Developer · Local MCP server
Memdocs
Git-native project memory for AI assistants with audit compliance.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.silversurfer562/memdocs- Version
- 2.1.4
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2025-12-05
- Updated
- 2025-12-05
- Publisher
- silversurfer562 (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/silversurfer562) · how
- Repository
- github.com/Smart-AI-Memory/memdocs
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPIruntime: uvx | memdocs | 2.1.4 | stdio |
How to connect Memdocs
Memdocs runs locally from a Python package published to PyPI: memdocs version 2.1.4. 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 memdocs. It reads these environment variables: PROJECT_ROOT and ANTHROPIC_API_KEY (required, 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": {
"memdocs": {
"command": "uvx",
"args": [
"memdocs"
],
"env": {
"PROJECT_ROOT": "<value>",
"ANTHROPIC_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 developer servers
| Server | Runs |
|---|---|
| Mem ContextTemporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation. | Local · stdio |
| Mem0 CloudA hosted agent-memory API shaped like mem0's REST API (an alternative to running mem0 yourself):... | Remote · HTTPLive check: ✓ handshake |
| MemAuthorityGit-backed long-term memory authority for AI agents via MCP. | Local · stdio |
| MemCellLiving memory for AI coding agents: recall before acting, report outcomes so confidence is earned. | Remote & Local · HTTP, stdioLive check: sign-in required |
| MementoLocal-first, LLM-agnostic memory layer for AI assistants. | Local · stdio |
| MementoAgent memory MCP server with 4-type cognitive memory, hybrid search, and TTL-based forgetting. | Local · stdio |
| MementoHosted MCP memory for coding agents: persistent across sessions, editable markdown, team sharing. | Remote · HTTPLive check: sign-in required |
| memexPersistent memory for AI agents - semantic + recency search, ONNX embeddings, Docker Compose. | Local · HTTP |