MCP Setup

This guide walks you through connecting your AI coding assistant to DevFlow using the Model Context Protocol (MCP).

What is MCP?

The Model Context Protocol (MCP) is a standard for integrating AI assistants with external tools. Instead of copy-pasting context back and forth, MCP gives the AI agent direct access to structured tools — reading flows, creating tasks, updating progress, and more.

Think of it as giving the AI agent a seat at your desk. It can see your project, understand your tasks, and report its work — all through a well-defined interface.

Installing the MCP Server

The DevFlow MCP server is distributed as an npm package. Install and run it with:

npx @devflow/mcp-server

This starts a local MCP server that connects your AI assistant to your DevFlow instance.

Configuring Your AI Assistant

Claude Code

Add the DevFlow MCP server to your Claude Code configuration. In your project’s .mcp.json or global MCP settings, add:

{
  "mcpServers": {
    "devflow": {
      "command": "npx",
      "args": ["@devflow/mcp-server"]
    }
  }
}

Once configured, Claude Code will automatically have access to DevFlow tools when you start a session.

Other AI Assistants

Any AI assistant that supports MCP can connect to DevFlow. The setup pattern is the same:

1. Point the assistant’s MCP configuration to npx @devflow/mcp-server
2. Ensure the server can reach your DevFlow instance
3. Authenticate (see below)

Authentication

The MCP server uses your DevFlow credentials to authenticate. When you first run the server, it will prompt you to log in. Your session is stored locally so you do not need to re-authenticate every time.

The agent inherits your permissions — it can only access projects and flows that you have access to.

Available Tools

Once connected, the AI agent has access to the following tools:

Tool	Purpose
flow_list	List all flows in a project
flow_get	Get details of a specific flow
flow_create	Create a new flow
flow_update	Update flow state, submit plans, or deliver results
flow_get_feedback	Check for user feedback on plans or reviews
task_list	List tasks for a flow
task_create	Create tasks to break down work
task_update	Mark tasks as complete or update details
devflow_init	Start a work session on a flow
search	Search across flows, tasks, and projects

The agent uses these tools to participate in the full flow lifecycle — from planning through implementation to review.

Testing the Connection

After setup, verify the connection works by asking your AI assistant to list your flows:

“List my DevFlow flows”

The agent should call flow_list and return your active flows. If you see your project data, the connection is working.

Troubleshooting

The agent cannot find any flows

• Verify the MCP server is running
• Check that you are authenticated
• Make sure you have at least one project with flows

The agent cannot update flows

• Ensure the flow is not locked by another agent session
• Check that the flow is in a state that allows the requested action

Connection errors

• Verify your DevFlow instance is reachable from the MCP server
• Check network/firewall settings if running DevFlow on a remote server