a revolutionary approach that **dramatically reduces token usage by up to 90%** and is included by default in all presets. Instead of spending thousands of tokens on sequential tool calls, AI agents use a single sandboxed execution to reason faster.
|
|
256
266
|
|
|
257
267
|
Code executes in a **sandboxed VM context** with multiple layers of security. All `mj.*` API calls execute against the journal within the sandbox, providing:
|
|
258
268
|
|
|
259
269
|
- **Static code validation** — blocked patterns include `require()`, `process`, `eval()`, and filesystem access
|
|
260
270
|
- **Rate limiting** — 60 executions per minute per client
|
|
261
271
|
- **Hard timeouts** — configurable execution limit (default 30s)
|
|
262
|
-
- **Full API access** — all 10 tool groups are available via `mj.*` (e.g., `mj.core.createEntry()`, `mj.search.searchEntries()`, `mj.github.getGithubIssues()`, `mj.
|
|
272
|
+
- **Full API access** — all 10 tool groups are available via `mj.*` (e.g., `mj.core.createEntry()`, `mj.search.searchEntries()`, `mj.github.getGithubIssues()`, `mj.team.passTeamFlag()`)
|
|
263
273
|
- **Strict Readonly Contract** — Calling any mutation method under `--tool-filter readonly` safely halts the sandbox to prevent execution, returning a structured `{ success: false, error: "..." }` response to the agent instead of a raw MCP protocol exception.
|
|
264
274
|
|
|
265
275
|
### ⚡ Code Mode Only (Maximum Token Savings)
|
|
266
276
|
|
|
267
|
-
Run with **only Code Mode enabled** — a single tool that provides access to all
|
|
277
|
+
Run with **only Code Mode enabled** — a single tool that provides access to all 69 tools' worth of capability through the `mj.*` API:
|
|
268
278
|
|
|
269
279
|
```json
|
|
270
280
|
{
|
|
@@ -291,6 +301,20 @@ If you prefer individual tool calls, exclude codemode:
|
|
|
291
301
|
|
|
292
302
|
---
|
|
293
303
|
|
|
304
|
+
## 🤫 Hush Protocol: Asynchronous Team Collaboration
|
|
305
|
+
|
|
306
|
+
The **Hush Protocol** reimagines team collaboration for AI-augmented workflows by replacing noisy Slack/Teams messages with structured, machine-actionable flags.
|
|
307
|
+
|
|
308
|
+
When you encounter a blocker, need a review, or want to broadcast a milestone, your AI agent can raise a flag in the shared Team Database:
|
|
309
|
+
|
|
310
|
+
- **Actionable Visibility**: Active flags automatically surface at the very top of the `memory://briefing` payload for all team members. When another developer's agent starts a session, it immediately sees your blockers and can help resolve them autonomously.
|
|
311
|
+
- **Structured Types**: Raise specific flag types (`blocker`, `needs_review`, `help_requested`, `fyi`). You can customize your team's vocabulary via the `--flag-vocabulary` configuration.
|
|
312
|
+
- **Searchable History**: Unlike chat messages that disappear into the void, Hush flags are permanent, query-able AI journal entries. Your agents can search past `needs_review` flags to understand how architectural blockers were conquered.
|
|
313
|
+
|
|
314
|
+
**Dashboard & Operations**: Read `memory://flags` to see an active dashboard overview and use `mj.team.passTeamFlag()` / `mj.team.resolveTeamFlag()` to manage them programmatically in Code Mode.
|
|
315
|
+
|
|
316
|
+
---
|
|
317
|
+
|
|
294
318
|
## 🚀 Quick Start
|
|
295
319
|
|
|
296
320
|
### Option 1: npm (Recommended)
|
|
@@ -385,10 +409,10 @@ For remote access or web-based clients, run the server in HTTP mode:
|
|
|
385
409
|
memory-journal-mcp --transport http --port 3000
|
|
386
410
|
```
|
|
387
411
|
|
|
388
|
-
To bind to all interfaces (required for containers):
|
|
412
|
+
To bind to all interfaces (required for containers) and enable the automated proactive analytics scheduler (e.g. daily digest):
|
|
389
413
|
|
|
390
414
|
```bash
|
|
391
|
-
memory-journal-mcp --transport http --port 3000 --server-host 0.0.0.0
|
|
415
|
+
memory-journal-mcp --transport http --port 3000 --server-host 0.0.0.0 --digest-interval 1440
|
|
392
416
|
```
|
|
393
417
|
|
|
394
418
|
**Endpoints:**
|
|
@@ -522,6 +546,7 @@ The GitHub tools (`get_github_issues`, `get_github_prs`, etc.) auto-detect the r
|
|
|
522
546
|
| `AUDIT_READS` | Log read-scoped tool calls in addition to write/admin (CLI: `--audit-reads`; default: `false`) |
|
|
523
547
|
| `AUDIT_LOG_MAX_SIZE` | Maximum audit log file size in bytes before rotation (CLI: `--audit-log-max-size`; default: `10485760`) |
|
|
524
548
|
| `MCP_METRICS_ENABLED` | Set to `false` to disable in-memory tool call metrics accumulation (default: `true`) |
|
|
549
|
+
| `FLAG_VOCABULARY` | Comma-separated flag types for Hush Protocol (CLI: `--flag-vocabulary`; default: `blocker,needs_review,help_requested,fyi`) |
|
|
525
550
|
|
|
526
551
|
**Multi-Project Workflows**: For agents to seamlessly support multiple projects, provide **`PROJECT_REGISTRY`**.
|
|
527
552
|
|
|
@@ -625,7 +650,7 @@ Memory Journal provides a **hybrid approach** to GitHub management:
|
|
|
625
650
|
|
|
626
651
|
### GitHub Commander Workflows
|
|
627
652
|
|
|
628
|
-
The server natively bundles the `github-commander` agent skill (accessible via `memory://skills/github-commander`). This extends your AI assistant with
|
|
653
|
+
The server natively bundles the `github-commander` agent skill (accessible via `memory://skills/github-commander`). This extends your AI assistant with 9 autonomous DevOps workflows for repository stewardship: **Issue Triage**, **Milestone Sprints**, **PR Reviews**, **Copilot Audits**, **Security Audits**, **Code Quality Audits**, **Performance Audits**, **Roadmap Kickoffs**, and **Dependency Updates**. Configure validation layers using the `PROJECT_*` environment overrides to enforce CI-matching execution locally during agent tasks!
|
|
629
654
|
|
|
630
655
|
## 🏗️ Architecture
|
|
631
656
|
|
|
@@ -636,8 +661,8 @@ flowchart TB
|
|
|
636
661
|
AI["🤖 AI Agent<br/>(Cursor, Windsurf, Claude)"]
|
|
637
662
|
|
|
638
663
|
subgraph MCP["Memory Journal MCP Server"]
|
|
639
|
-
Tools["🛠️
|
|
640
|
-
Resources["📡
|
|
664
|
+
Tools["🛠️ 70 Tools"]
|
|
665
|
+
Resources["📡 36 Resources"]
|
|
641
666
|
Prompts["💬 17 Prompts"]
|
|
642
667
|
end
|
|
643
668
|
|
|
@@ -665,7 +690,7 @@ flowchart TB
|
|
|
665
690
|
┌─────────────────────────────────────────────────────────────┐
|
|
666
691
|
│ MCP Server Layer (TypeScript) │
|
|
667
692
|
│ ┌─────────────────┐ ┌─────────────────┐ ┌─────────────┐ │
|
|
668
|
-
│ │ Tools (
|
|
693
|
+
│ │ Tools (70) │ │ Resources (36) │ │ Prompts (17)│ │
|
|
669
694
|
│ │ with Annotations│ │ with Annotations│ │ │ │
|
|
670
695
|
│ └─────────────────┘ └─────────────────┘ └─────────────┘ │
|
|
671
696
|
├─────────────────────────────────────────────────────────────┤
|