"Pix" matching MCP servers:

Enables delegating coding tasks to a pi agent as a steerable background worker, allowing mid-run redirection, follow-ups, and keeping the delegate's context isolated from your main conversation.

Exposes pi as a sub-agent for MCP-capable coding assistants, enabling task dispatch, messaging, and interactive dialog handling via tools like pi_dispatch, pi_send, and pi_respond.

Enables any MCP client to browse, triage, search, read, and drive pi coding agent sessions through Pi Web's HTTP API via 25 tools. Supports listing and filtering sessions, reading transcripts, flagging conversations awaiting input, sending messages and waiting for replies, inspecting project diffs, and forking, renaming, or deleting sessions over either stdio or Streamable HTTP.

A tiny Hermes-friendly bridge that exposes oh-my-pi's CLI as MCP tools (prompt and doctor) for code generation and environment verification.

Enables delegating coding tasks to the Pi CLI through MCP with named sessions, synchronous or asynchronous execution, and a read-only transcript window on Windows.

Enables MCP hosts to delegate coding tasks to Pi CLI as a programmable sub-agent with session tracking and process management.

An MCP bridge for the Pi coding agent running in WSL, enabling task execution, research, review, and session management through MCP.

Enables Claude Code to delegate coding implementation and testing to a local pi agent via MCP tools, including dispatching task books, monitoring status, steering or aborting runs mid-execution, and retrieving results and transcripts.

MCP server exposing pi coding-agent tools for file and shell operations, including read, write, edit, bash, grep, find, and ls.

Enables pi coding agent users to run Pega Infinity authoring tools as native pi tools, with read-only access by default and write tools behind an explicit opt-in flag.

Lets MCP clients create, resume, message, and stop Pi coding-agent sessions running on another machine, with conversations that survive client disconnects and server restarts. Sessions can be kept loopback-only or published privately to trusted callers over Tailscale HTTPS.

Enables delegating coding tasks to sandboxed agents, returning changes as auditable diffs for human review before applying or discarding them.

Enables an assistant to run pi coding-agent tasks in the background: dispatching a task, polling its status and tool trace, reading the final result, and cancelling it when no longer needed, all without pulling the delegate's context into its own conversation.

Enables Codex to supervise one or more local Pi coding-agent workers through bounded task execution, state polling, steering, aborting, and listing. Tasks can run in a direct working directory or isolated Git worktree while Codex remains the planner and reviewer.

Enables MCP clients such as Claude Code and Codex to delegate background Pi Coding Agent tasks, inspect and steer running work, and recover saved checkpoints after server restarts.

Enables Codex to delegate subtasks to concurrent background coding agents that can each run on any model provider supported by Pi, such as DeepSeek, Anthropic, Gemini, OpenRouter, or local models. Exposes MCP tools for listing models, spawning and waiting on agents, sending follow-ups, and aborting, backed by a live local web panel showing status, token usage, and streaming output.

Delegates bounded coding tasks from MCP clients to the Pi Coding Agent over stdio. Supports review, verification, implementation, and batch operations with long-running task polling.

Orchestrates multiple coding agents at once so an MCP client can delegate implementation work while retaining judgment: each agent runs in its own isolated git worktree and branch, claims the files it edits, and communicates via a mailbox and shared board. Supports blocking questions to the orchestrator, Codex-written acceptance tests locked before workers start, scope validation, and reporting on first-pass success.

Enables a coding agent such as Codex or Claude Code to delegate work to a local Pi coding-agent session, including second-opinion reviews, bulk reading kept out of the main context, and follow-up turns that retain context. Operators control what is possible by defining workspace and execution-profile aliases in a local config file, so clients cannot choose directories, models, providers, or permission levels themselves.

Enables local AI agents to access DeepSeek V4 models and perform coding tasks via Pi's agent SDK.