memory-mcp
A local stdio MCP server that exposes a shared brain (read/search/write) over ~/.claude/memory, allowing memories written in any agent to be readable and searchable across all three (Claude Code, Cursor, Codex). It provides tools like memory_search, memory_read, memory_write, etc., with no external services.
README
memory-mcp — shared-brain MCP server
A local stdio MCP server over ~/.claude/memory.
Exposes the LLM-Wiki brain (read / search / write) so a memory written in any
agent — Claude Code, Cursor, Codex — is readable and searchable in all three.
One brain, three clients, file-backed, no external service.
Tools
| Tool | What it does |
|---|---|
memory_search |
Text + frontmatter ranking over name/description/tags/body (+ bucket filter, limit). |
memory_read |
One memory by name → frontmatter + body + resolved outbound [[wikilinks]]. |
memory_list |
List memories (name, type, description), optional bucket filter. |
memory_links |
Inbound + outbound wikilink neighbours for a memory. |
memory_write |
Create/update a memory, regenerate MEMORY.md + hot.md, run the brain lint. A failed lint fails the write (file left for inspection). |
Architecture
- Standalone TypeScript (ESM, strict +
exactOptionalPropertyTypes), run viatsx. - Reads use a strict-typed parser/scanner; a corpus-parity test asserts agreement with the real brain so frontmatter never drifts.
- Writes delegate index/hot/lint to the existing
~/.claude/tools/braintoolkit (subprocess,CLAUDE_DIR-scoped) — brain's exact logic, no source coupling. - Search is text + frontmatter only (no embeddings in v1).
Config
CLAUDE_DIR— brain root (default~/.claude);<CLAUDE_DIR>/memoryholds the buckets.BRAIN_DIR—tools/braincheckout (default<CLAUDE_DIR>/tools/brain).
Run
node node_modules/tsx/dist/cli.mjs src/server.ts # stdio MCP server (stdout = MCP channel)
npm test # vitest
npm run typecheck
Registration in Claude Code / Cursor / Codex: see register.md.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.