Data · Local MCP server

Memwright

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.bolnet/memwright
Version
0.1.3
Status
Active
Category
data
Transport
stdio (local process)
Package
PyPI
Published
2026-03-09
Updated
2026-03-09
Publisher
bolnet (GitHub) · 2 servers with pages here
Repository
github.com/bolnet/agent-memory
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPImemwright0.1.3stdioPG_CONNECTION_STRING, NEO4J_PASSWORD (secret), OPENROUTER_API_KEY (secret), OPENAI_API_KEY (secret)

How to connect Memwright

Memwright runs locally from a Python package published to PyPI: memwright version 0.1.3. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx memwright. It reads these environment variables: PG_CONNECTION_STRING, NEO4J_PASSWORD (secret), OPENROUTER_API_KEY (secret) and OPENAI_API_KEY (secret); set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "memwright": {
      "command": "uvx",
      "args": [
        "memwright"
      ],
      "env": {
        "PG_CONNECTION_STRING": "<value>",
        "NEO4J_PASSWORD": "<secret>",
        "OPENROUTER_API_KEY": "<secret>",
        "OPENAI_API_KEY": "<secret>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from bolnet (GitHub)

ServerRunsEndpoint or package
AttestorSelf-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.Local · stdioPyPI: attestor

More data servers

All 4,395 →
ServerRunsEndpoint or package
Memory for AILocal codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.Local · stdionpm: memory-for-ai-mcp
Memory Nexus MCPPersistent semantic memory for AI agents with knowledge graphs and Intelligence Packs.Local · stdionpm: @memory-nexus/mcp
Memory OS AIAdaptive memory for AI agents — FAISS search, chat extraction, cross-project linking.Local · stdioPyPI: memory-os-ai
MemorySyncPersistent memory for AI agents. Search and store durable facts, preferences and decisions.Remote · HTTPmcp.memorysync.io
MemwyreUniversal persistent memory and knowledge retrieval layer for AI agents and LLMs.Remote · HTTPserver.memwyre.tech
MenhthienConnect astrology chart data from menhthien.com to Claude Desktop and MCP-compatible AI assistants.Local · stdionpm: menhthien
Meok Bs7121 MCPBS 7121 lift-plan compliance for UK crane + hiab operators. Parts 1/3/4/5 clause lookup, Appointed.Local · stdioPyPI: meok-bs7121-mcp
Meok Omnibus Tracker MCPEU Digital Omnibus AI Act tracker - Track delay status by article. First-mover advantage for SEO + b.Local · stdioPyPI: meok-omnibus-tracker-mcp