@pipeshub-ai/mcp 2.3.2 → 2.3.3

package/README.md

@@ -2,10 +2,12 @@
 
 This guide covers how to connect PipesHub's remote MCP server to **Cursor**, **Claude Code**, **Gemini CLI**, **Codex CLI**, **Claude.ai (Web)**, and **LibreChat** using static OAuth credentials or bearer tokens.
 
-PipesHub exposes a remote MCP endpoint over **Streamable HTTP** at `/mcp`.MCP Clients connect to this endpoint directly -- no local npm packages or stdio processes needed.
-
-> **Looking for the tool reference?** See [TOOLS.md](./TOOLS.md) for descriptions, arguments, and a decision guide for each tool the MCP server exposes (`pipeshub_chat`, `pipeshub_search`, `pipeshub_download_record`, `pipeshub_directory`, `pipeshub_sources`).
+PipesHub exposes a remote MCP endpoint over **Streamable HTTP** at `/mcp`. MCP Clients connect to this endpoint directly -- no local npm packages or stdio processes needed.
 
+> **Coding agent?** Start at [For coding agents](https://docs.pipeshub.com/for-agents.md). Install the skill into the *user's* repo with `npx skills add pipeshub-ai/mcp-server` (see [`skills/pipeshub`](./skills/pipeshub/SKILL.md)). Contributors working in this repository: read [AGENTS.md](./AGENTS.md).
+>
+> **Looking for the tool reference?** See [TOOLS.md](./TOOLS.md) for descriptions, arguments, and a decision guide for each tool the MCP server exposes (`pipeshub_chat`, `pipeshub_search`, `pipeshub_get_record_content`, `pipeshub_download_record`, `pipeshub_directory`, `pipeshub_sources`, `pipeshub_agents`).
+>
 > **Using QM?** QM cannot attach a third-party MCP endpoint — it is an MCP *server* to its own harness, not a client. Follow [Use PipesHub with QM](./qm/docs/use-with-qm.md). The deployment-layer bundle in [`qm/`](./qm/) gives agents a `pipeshub` command inside their sandbox; this package ships that command as a second bin.
 
 ## Prerequisites

package/bin/mcp-server.js

@@ -53433,7 +53433,7 @@ var init_pipeshubChat = __esm(() => {
     query: string2().min(1).describe("The user's question or message for this turn."),
     conversationId: string2().optional().describe("Existing conversation id to continue. Omit on the FIRST turn; on every " + "subsequent turn pass the `conversationId` returned by the previous " + "call. Server-side message history is preserved — do NOT replay " + "prior messages."),
     filters: FiltersShape.describe("Source scoping for retrieval. Pass `apps` ids from `pipeshub_sources`. " + "Only meaningful on the FIRST turn (when starting a new conversation)."),
-    modelKey: string2().optional().describe("Model id to use (from `pipeshub_sources` `models[*].modelKey`). " + "Defaults to the org's default LLM."),
+    modelKey: string2().optional().describe("Model id to use (from `pipeshub_sources` `llmModels[*].modelKey`). " + "Defaults to the org's default LLM."),
     modelName: string2().optional(),
     modelFriendlyName: string2().optional(),
     agentId: string2().optional().describe("Optional PipesHub agent to converse with — the `agentId` from " + "`pipeshub_agents`. When set, this turn runs against that agent's " + "configuration (prompt, tools, knowledge). On follow-up turns pass the " + "SAME `agentId` together with the `conversationId` returned by the " + "previous call. Omit for a plain (non-agent) conversation. If unsure " + "which agent to use, call `pipeshub_agents` first to see the options."),
@@ -59234,5 +59234,5 @@ export {
   app
 };
 
-//# debugId=B3EADAB5212D24DD64756E2164756E21
+//# debugId=AB395F463BB257DB64756E2164756E21
 //# sourceMappingURL=mcp-server.js.map