Perseus: MCP server and live context engine MCP Server
io.github.Perseus-Computing-LLC/perseus
Live context engine that resolves git, services, and tests into agent-ready context.
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Perseus: MCP server and live context engine MCP server?
The Perseus MCP server is a live context engine that integrates git repositories, services, and tests into a unified agent context. It provides local-first context resolution designed to help AI agents understand and work with your codebase and infrastructure.
Perseus is a context engine that automatically resolves and surfaces information about your git repositories, running services, and test suites. It's designed to give AI agents a comprehensive, up-to-date view of your development environment without relying on external services.
How to install Perseus: MCP server and live context engine
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"perseus": {
"command": "uvx",
"args": [
"perseus-ctx",
"mcp",
"serve"
]
}
}
}Use cases
- Provide AI agents with real-time context about your codebase and services
- Automatically surface relevant git history and repository state to AI assistants
- Enable agents to understand test coverage and service dependencies
- Maintain local-first context resolution for privacy and performance
- Help agents make informed decisions based on current infrastructure state
Perseus: MCP server and live context engine MCP server FAQ
Perseus is a live context engine that resolves git repositories, services, and tests into structured context for AI agents. It operates locally-first, meaning all context resolution happens on your machine without external dependencies.
Yes, Perseus is open-source under the MIT license.
Install via PyPI using: pip install perseus-ctx, then configure it as an MCP server in your client (Cursor, Claude Desktop, etc.).
No, Perseus operates locally-first and does not require external authentication or API keys.
Perseus resolves git repository state, active services, and test information into agent-readable context, helping AI understand your development environment.
Yes, Perseus is local-first, meaning all context resolution happens on your machine without sending data to external services.
Related MCP servers
Persistent, encrypted, deterministic memory system for AI agents with 173 canonical tools.
Verifiable, hash-chained event provenance for autonomous systems. Local-first, MIT. 5 MCP tools.
stdio proxy and MCP tools for recording AI agent interactions.

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

PERSONAIZER
Free MCP API to create AI chat personas for websites — upload knowledge, search, and chat
Live aviation data for AI agents: METAR weather, airports, aircraft, glossary & FAA questions.

