Pi extension that delegates prompts to agents on a self-hosted Trinity agent platform (https://github.com/Abilityai/trinity) via its MCP endpoint
Pi MCP server exists for a simple reason — assistants are far more useful when they can act on Pi directly instead of describing what you should do. Pi extension that delegates prompts to agents on a self-hosted Trinity agent platform (https://github.com/Abilityai/trinity) via its MCP endpoint (HTTP+SSE Streamable transport). Config-less auth via env vars. Surfaces a curated subset of.
Trinity is an open-source platform for deploying, orchestrating, and governing fleets of autonomous AI agents on your own hardware. It exposes a MCP (Model Context Protocol) endpoint at https://<your-trinity-host>/mcp that lists dozens of tools for agent CRUD, scheduled loops, fleet health, event subscriptions, file sharing, voice calling, and more.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Pi is connected, these are the calls the assistant has available:
trinity_chat — chat_with_agent — send a prompt to any agenttrinity_agents_list — list_agents — list all deployed agentstrinity_get_agent — get_agent — detailed info on one agenttrinity_fleet_health — get_fleet_health — fleet-wide health rolluptrinity_get_agent_health — get_agent_health — deep health for one agenttrinity_get_agent_logs — get_agent_logs — tail container logsYou will need 2 environment variables: TRINITY_URL, TRINITY_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the monitoring and observability options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Pi's toolset — trinity_chat, trinity_agents_list, trinity_get_agent and 3 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| trinity_chat | chat_with_agent — send a prompt to any agent |
| trinity_agents_list | list_agents — list all deployed agents |
| trinity_get_agent | get_agent — detailed info on one agent |
| trinity_fleet_health | get_fleet_health — fleet-wide health rollup |
| trinity_get_agent_health | get_agent_health — deep health for one agent |
| trinity_get_agent_logs | get_agent_logs — tail container logs |
| Variable | Description | Required |
|---|---|---|
| TRINITY_URL | Endpoint or connection string the server talks to. | Yes |
| TRINITY_API_KEY | Credential the server authenticates with. | Yes |
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
Errors with full context — stack traces, issue triage and AI-powered root-cause analysis from Sentry's server.
Enables enhanced web research capabilities for large language models through intelligent search queuing and advanced content extraction.
Automates browser interactions and enables Large Language Models (LLMs) to interact with web pages through Playwright and Chrome DevTools Protocol
Guides tool usage by providing recommendations for MCP tools at each problem-solving stage.