- Home
- MCP servers
- Conduit
Conduit
- python
5
GitHub Stars
python
Language
4 months ago
First Indexed
3 weeks ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"cortex-app-conduit": {
"command": "conduit-mcp",
"args": [
"--host",
"127.0.0.1",
"--port",
"8000"
],
"env": {
"PHABRICATOR_URL": "https://your-phabricator-instance.com/api/",
"PHABRICATOR_PROXY": "socks5://127.0.0.1:1080",
"PHABRICATOR_TOKEN": "YOUR_TOKEN",
"PHABRICATOR_DISABLE_CERT_VERIFY": "1"
}
}
}
}Conduit is a dedicated MCP server that bridges Phabricator and Phorge APIs with MCP tooling, enabling automated workflows, task interactions, and safe, typed integrations for your development environment.
How to use
You can run Conduit as an HTTP/SSE MCP server or as a local stdio MCP server. Connect your MCP client to Conduit to perform automated actions against Phabricator/Phorge APIs, manage tasks, and leverage built‑in tooling with strong type safety and robust error handling.
Available tools
error_handling
Advanced error handling with detailed error codes and actionable suggestions to help you diagnose and recover from failures.
token_optimization
Token optimization features that streamline API responses for faster interactions.
pagination_and_limiting
Smart pagination and data limiting to efficiently navigate large data sets.
runtime_type_safety
Runtime validation ensuring type safety across client-server boundaries.
configurable_client
Client configuration with caching and retry mechanisms to improve reliability.
mcp_tools_integration
Ready-to-use MCP tools for task management and automation.