Forkflux MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 101 installs a week from pypi. Last commit 11 Aug 2026.
Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
We read the source, 5 d ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
subprocess.run([command_name, "--version"], capture_output=True, text=True, check=True) # noqa: S603
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check Forkflux MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 mcp add forkflux-mcp -e 'FORKFLUX_API_KEY=<FORKFLUX_API_KEY>' -- uvx forkflux-mcp
{
"mcpServers": {
"forkflux-mcp": {
"command": "uvx",
"args": [
"forkflux-mcp"
],
"env": {
"FORKFLUX_API_KEY": "<FORKFLUX_API_KEY>"
}
}
}
}
[mcp_servers.forkflux-mcp]
command = "uvx"
args = ["forkflux-mcp"]
env = { FORKFLUX_API_KEY = "<FORKFLUX_API_KEY>" }
{
"mcpServers": {
"forkflux-mcp": {
"command": "uvx",
"args": [
"forkflux-mcp"
],
"env": {
"FORKFLUX_API_KEY": "<FORKFLUX_API_KEY>"
}
}
}
}
{
"servers": {
"forkflux-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"forkflux-mcp"
],
"env": {
"FORKFLUX_API_KEY": "<FORKFLUX_API_KEY>"
}
}
}
}
Put your own value in place of
<FORKFLUX_API_KEY> (Your API key for the service).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
FORKFLUX_API_URL (Your API URL for the service. Defaults to http://localhost:8000/api/v1 if not set).
Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.
Tasks, sprints, releases and docs for engineering teams with AI coding agents.
shared AI-context layer for teams — persistent memory your agents search and update over MCP
Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.
The operating system for self-organised AI agent teams.
Hosted login, teams, billing and feature flags for your SaaS app, set up by your AI assistant.
Self-hosted, consent-based access to Telegram accounts and bots for MCP clients
Senior LatAm engineers for US teams. Facts, role fit, and staffing requests.
Answers built from our own checks of this server.