mcpField
C
Claude Memory MCP Server

Claude Memory MCP Server

Local
github.com/WhenMoon-afkMemory & Knowledge69Updated 5w ago
Repository

About Claude Memory MCP Server

Mooncite is a local memory MCP server that lets coding agents recall past context from Pi, OMP, Claude Code, Codex, and ChatGPT history on the same machine. Its inspect tool checks each citation against the original source file before an agent relies on it.

Key features

  1. 01Searches authorized local history sources
  2. 02Inspects citations against current source bytes
  3. 03Reports coverage and health without transcript text
  4. 04Combines lexical search with local embeddings

Use cases

  1. 01Recovering earlier context without repeating explanations
  2. 02Verifying a cited passage before relying on it

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "claude-memory": {
      "command": "npx",
      "args": [
        "-y",
        "@whenmoon-afk/memory-mcp"
      ]
    }
  }
}
Run commandnpx -y @whenmoon-afk/memory-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@whenmoon-afk/memory-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Mooncite

Mooncite lets coding agents recover past context without asking you to explain it again. It searches authorized Pi, OMP, Claude Code, Codex, and ChatGPT history stored on this machine. Before an agent relies on a result, mooncite_inspect checks the citation against the original file. That confirms where the text came from. It does not prove the text is still true.

Mooncite was formerly Claude Memory MCP. The repository keeps its old claude-memory-mcp URL.

flowchart LR
    H[Human] -->|installs| M[Mooncite]
    A[Coding agent<br/>Pi, OMP, Codex, Claude Code] -->|recall and inspect| M
    M -->|reads only| S[Local history<br/>Pi, OMP, Claude Code, Codex, ChatGPT]
    M <--> I[(Search index)]
    M -->|cited context| A

Install

Mooncite requires Linux with procfs, Node.js 24 or newer, npm, and access to GitHub. Packaged local embeddings are Linux x64 only. Other Linux architectures still install and search lexically.

npx --yes github:WhenMoon-afk/claude-memory-mcp#v4.0.7 install

Tagged v4.0.7 is the current stable release. After installation, check the launcher. Then fully restart or reload each client whose registration is exact:

"$HOME/.local/bin/mooncite" status

The installer configures available Pi, OMP, Codex, and Claude Code clients. ChatGPT is a source, not a client. See operations for source setup, ChatGPT exports, removal commands, and quick fixes.

First search

Recall runs inside a configured client. It is not a shell command. Give the agent one distinctive phrase:

Call mooncite_recall with "". Start without a scope. If it returns a candidate, inspect that candidate's evidence_id with mooncite_inspect. Treat verified as proof that the cited text still matches its source file. It does not prove the text is true.

Mooncite exposes exactly three tools:

  • mooncite_recall searches bounded local evidence. An unquoted query of at least two terms may add local embedding matches after no strong lexical hit.
  • mooncite_inspect checks a locator against current source bytes.
  • mooncite_status reports coverage and health without transcript text.

Read next

  • Agent workflow tells an agent when to recall, narrow, inspect, and recover.
  • MCP protocol lists exact tool inputs and outcomes.
  • Operations covers install, source configuration, status, rebuild, disable, uninstall, and purge.
  • Architecture explains the engine, index, and clients.
  • Security explains source containment, local data handling, and deletion limits.

Mooncite never writes source history. Text returned through MCP becomes model context and is subject to that model provider's data handling.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.