"Mock Service Worker" matching MCP servers:

A universal Worker control plane exposed over MCP that lets a host configure OpenAI-compatible providers and API keys, discover model capabilities, and run, monitor, steer, or cancel Codex worker threads. It ships an app-only control panel so humans manage secrets and worker permissions while models call worker lifecycle tools.

Enables Codex to delegate bulk code reading, patching, and testing to an async worker using cheaper AI models, while receiving compact results.

Implements a distributed AI worker pattern over MCP, enabling clients to register as workers, poll for tasks, process prompts with AI, and submit results back to the server continuously.

Enables Codex to offload expensive code reading, editing, and checking to a worker agent via Claude Code, supporting async jobs and long-running tasks.

An MCP bridge that lets Codex supervise Reasonix as an implementation worker in an isolated Git worktree, ensuring safe delegation with scoped writes and sandboxed execution.

An MCP server that enables a supervising OpenAI Codex agent to delegate bounded implementation tasks to isolated worker threads with enforced file scopes and verification, optionally running in parallel git worktrees.

Enables delegating asynchronous coding tasks and DAG workflows to local Oh My Pi (OMP) CLI sub-agents, with topological orchestration, path isolation, and supervised resumption.

Enables orchestrator agents to route coding tasks to native CLI worker agents via MCP, providing tools for agent discovery, task submission, waiting, inspection, and cancellation.

Delegate coding tasks to external AI coding agents in isolated git worktrees with independent verification, enabling any MCP client to orchestrate multi-agent workflows.

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.

Enables collaboration across Claude, GPT, and Gemini through a unified MCP interface, with configurable execution policies for synthesizing or directly delivering worker outputs.

Private escrow for AI agent work on Beam mainnet an agent locks payment, the worker locks collateral, and delivery settles on hash match or review, with M of N arbitrator voting and slashable worker bonds as the dispute backstop. 22 tools cover the full contract lifecycle, and dispute voting is deliberately not an agent tool, so an agent can never rule in its own favour.

A small local MCP adapter that lets Claude Code delegate bounded research work to Codex plan credits without giving the worker ownership of the final report.

Turns a real USB HID device — a Raspberry Pi Pico 2 running open-source firmware — into MCP tools (move, click, drag, type, key combos, scroll) for any MCP client. Includes a --mock mode to try every tool with no hardware.

Enables MCP clients to run Google Antigravity CLI (agy) as durable, detached asynchronous jobs with a permission gate and broker-computed verdicts that do not trust agy's own exit code.

MCP server that exposes grok-ask and grok-workflow tools, enabling Claude Code to delegate to Grok for consult/worker tasks and run adversarial multi-agent workflow panels.

Delegates heavy development tasks from a supervisor to an autonomous worker on a cheaper model via MCP, with isolated git worktrees and provider-agnostic support.

9 tools, Lightning-gated. Pay per call. For agents that need verifiable signed actions with an audit trail. Nostr event signing via daemon Publish events to relays Create Lightning invoices Action receipts — signed proof of agent actions Identity attestation

Enables multi-worker autonomous agent orchestration: decompose complex tasks, run parallel workers, auto-review, and generate follow-up tasks via the Model Context Protocol.

Enables durable, evidence-backed deliberation and Decision CI by running multi-stage model protocols with detached worker processes, persistent jobs, and SQLite-stored decisions, evidence, outcomes, and quality metrics.