Local-first memory layer for AI agents - 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.
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.
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.
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 revisionsRead — only health checks:** doctor verifies the runtime; lint findsOperation — What Wenlan doesCapture — Agents write one complete, self-contained idea per Memory, following the Zettelkasten atomic-note principle instead of saving the whole conversationClassify — With the on-device model, Wenlan assigns identity, preference, decision, lesson, gotcha, or fact; a precise type supplied by the caller remainsEnrich — With the on-device model, adds structured fields, retrieval cues, event dates, quality, importance, and tags when availableLink — Retains provenance and, when enrichment is enabled, connects Memories to entities and relations in the knowledge graphReconcile — Explicit replacements preserve a supersedes chain. An optional on-device pass can queue protected conflicts for review instead of overwritingDistill — Compiles related Sources and Memories into one Markdown PageCite — Retains citation records and verification status; automatic refresh discards a draft when its citation-support check failsTrack — Records which evidence supports the Page, why it became stale, and a bounded changelogRefresh — When a Page is marked stale, rebuilds the eligible machine-maintained Page from current evidencePlenty 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.
| Tool | What it does |
|---|---|
| Citation | gated refresh:** Automatic refresh rejects citation-poor drafts; machine Pages update while human edits become reviewable revisions. |
| Read | only 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 |
| 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 authoritative. |
| 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 history; it is off by default and must be explicitly enabled. |
| 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. |
| Review | Turns changes to a Page you edited into a proposed revision instead of a silent rewrite. |
| Benchmark | Recall@5 |
{
"mcpServers": {
"wenlan": {
"command": "npx",
"args": ["-y", "wenlan"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.