Agent MCP Server

Cross-session memory for AI agents - knowledge graph, scoring, semantic search

Local serverstdioPython

What is the Agent MCP server?

Connect Agent to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Cross-session memory for AI agents - knowledge graph, scoring, semantic search. The agent mcp server is what makes that connection.

What the server does

Knowledge base with category filtering TF-IDF ranked session search

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Cursor — JSONL
  • Aider — Markdown/JSONL
  • Continue.dev — JSON
  • Cline — JSON
  • OpenCode — SQLite
  • Method — Endpoint
  • GET — /api/knowledge
  • POST — /api/knowledge
  • Search — Response shape: {mode: "general" | "scoped", sessions, knowledge}. Scoped mode returns knowledge: [] by design
  • Sessions — The Sessions tool exposed by this server
  • Analysis — The Analysis tool exposed by this server
  • Admin — The Admin tool exposed by this server

Installation

The server ships on npm as agent-knowledge, 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.

Where it fits

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. Agent's toolset — Cursor, Aider, Continue.dev and 9 more — is a fair guide to whether it matches your workflow. It is maintained by keshrath; 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We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

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

Available tools

ToolWhat it does
CursorJSONL
AiderMarkdown/JSONL
Continue.devJSON
ClineJSON
OpenCodeSQLite
MethodEndpoint
GET/api/knowledge
POST/api/knowledge
SearchResponse shape: {mode: "general" | "scoped", sessions, knowledge}. Scoped mode returns knowledge: [] by design.
SessionsThe Sessions tool exposed by this server.
AnalysisThe Analysis tool exposed by this server.
AdminThe Admin tool exposed by this server.

How to install the Agent MCP server

{
  "mcpServers": {
    "agent-knowledge": {
      "command": "npx",
      "args": ["agent-knowledge"]
    }
  }
}

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

Example prompts to try

  • Use Agent to Cursor.
  • Use Agent to Aider.
  • Use Agent to Continue.dev.

Frequently asked questions

It connects Agent to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (Cursor, Aider, Continue.dev, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agent directly.