Skip to main content
MCP server CX Codex

Memwyre — Claude Code MCP server: what it does, how to install

External shared memory layer for AI agents. Retains knowledge and facts across multiple coding sessions via MCP.

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http memwyre https://server.memwyre.tech/mcp/
Open on GitHub

What Memwyre does

The server provides a shared long-term memory store for developer assistants. It groups user notes by workspace and lowers the priority of outdated details using an Ebbinghaus logarithmic curve. This avoids token waste in long prompts.

Under the hood, the MCP layer surfaces three core tools: save_memory, search_memory, and get_document. The architecture couples a FastAPI application with Celery task queues, SQLite or PostgreSQL for records, and vector backends like Pinecone or ChromaDB.

Connecting through MCP requires network access to https://server.memwyre.tech/mcp/. Auto-captured entries route to an inbox first, so you can discard noisy facts before vector indexing commits them.

What it helps with

  • persist developer context across distinct chat sessions
  • locate recorded technical decisions using search_memory
  • isolate facts into project-specific containers
  • discard obsolete preferences to prevent token bloat

Example prompts for the agent

  • Store this database migration plan in Memwyre using save_memory
  • Find our earlier API design notes with search_memory
  • Fetch the linked specification text via get_document

How to install Memwyre

Platform CLI: remote server

claude mcp add --transport http memwyre https://server.memwyre.tech/mcp/

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Memwyre

How to install Memwyre in Claude Code?

Run claude mcp add --transport http memwyre https://server.memwyre.tech/mcp/ in your terminal. This registers the remote HTTP endpoint in your configuration.

What does Memwyre do?

It functions as an external store for conversation history and project notes. Coding agents query it to fetch past facts without resetting context between sessions.

Which tools does the Memwyre MCP server expose?

It provides save_memory to store new facts, search_memory to run vector queries, and get_document to inspect stored documents.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor