Wenlan MCP Server

Local-first memory layer for AI agents - MCP server

Local serverstdioGo

What is the Wenlan MCP server?

Wenlan MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Local-first memory layer for AI agents - MCP server.

What you get

Wenlan turns documents, notes, and past AI conversations into a source-backed knowledge base that stays current as your work evolves. Sources remain traceable; decisions, lessons, and corrections become durable memories; both can support the same maintained Pages.

  • Chat import: — Bring in ChatGPT or Claude export ZIPs; Wenlan automatically skips conversations already imported
  • Document Sources: — Ingest one .md, .txt, or text-extractable .pdf file; recurse through a folder of them; or index Markdown from an Obsidian vault
  • Incremental sync: — Regular file and folder Sources track changes in the background; Obsidian vaults stay read-only and resync on demand
  • Atomic Memory: — MCP clients save one complete decision, lesson, correction, preference, or fact, with provenance and supersession recording where it came from and what it replaces
  • Typed enrichment: — A configured model classifies each Memory, then adds the structured fields defined for its type, plus dates, tags, retrieval cues, and graph links
  • Source-backed Pages: — Distill related Sources and Memories into Markdown Pages with source references and [[wikilinks]]; the daemon can verify and record per-claim citations

Setting it up

The server ships on npm as wenlan, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Wenlan is connected, these are the calls the assistant has available:

  • Citation — gated refresh:** Automatic refresh rejects citation-poor drafts; machine Pages update while human edits become reviewable revisions
  • Read — only health checks:** doctor verifies the runtime; lint finds
  • Operation — What Wenlan does
  • Capture — Agents write one complete, self-contained idea per Memory, following the Zettelkasten atomic-note principle instead of saving the whole conversation
  • Classify — With the on-device model, Wenlan assigns identity, preference, decision, lesson, gotcha, or fact; a precise type supplied by the caller remains
  • Enrich — With the on-device model, adds structured fields, retrieval cues, event dates, quality, importance, and tags when available
  • Link — Retains provenance and, when enrichment is enabled, connects Memories to entities and relations in the knowledge graph
  • Reconcile — Explicit replacements preserve a supersedes chain. An optional on-device pass can queue protected conflicts for review instead of overwriting
  • Distill — Compiles related Sources and Memories into one Markdown Page
  • Cite — Retains citation records and verification status; automatic refresh discards a draft when its citation-support check fails
  • Track — Records which evidence supports the Page, why it became stale, and a bounded changelog
  • Refresh — When a Page is marked stale, rebuilds the eligible machine-maintained Page from current evidence

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Wenlan.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the wenlan mcp server does with a few real requests.

Choosing this one

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Wenlan's toolset — Citation, Read, Operation and 11 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
Citationgated refresh:** Automatic refresh rejects citation-poor drafts; machine Pages update while human edits become reviewable revisions.
Readonly health checks:** [doctor](https://wenlan.app/docs/diagnostics-and-issue-reports) verifies the runtime; [lint](plugin/skills/lint/SKILL.md) finds malformed citations, orphan links, broken embeddings, and search-index
OperationWhat Wenlan does
CaptureAgents write one complete, self-contained idea per Memory, following the Zettelkasten atomic-note principle instead of saving the whole conversation.
ClassifyWith the on-device model, Wenlan assigns identity, preference, decision, lesson, gotcha, or fact; a precise type supplied by the caller remains authoritative.
EnrichWith the on-device model, adds structured fields, retrieval cues, event dates, quality, importance, and tags when available.
LinkRetains provenance and, when enrichment is enabled, connects Memories to entities and relations in the knowledge graph.
ReconcileExplicit replacements preserve a supersedes chain. An optional on-device pass can queue protected conflicts for review instead of overwriting history; it is off by default and must be explicitly enabled.
DistillCompiles related Sources and Memories into one Markdown Page.
CiteRetains citation records and verification status; automatic refresh discards a draft when its citation-support check fails.
TrackRecords which evidence supports the Page, why it became stale, and a bounded changelog.
RefreshWhen a Page is marked stale, rebuilds the eligible machine-maintained Page from current evidence.
ReviewTurns changes to a Page you edited into a proposed revision instead of a silent rewrite.
BenchmarkRecall@5

How to install the Wenlan MCP server

{
  "mcpServers": {
    "wenlan": {
      "command": "npx",
      "args": ["-y", "wenlan"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Wenlan to Citation.
  • Use Wenlan to Read.
  • Use Wenlan to Operation.

Frequently asked questions

It connects Wenlan to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Citation, Read, Operation, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Wenlan directly.