Link MCP Server

Link gives Codex, Claude, Cursor, Kiro, VS Code, Copilot, Antigravity, and other local agents the same source-backed memory, stored locally as

Local serverstdioPython

What is the Link MCP server?

Link gives Codex, Claude, Cursor, Kiro, VS Code, Copilot, Antigravity, and other local agents the same source-backed memory, stored locally as Markdown. That is what the link mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Link is an open-source memory layer for local AI agents. Raw sources become an inspectable Markdown wiki. Explicit "remember this" requests become reviewable memories. Agents retrieve compact, source-backed context through the CLI, MCP, official skills, or the local viewer without dumping the whole wiki into a chat window.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

The tools it exposes

The server publishes 9 tools. What each one is for:

  • status — readiness, schema state, validation, interrupted writes, and safe
  • recall — the one read path for startup briefs, answer-ready query packets,
  • remember — durable local memory only after explicit user approval, with
  • ingest — exact next steps for raw files, source safety, stale ingest
  • review — memory inbox, profile, audit, log, explain, archive, restore,
  • admin — the escape hatch for backup, migrate, validate, graph export, pages,
  • Pain — Link's answer
  • What — Link
  • Layer — What lives there

Things to watch

  • 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 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Link.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

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. Link's toolset — status, recall, remember and 6 more — is a fair guide to whether it matches your workflow. It is maintained by gowtham0992; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
statusreadiness, schema state, validation, interrupted writes, and safe
recallthe one read path for startup briefs, answer-ready query packets,
rememberdurable local memory only after explicit user approval, with
ingestexact next steps for raw files, source safety, stale ingest
reviewmemory inbox, profile, audit, log, explain, archive, restore,
adminthe escape hatch for backup, migrate, validate, graph export, pages,
PainLink's answer
WhatLink
LayerWhat lives there

How to install the Link MCP server

```json
{
  "mcpServers": {
    "link": {
      "command": "python3",
      "args": ["-m", "link_mcp", "--wiki", "~/link/wiki", "--surface", "slim"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Link to status.
  • Use Link to recall.
  • Use Link to remember.

Frequently asked questions

It connects Link to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (status, recall, remember, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Link directly.