mcpbeat Sign in

Perseus — Live Context Engine for AI Agents MCP Server

local only

Perseus — Live Context Engine for AI Agents runs on your own machine — the client starts it, so there is no endpoint to ping. 238 installs a week from pypi.

Live context engine for AI agents. 27+ MCP tools: health, memory, skills, file trees on demand.

Installs per day peak 169 · avg 36 · -34% w/w
a month agotoday
238
Installs / week
pypi · perseus-ctx
—
Stars
on GitHub
—
Last commit
from GitHub
—
License
language unknown

Nothing serious here today

Today is the operative word: we check Perseus — Live Context Engine for AI Agents every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

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.

run in your terminal
claude mcp add perseus -e 'PERSEUS_WORKSPACE=<PERSEUS_WORKSPACE>' -- uvx perseus-ctx
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "perseus": {
      "command": "uvx",
      "args": [
        "perseus-ctx"
      ],
      "env": {
        "PERSEUS_WORKSPACE": "<PERSEUS_WORKSPACE>"
      }
    }
  }
}
~/.codex/config.toml
[mcp_servers.perseus]
command = "uvx"
args = ["perseus-ctx"]
env = { PERSEUS_WORKSPACE = "<PERSEUS_WORKSPACE>" }
.cursor/mcp.json
{
  "mcpServers": {
    "perseus": {
      "command": "uvx",
      "args": [
        "perseus-ctx"
      ],
      "env": {
        "PERSEUS_WORKSPACE": "<PERSEUS_WORKSPACE>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "perseus": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "perseus-ctx"
      ],
      "env": {
        "PERSEUS_WORKSPACE": "<PERSEUS_WORKSPACE>"
      }
    }
  }
}

Put your own value in place of <PERSEUS_WORKSPACE> (Path to the workspace directory to serve context for). The author’s registry entry marks it as required.

Alternatives to Perseus — Live Context Engine for AI Agents

same job, measured the same way
Context Engine
by shamsundarsk

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

128 installs/wk local only
Agent Memory MCP
by ipiton

Memory, docs, and repo context layer for engineering agents.

local only
Token Context MCP
by mck564

On-demand, local code-context MCP server for AI coding agents with Tree-sitter AST.

609 installs/wk local only
Perseus: MCP server and live context engine
by perseus-computing-llc

Live context MCP server: resolves git, services, and tests into agent context. Local-first, MIT.

local only
Hexis
by bevel-software

Git-backed platform for skills, tools, and context for AI agents

answering
Synap Memory
by maximem

Persistent memory for AI agents — log and recall conversation context over MCP.

4 tools answering
Openfuse MCP
by openfused

Encrypted mail, shared memory, and persistent context for AI agents.

90 installs/wk local only
Website
by cuvo

Cuvo Health published site content and live discovery-call booking tools for AI agents.

47 installs/wk 9 tools answering

Perseus — Live Context Engine for AI Agents — questions

Answers built from our own checks of this server.

Why is there no uptime for Perseus — Live Context Engine for AI Agents?
Perseus — Live Context Engine for AI Agents 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 perseus-ctx was installed 238 times last week.
How do I connect Perseus — Live Context Engine for AI Agents?
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 perseus-ctx straight from pypi; nothing to host, nothing to sign up for.
How many people use Perseus — Live Context Engine for AI Agents?
The pypi package perseus-ctx was installed 238 times in the last week. Week over week that is -34%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.