Forkflux MCP

Name: Forkflux MCP
Author: forkflux

by forkfluxversion 0.6.0i★ –iRuns on your computer

Registry nameio.github.forkflux/forkflux-mcp

Install

Overview

Description from the maker (original English)

Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Other
You need to fill in: FORKFLUX_API_KEY

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
You fill in yourself: FORKFLUX_API_KEY, FORKFLUX_API_URL

Values marked secret are keys to your account. Never share them or paste them into a chat.

You need

PyPIPython’s uv installed (for the uvx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "forkflux": {
      "command": "uvx",
      "args": [
        "forkflux-mcp"
      ],
      "env": {
        "FORKFLUX_API_KEY": "your-value",
        "FORKFLUX_API_URL": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add forkflux --env FORKFLUX_API_KEY=your-value --env FORKFLUX_API_URL=your-value -- uvx forkflux-mcp

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "forkflux": {
      "command": "uvx",
      "args": [
        "forkflux-mcp"
      ],
      "env": {
        "FORKFLUX_API_KEY": "your-value",
        "FORKFLUX_API_URL": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "forkflux": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "forkflux-mcp"
      ],
      "env": {
        "FORKFLUX_API_KEY": "your-value",
        "FORKFLUX_API_URL": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

FORKFLUX_API_KEY secret required env
Your API key for the service
FORKFLUX_API_URL env
Your API URL for the service. Defaults to http://localhost:8000/api/v1 if not set.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account forkflux, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Otheri

More stars than 0% of the other 32572 servers in this category
Published to the registry more recently than 21% of the other 32572 servers in this category
Basic checks equal to or better than 100% of the other 32572 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Forkflux MCP safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: FORKFLUX_API_KEY

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.6.0) reached the registry 3 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.

What can I use instead?

In the same category: Spec Driven Development, Remote Desktop Commander, AvaHR

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Spec Driven Development

by formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

Runs on your computer★ 440MITUpdated 14 months ago

Install

Remote Desktop Commander

by desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

Runs in the cloud★ 211Updated yesterday

Install

AvaHR

by avahr.com

Read hiring data and create inactive assessment and questionnaire drafts for human review.

Runs in the cloudUpdated today

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

ForkFlux MCP Server

Model Context Protocol (MCP) server for ForkFlux, the self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams.

ForkFlux MCP connects MCP-compatible assistants such as Cursor, Claude Code, and Codex to a self-hosted ForkFlux API instance. It gives engineering teams a shared, auditable workflow for delegating work between isolated AI agents, tracking its lifecycle, and retaining the context behind each handoff.

Use this package when AI agents work across separate machines or workspaces and need to exchange structured work without copy-pasting logs, sharing local files, or relying on human task trackers as an ad-hoc coordination layer.

What it provides

forkflux_create_job — publish a structured handoff job with context, constraints, artifacts, priority, target role, dependencies, and optional follow-on routing rules.
forkflux_list_jobs — list shared jobs, with filters for lifecycle status, target role, and the calling agent's roles.
forkflux_job_details — retrieve the complete record for a job, including its context, constraints, and artifacts.
forkflux_claim_job — atomically claim a published job and receive its full context payload.
forkflux_claim_next_job — atomically claim the highest-priority available job for a target role.
forkflux_change_job_status — record lifecycle transitions for claimed work: blocked, in_progress, completed, failed, or cancelled.
forkflux_update_job — revise a published job's context payload and/or constraints when the handoff needs correction or clarification.
forkflux_reject_job — reject completed work and create a linked retry job containing the rejection reason.
forkflux_get_reopen_context — retrieve focused retry context for a reopened job without loading the original full context payload.

Requirements

Python 3.12+
A running ForkFlux API endpoint
A ForkFlux API key for the agent using this MCP server when running over stdio

Configuration

Set these environment variables before starting the server:

export FORKFLUX_API_URL="http://localhost:8000/api/v1"

export FORKFLUX_API_KEY="your-agent-api-key"

Run the server over stdio with either an installed package or uvx:

pip install forkflux-mcp

forkflux-mcp

Or run without installing into the current environment.

uvx forkflux-mcp

Run as an HTTP service

The package also exposes a Streamable HTTP ASGI application for assistants that connect to a shared, long-running MCP service:

export FORKFLUX_API_URL="http://localhost:8000/api/v1"

export FORKFLUX_SHARED_API_KEY="your-shared-api-key" uvicorn forkflux_mcp.main:app --host 0.0.0.0 --port 8080

The MCP endpoint is available at http://localhost:8080/mcp. HTTP clients must send their own agent token in the Authorization: Bearer header. The MCP service forwards that header to the API for agent-authenticated tool calls.

For HTTP mode, configure the API service with the matching shared key:

export SHARED_API_KEY="your-shared-api-key"

SHARED_API_KEY and FORKFLUX_SHARED_API_KEY are the same private service credential viewed from the API and MCP services. It is used for MCP requests that have no incoming client header, such as startup role discovery; it is not an agent token and should not replace FORKFLUX_API_KEY in a client configuration.

The repository's Docker Compose example shows the API, MCP HTTP service, and PostgreSQL running together.

The MCP server is intentionally stateless. It prefixes API requests with /mcp, authenticates them with either the calling agent's bearer token or the shared service credential when no client header is available, and returns structured success or error results. The API remains the source of truth for agents, roles, jobs, dependencies, routing rules, artifacts, and lifecycle events.

For a client configuration example, see the MCP integration guide. For local development:

uv sync

uv run pytest -v

License

Apache-2.0. See the project repository for full license details.

Forkflux MCP

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Values you fill in

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Otheri

Common questions

Alternatives

Spec Driven Development

Remote Desktop Commander

AvaHR

README from the maker

ForkFlux MCP Server

What it provides

Requirements

Configuration

Or run without installing into the current environment.

Run as an HTTP service

License