Skip to main content
MCP server CX Codex

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

Remote long-term memory server for AI agents with hybrid retrieval, write-time conflict detection, and EU hosting.

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

What memra does

The server keeps project conventions, technical decisions, and context across separate agent runs. It combines vector semantics with BM25 keyword matching, which helps agents look up exact error messages or variable names. When storing a new observation, the service spots clashes against existing records and flags conflicts so the agent can retire superseded facts.

Calls go to the remote HTTP endpoint at https://usememra.com/mcp. You need an API token from usememra.com before connecting your client. Infrastructure runs in Helsinki and includes PII masking across seven European languages. Teams seeking a self-contained setup can run the offline memra-local package with SQLite and ONNX embeddings.

What it helps with

  • keep architectural decisions across independent agent sessions
  • locate exact symbol names and error codes with BM25 hybrid lookup
  • detect contradicting statements before saving new records
  • fit retrieved context into a strict token budget

Example prompts for the agent

  • Remember that we enforce strict input validation on all auth endpoints
  • Recall our decisions regarding database migrations and foreign key constraints
  • Check memory for the error code ERR_PAYMENT_TIMEOUT and show its history

How to install memra

Platform CLI: remote server

claude mcp add --transport http memra https://usememra.com/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 memra

How to install memra in Claude Code?

Run claude mcp add --transport http memra https://usememra.com/mcp. You will also need to pass your authorization token in the request header.

What does memra do?

It provides persistent external memory for AI coding agents. The server stores facts, surfaces conflicting information on write, and retrieves past context using lexical and semantic search.

Is an internet connection required to use memra?

The primary MCP server connects to https://usememra.com/mcp and requires an API key. For environments without web access, you can run memra-local using SQLite and local ONNX models.

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