Phabricator is an MCP server that provides an interface between AI assistants and the Phabricator developer platform. Designed for software engineering teams, DevOps engineers, and project managers who rely on Phabricator for their development workflows, this tool connects language models directly to the Phabricator API. By serving as an intermediary, it enables AI agents to query project information, inspect revision statuses, interact with work tasks, and retrieve review metadata without requiring the developer to navigate the web interface manually. Engineering teams can use it to incorporate project tracking and code collaboration data into their automated LLM workflows. The server facilitates task management, status updates, and code review investigations by exposing platform capabilities to standard MCP-compliant clients. Because it functions over the standard Model Context Protocol, it fits directly into conversational interfaces and IDE plugins that support MCP integrations, giving developers a structured mechanism to query their Phabricator deployment alongside other codebase tooling.
Visit the project repository at https://github.com/baba786/phabricator-mcp-server to inspect the project files and prerequisite setup. 2. Clone the repository locally or install any required dependencies as specified in the repository. 3. Open your MCP client configuration file (such as Claude Desktop or Cursor configuration). 4. Add an entry for the Phabricator server pointing to the local executable or script, supplying any required Phabricator API tokens or instance URLs as environment variables according to the project repository guidelines. 5. Save the configuration and restart your MCP client to verify the connection.
What you can do with Phabricator
Querying Maniphest task statuses and details directly through an AI assistant during daily engineering standups. - Retrieving Differential code review metadata and feedback histories to summarize ongoing code review discussions. - Searching workboards and project tags to identify unassigned or blocking tasks within specific development sprints. - Enabling development agents to link active coding tasks directly to associated Phabricator issue tracking records.
MCP Kanban Memory — MCP Kanban Memory is an MCP server that provides a kanban-based task management and state retention system for AI-driven workflows.…
MCP Kubernetes Server — MCP Kubernetes Server is an MCP server that provides tools for managing and inspecting Kubernetes clusters directly through Large Language…
MCP Nomad Go — MCP Nomad Go is an MCP server that connects AI assistants to HashiCorp Nomad clusters. Written in Go, it allows…
MCP Orchestro — MCP Orchestro is an MCP server that integrates AI coding tools with a Supabase-backed task orchestration and Kanban system. Designed…
MCP PR Messages Generator — MCP PR Messages Generator is an MCP server that generates structured pull request descriptions and summary messages directly from Git…
MCP Outlook Tools — MCP Outlook Tools is an MCP server that enables AI assistants like Claude Desktop to connect with a locally installed…
What is the Phabricator MCP server?
The Phabricator MCP server is an integration component that connects AI assistants to the Phabricator API using the Model Context Protocol. It allows developers and project teams to inspect tasks, reviews, and project data directly within their AI chat interfaces.
How do I install the Phabricator MCP server?
Installation details depend on the specific runtime used in the project. You should check the official repository at https://github.com/baba786/phabricator-mcp-server for explicit setup commands, environment variables, and configuration steps required by your MCP client.
Which MCP clients work with Phabricator?
Any client supporting the Model Context Protocol can communicate with the server. Common examples include Claude Desktop, Cursor, and custom developer tools built to interface with local or remote MCP servers.
What can the Phabricator MCP server do?
It allows AI agents to interact with the Phabricator API to read and manage development artifacts. Depending on the configured tools, this includes retrieving information on code reviews, inspecting Maniphest tasks, and checking project statuses.