"Open Collective" matching MCP servers:

Delegate a Cursor task to a real, unattended background OpenCode agent — cheaper model, isolated history — through five small MCP tools.

An MCP server that enables AI clients to autonomously discover, analyze, fix, test, submit, and track open-source contributions on GitHub through specialized tools.

An open engine that gives AI persistent, reusable UI components with a writable component registry, versioned data storage, and a shell runtime, enabling AI to create, save, and reuse single-purpose apps.

Enables coding agents to check human-stated assumptions against authoritative sources like AWS AppConfig, Sentry, and the repository, detecting when beliefs have drifted from reality. It provides tools to inspect belief history, list verifiable properties, review open drifts, and record verified understanding.

Enables a local MCP client to drive an already-open DeepSeek Harness Desktop session over a loopback-only, Bearer-authenticated endpoint — submitting standard-mode tasks, reading bounded output, continuing or canceling runs, and inspecting diagnostics.

Enables coding agents to open files and git diffs directly in VS Code, allowing users to review code changes without leaving their conversation.

Open-source terminal AI agent with 600+ tools, 35 specialist agents, and 20 providers. Plug kbot into Claude Code, Cursor, VS Code, Zed, or Neovim as an MCP tool provider.

Connects MCP-compatible AI clients and agents to one durable Project Brain plus controlled access to authorized project folders on your own machine. Enables file editing, terminal and Git operations, project intelligence, browser automation, and local MCP server federation, all scoped to explicit workspace grants.

An open-source AI-powered development assistant that connects Claude Desktop to your codebase via MCP, enabling semantic code search, AI-assisted editing, and persistent memory without additional subscriptions.

AI-native open-source 2D game engine whose MCP server exposes every editor operation to coding agents as typed commands, so an agent can build, run, and verify a game inside the editor. It runs locally on macOS, Windows, and Linux with no cloud service or API key.

Enables coding agents to manage multiple isolated IDA Pro analysis sessions concurrently through a single MCP endpoint, allowing them to open, inspect, save, and close binary analysis sessions without launching multiple IDA windows.

An open-source MCP server for industrial automation that generates, debugs, and validates PLC code for Siemens S7-1200, serving as a free and customizable alternative to Siemens Eigen Engineering Agent.

Enables conversational management of a small invoicing SaaS — customers, offers, invoices, payments, open items, reports, and exports — while capturing missing feature requests, clarifying and assessing them, producing development offers, and triggering a local coding agent to create draft PRs for human review.

A native Visual Studio 2026 extension implementing Claude Code's IDE integration protocol: agent edits open in VS's diff viewer for accept/reject, and MCP servers expose the live debugger (stepping, data breakpoints, attach), Test Explorer runs, and Roslyn navigation with decompile to the agent.

Enables MCP clients to drive long-running Codex Desktop work through durable asynchronous operations, polling, approvals, Plan Mode workflows, recovery, diagnostics, and local state without holding MCP calls open.

Enables hybrid agentic coding by delegating token-heavy implementation, editing, and test-debug loops to local open-source models while frontier cloud models handle architecture and review, reducing premium API token usage and keeping code private.

Enables Claude or any MCP client to drive the GitHub Copilot cloud agent via its REST API, allowing it to research, edit, and open pull requests on repositories without manual intervention.

Marketplace where AI coding agents fix GitHub bugs for cash bounties. Posters draft and fund bounties from chat (Stripe Checkout); solvers browse open work, request repo access, submit PRs, and get paid in USDC, ETH, or BTC. 11 tools.

An open-source MCP server that connects your IDE or AI assistant to the Codex CLI, enabling non-interactive automation with codex exec, safe sandboxed edits with approvals, and large-scale code analysis via @ file references.

YouTrack MCP server and coding-agent pipelines. Every built-in YouTrack MCP tool plus deletes, sprints, attachments, history and reports, signed in with your login and password. Pipelines hand YouTrack issues to Claude Code, Kimi or any ACP agent and open the pull requests. One-command install into Claude, Cursor, VS Code, Zed, Codex and more.

Enables ChatGPT to work on a local project by reading and editing files, running shell commands, keeping terminals and desktop sessions open, and splitting work across durable workers whose context persists between tasks. Long-running work can be steered mid-flight, tracked with Goal, and carried into fresh chats via Compact & Resume.

Enables Claude Code and Cowork to delegate coding tasks over Remote MCP to isolated Cloudflare Container sandboxes that push work branches and open Draft PRs, with tools for task polling, steering, cancellation, and optional web search and fetch. It authenticates users through a GitHub App and supports long-running task status, results, and budget controls.

Lets ChatGPT work directly on a local project by reading and editing files, running shell commands and tests, keeping terminals open, and using the user's desktop, all paired with an approved workspace folder. It also splits independent jobs across persistent workers that retain context, while riding the user's existing ChatGPT plan rather than Codex quota.

Turns Codex Desktop and codex-app-server into a durable asynchronous worker that MCP clients can submit long-running tasks and Plan Mode workflows to, receiving an operationId or workflowId immediately instead of holding a call open for hours. Enables retry-safe polling for status, approvals, questions, interrupts, code review, diagnostics, and final reports, with persisted SQLite state that survives client retries and server restarts.

Enables MCP clients to drive Codex Desktop and codex-app-server as a durable worker for long-running tasks by submitting work and receiving an operationId or workflowId immediately, then polling status, handling Plan Mode approvals and pending questions, and reading final reports without holding multi-hour MCP calls open.