# Conduit (Phabricator)

> Use this tool when you need to automate task management, project automation, and code review processes in Phabricator and Phorge. It provides a seamless integration API for creating tasks, searching tasks, and retrieving task details, with modular architecture and secure token-based authentication. Ideal for development teams and AI assistants requiring structured access to Phabricator's project management ecosystem.

Canonical page: https://skillsregistry.net/skills/conduit  
JSON: https://api.skillsregistry.net/v1/skills/conduit

## Description

This MCP server provides seamless integration with Phabricator and Phorge APIs, enabling task management and project automation through the Conduit API. Built by mcpnow.io using Python with httpx for modern HTTP/2 support, it features both synchronous and asynchronous clients with modular architecture covering Maniphest (tasks), Differential (code review), Diffusion (repositories), Projects, Users, and Files. The implementation offers four core MCP tools for creating tasks, searching tasks with status filtering, retrieving specific task details, and testing API connectivity, with comprehensive error handling and environment variable configuration for secure token-based authentication. The server supports complex Phabricator workflows including task creation with owners and project assignments, advanced search constraints, and full type safety with structured responses, making it valuable for development teams automating issue tracking, code review processes, and building AI assistants that need structured access to Phabricator's project management ecosystem.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/conduit)
- **Repository:** <https://github.com/cortex-app/conduit>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "conduit"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/conduit` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/conduit/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt