Contextual MCP Server

by contextual-laboratories Your server? Claim it

local only

Contextual runs on your own machine — the client starts it, so there is no endpoint to ping. 21 installs a week from pypi.

Persistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.

Installs per day peak 149 · avg 13 · -46% w/w

a month agotoday

Installs / week

pypi · contextual-engine

—

Stars

on GitHub

—

Last commit

from GitHub

—

License

language unknown

Nothing serious here today

Today is the operative word: we check Contextual every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add contextual -- uvx contextual-engine

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "contextual": {
      "command": "uvx",
      "args": [
        "contextual-engine"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.contextual]
command = "uvx"
args = ["contextual-engine"]

.cursor/mcp.json

{
  "mcpServers": {
    "contextual": {
      "command": "uvx",
      "args": [
        "contextual-engine"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "contextual": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "contextual-engine"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: CONTEXTUAL_LOG_LEVEL (Python logging level as an integer (e.g. 10=DEBUG, 20=INFO). Defaults to INFO).

Alternatives to Contextual

same job, measured the same way

PMB AI

by oleksiijko

Local-first persistent memory for AI coding agents.

278 installs/wk local only

Agentos

by officialtanishsharma

Local-first persistent memory MCP server for AI coding agents.

local only

Ace Memory

by rudedoggg

Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.

answering

Graph-Mem

by sathvik-1007

Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.

87 installs/wk local only

Omega Memory

by omega-memory

Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.

local only

MCP Documentation Server

by andrea9293

Local-first document management and semantic search for AI coding agents

233 installs/wk local only

Context Engine

by shamsundarsk

Local-first persistent context memory MCP server for AI coding agents.

128 installs/wk local only

MCP Light Memory

by peterpirog

Local-first persistent memory for coding agents and MCP clients.

local only

Contextual — questions

Answers built from our own checks of this server.

Why is there no uptime for Contextual?

Contextual runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package contextual-engine was installed 21 times last week.

How do I connect Contextual?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls contextual-engine straight from pypi; nothing to host, nothing to sign up for.

How many people use Contextual?

The pypi package contextual-engine was installed 21 times in the last week. Week over week that is -46%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.