8739805f99
Some checks failed
Auto-update PR branches / Update open PR branches (push) Has been cancelled
CI / Frontend Static Quality Checks (push) Has been cancelled
CI / Frontend Tests & Coverage (push) Has been cancelled
CI / Rust Tests & Quality Checks (push) Has been cancelled
CI / Linux build verification (push) Has been cancelled
Release (Alpha) / Compute alpha version (push) Has been cancelled
Release (Alpha) / Build release artifacts (push) Has been cancelled
Release (Alpha) / GitHub Release (alpha) (push) Has been cancelled
Release (Alpha) / Update docs and release pages (push) Has been cancelled
Deploy docs / Build VitePress site (push) Has been cancelled
Deploy docs / Deploy to GitHub Pages (push) Has been cancelled
1.9 KiB
1.9 KiB
type, id, title, status, date
| type | id | title | status | date |
|---|---|---|---|---|
| ADR | 0011 | MCP server for AI tool integration | active | 2026-02-28 |
Context
Laputa's AI features (agent panel, chat) need structured access to vault data — searching notes, reading content, editing frontmatter, and steering the UI. Rather than building a bespoke API, the Model Context Protocol (MCP) provides a standardized tool interface that works with Claude Code, Cursor, and any MCP-compatible client.
Decision
Laputa ships a Node.js MCP server (mcp-server/) that exposes vault operations as 14 tools. It runs on stdio for external clients and on two WebSocket ports (9710 for tool calls, 9711 for UI actions) for the embedded Laputa frontend. Tauri spawns the server on startup and auto-registers it in Claude Code and Cursor configs.
Options considered
- Option A (chosen): Node.js MCP server with stdio + WebSocket dual transport — standard MCP compatibility, works with Claude Code/Cursor out of the box, WebSocket enables real-time UI steering. Downside: Node.js dependency, two extra ports.
- Option B: Rust-native MCP server — no Node.js dependency. Downside: MCP SDK is JavaScript-first, Rust implementation would be custom and harder to maintain.
- Option C: Custom REST/gRPC API — full control. Downside: no compatibility with existing AI tool ecosystems, each client needs a custom integration.
Consequences
- Vault tools (search, read, create, edit, delete, link) are available to any MCP-compatible client.
- Auto-registration in
~/.claude/mcp.jsonand~/.cursor/mcp.jsonmeans zero setup for users. - The WebSocket bridge enables real-time UI actions (highlight elements, open notes, set filters) from AI tools.
mcp-server/is bundled into release builds and spawned as a child process bymcp.rs.- Port conflicts on 9710/9711 are handled gracefully (EADDRINUSE tolerance).
- Re-evaluation trigger: if MCP SDK gains a Rust implementation that eliminates the Node.js dependency.