An MCP server that extends AI coding assistants with deterministic, algorithmic capabilities such as code analysis, fault localization, and formal verification, enabling an autonomous engineering team within the IDE.
Enables AI assistants to control running Neovim sessions via RPC socket, supporting command execution, state inspection, and LSP actions. Automatically discovers Neovim instances and supports multi-instance management on Linux and macOS.
Enables coding agents to search and retrieve persistent repository memory created by Cliper, providing context, gaps, architecture, and timeline information via MCP tools.
Enables parallel execution of shell commands and AI coding agents (Claude, Gemini, Codex) across lists of items like files or URLs, with batched processing and real-time streaming output for batch operations.
Governed memory for coding agents with trust lifecycle, conflict detection, staleness tracking, and health scoring. SQLite + FTS5, zero infrastructure. Works with Claude Code, Cursor, Codex, Windsurf.
Runs as an MCP server providing file system operations, shell execution, and system information tools, allowing Claude or any MCP client to edit files and control the machine.
A fully featured coding agent that uses symbolic operations (enabled by language servers) and works well even in large code bases. Essentially a free to use alternative to Cursor and Windsurf Agents, Cline, Roo Code and others.
Enhanced fork of Google's Colab MCP, pre-registers all 7 notebook tools at startup (get_cells, add/run/update/delete/move_cell, add_text_cell), adds programmatic GPU control (T4/L4/A100) via OAuth, and fixes the "Disconnected from local server" issue with IPv4-only bind, PNA CORS headers, and stale-tab dedup. Works on Chrome, Edge, Windows, macOS, Linux.
Lets AI coding agents ask a Rails app about itself: 35 read-only tools answer from the schema, models, routes, controllers, views, jobs and conventions, over MCP or the command line, even when the app cannot boot.
Self-hosted coding agent that runs Claude Code or Codex in your own infrastructure and works from Slack. Exposes codebase investigation, file edits, branch and PR creation, allowlisted command execution, CI status and an audit log as MCP tools, keeping every credential behind the tool layer instead of handing it to the model.
Enables Claude Code to delegate tasks such as planning, coding, reviews, debugging, tests, and docs to a cheaper model that works autonomously in a project-sandboxed loop with file, search, and test tools, returning a compact report to save tokens. Routing rules, approval-gated deletes and commands, per-task model/effort settings, and backups keep the user in control of what gets handed off.
Turn the AI you already use into a game studio. Describe a game and Claude or Cursor builds it as a real 3D browser game: playable immediately, hosted on its own link, shareable with anyone. No engine, no build step, no code knowledge, nothing to export. Your AI ships the whole thing: it pulls free 3D assets, rigs characters, and playtests its own build until the game works. Free to start.
Connects AI assistants to an AgentX account so they can list and inspect a fleet of AI coding agents running on the user's own machines, read their output, send them messages, create chats, wait for events, and retrieve artifacts. Sign-in happens through browser-based OAuth, with no API key or local install required.
Enables finding existing shadcn-format UI components by plain-language description instead of exact names, returning ranked matches with install commands and per-dimension match reasons.
Enables ChatGPT (or any MCP client) to delegate coding tasks to a local Hermes-backed agent with async job management, supporting read-only investigation, implementation, and continuation of sessions via secure MCP tunnel.
A server component of the Model Context Protocol that provides intelligent analysis of codebases using vector search and machine learning to understand code patterns, architectural decisions, and documentation.
Enables Puck (or any MCP client) to start, inspect, list, cancel, and continue durable Factory Droid tasks on the same host, with idempotent request keys, workspace locking, autonomy/reasoning control, and live authenticated model discovery. It runs without a UI, database, or daemon and inherits the service user's existing Droid CLI login instead of collecting credentials.
Enables users to run shell commands with compressed output, extract information from large files, drive local opencode and Codex agents, perform browser-automation tasks, and monitor runs via a live dashboard.
Enables Codex to delegate scoped tasks to a local DeepSeek Harness over MCP — dispatching read-only reviews or authorized workspace writes, steering and monitoring runs to a terminal state, and returning structured evidence such as changed paths, test results, and assistant text. It also supports exact archival of the terminal session by full session ID.
Enables coding agents to query a parsed graph of a repository and to recall what earlier sessions learned about it, both stored in FalkorDB behind one traversal. It exposes eight MCP tools over stdio for locating symbols, tracing calls and impact paths, and writing or recalling user- and repo-scoped facts, procedures, and handoffs.
A Model Context Protocol (MCP) server that turns multiple AI coding agents into a coordinated team that chats, debates, remembers, audits security, and works in parallel on the same project.
Provides AI-powered development assistance with continuous chain-of-thought reasoning (CoConuT), automated task planning and execution, quality validation, and persistent memory of project context and decisions.
A Windows proof-of-concept MCP server that connects ChatGPT developer-mode to a local Codex CLI via Secure MCP Tunnel, exposing a small set of read-only, allowlisted tools in an isolated workspace.
Enables Codex and DeepSeek Harness to hand off work to each other, then track progress, wait for results, cancel running work, and continue the original execution session. Tasks run in a local service independent of the caller, so closing a chat or losing the MCP connection does not stop them.
Provides file caching and diff tracking for AI coding agents, reducing token usage by returning changes or confirming no changes instead of full file contents on repeated reads.
Enables Claude Code to delegate coding work to a team of Google Antigravity specialists, dispatching tasks to particular roles, listing available agents, checking or cancelling task status, and validating delivered work against acceptance criteria and verification commands. It keeps the leader model in control by returning short results with token usage, git change summaries and output tails instead of the full work.
https://gopls-mcp.org/
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
Lets any MCP-capable coding harness (Cursor, Claude Code, Codex, Gemini CLI, VS Code/Copilot, opencode, and others) hand a self-contained task to a real, isolated DeepSeek Harness process that works in a chosen workspace with its own context window, model, and toolchain, then returns the final answer. Exposes task submission with time estimates and acceptance criteria, status polling with live progress and process-tree telemetry, graceful cancel and forced kill of whole process trees, and a health probe reporting concurrency, deadlines, and recent jobs.
Provides AI coding agents with access to Figma design data through the Figma API. Enables accurate one-shot implementation of designs in any framework by translating Figma files into simplified layout and styling information.
Enables AI assistants to work through complex problems step-by-step with dynamic thought processes, allowing for revision of previous steps, exploration of alternative approaches, and flexible planning as understanding deepens.
Zettelkasten-based persistent memory for AI coding agents. Auto-saves atomic knowledge cards with \[\[bidirectional links]] after tasks and auto-recalls before new ones. No vector DB — plain markdown files with git sync. Works as Claude Code plugin or MCP server for Cursor, VS Code Copilot, Codex, and Windsurf.
Enables managing Linux hosts and local coding agents from an MCP client through shell commands, files, background jobs, system information, instruction and skill discovery, and optional Claude Code, Codex, or Cursor CLI conversations. It provides privileged remote access with token authentication and can run longer work in the background.
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.
Local-first MCP server that indexes all projects on your machine and provides coding agents with briefings about each project's stack, services, and run instructions, so they can start sessions with context across all repos. No cloud, no accounts, no telemetry.
MCP server that enables Claude Code to communicate with other Claude Code agents over HTTP, allowing users to ask questions about remote codebases or delegate coding tasks.
Enables running a validated DAG of coding tasks across a pool of model workers, with independent tasks executing in parallel and dependent ones receiving upstream results. Only a pinned acceptance command's exit code 0 counts as success, with atomic task claims, leases, takeover of killed runners, and scope- and hash-checked applies that refuse to overwrite files or leak secrets.
An MCP server for AI-to-AI collaboration via the Gemini CLI. Available on npm: ask-gemini-mcp. Works with Claude Code, Claude Desktop, Cursor, Warp, Copilot, and 40+ other MCP clients. Leverage Gemini's massive 1M+ token context window for large file and codebase analysis while your primary AI handles interaction and code editing.
Enables diagnosis of recurring coding-agent loop failures from clean, local, zero-telemetry traces and proposes small, reversible fixes to verifiers, retry policies, stop conditions, or skills that are applied only after explicit approval.
Bridges Large Language Models with Language Server Protocol interfaces, allowing LLMs to access LSP's hover information, completions, diagnostics, and code actions for improved code suggestions.
MCP server for shared file state, overlap warnings, and messaging between AI coding agents working in parallel on one GitHub repo. Works with Claude Code, Cursor, Codex, VS Code, Kiro, Windsurf and Perplexity; hosted service by Crews with a free solo tier.
An autonomous code-reasoning agent that parses repositories using tree-sitter, indexes symbols into SQLite, and answers questions about the codebase through an agentic loop powered by Claude via OpenRouter.
Enables MCP clients and local orchestrators to drive Codex Desktop and codex-app-server as a durable async worker: submit tasks or Plan Mode workflows, immediately receive an operation or workflow ID, and poll for status, approvals, and final reports instead of holding long blocking calls. It adds retry-safe request IDs, duplicate-turn protection, SQLite-persisted state with leases and heartbeats for restart recovery, plus health checks, diagnostics, and repair tools.
Enables coding agents to speak aloud using text-to-speech functionality. Works with agents running inside devcontainers and provides configurable voice settings for creating chatty AI companions.
Enables AI coding agents to access real-time VSCode LSP diagnostics, type information, and code navigation without slow tsc/eslint checks, plus symbol renaming and file operations.
Enables LLMs to reason dialectically by running separate thesis, antithesis, and synthesis calls, and to build verified code through a player-coach loop where an independent verifier checks each requirement rather than trusting the implementer's self-report. Works in any MCP-enabled editor such as Claude Desktop, Cursor, or VS Code, either prompt-driven without API keys or with optional server-side backends.
Plori runs AI agents in Workspaces. A Workspace is a project folder in the cloud. Several agents can work in it at the same time, each on its own copy of the files, and Plori merges their work back into the folder. Every version of the files is kept.
Provide a human vision statement. The AI autonomously researches, audits your codebase, generates specs and plans, implements, and validates — with bi-directional verification at every junction to ensure nothing is missed or invented.
Enables running one Codex CLI task at a time in an isolated temporary folder, returning Codex's answer and a manifest of produced files for manual review and selective copying.
Enables AI coding agents to retrieve relevant execution context before a task, compare candidate paths, log outcomes, and search past experiences stored locally in SQLite. It lets agents reuse what worked on similar tasks and get live alerts when a run stagnates or repeats failures.
MCP server that packages DeepSeek agents as callable tools, offering a bare model for quick Q&A and a full agent capable of executing real coding and file-modifying tasks in a workspace.