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.
A Model Context Protocol (MCP) server implementation for the Google Gemini language model. This server allows Claude Desktop users to access the powerful reasoning capabilities of Gemini-2.0-flash-thinking-exp-01-21 model.
Enables structured, step-by-step problem-solving through dynamic thinking processes that can be revised, branched, and adjusted as understanding deepens. Supports breaking down complex problems into manageable steps with the ability to revise previous thoughts and explore alternative reasoning paths.
An enhanced sequential thinking tool optimized for programming tasks that helps break down complex coding problems into structured, self-auditing thought steps with branching and revision capabilities.
Turns a Claude Desktop or Claude Code conversation into an orchestrator for parallel AI coding agents, each running in its own Tern terminal tab and git worktree on its own branch, with any model available on the machine. It enables starting, monitoring, correcting, and merging agents—reading their reports and diffs, switching models or thinking levels mid-task, and enforcing model policies.
Enables Claude Code to run OpenAI Codex (GPT-5) tasks asynchronously in the background, filtering out thinking logs to save 95% context tokens and allowing parallel execution.
MCP server for DeepSeek AI models (Chat + Reasoner). Supports multi-turn sessions, model fallback with circuit breaker, function calling, thinking mode, JSON output, multimodal input, and cost tracking.
An MCP server that enables AI clients to delegate tasks to autonomous developer teams using Goose CLI subagents, supporting parallel and sequential execution across specialized roles like backend developers, frontend developers, and security auditors.
Turns AI assistants into full-stack software engineers with 36 tools for cognitive reasoning, code validation, project scaffolding, and AI/IDE configuration generation across 130+ programming languages, databases, and frameworks.
Wraps the cursor-agent CLI to provide cost-effective tools for repository analysis, code search, planning, and editing. Offloads heavy thinking tasks from the host AI to reduce token usage while maintaining precise, scoped workspace operations.
An MCP server implementing the TRUE Recursive Language Model technique for managing large context windows in Claude Code, enabling analysis of codebases beyond 200k tokens by storing content as variables and using LLM-generated code for search and analysis.
Enables Claude Code and Mistral Vibe to collaborate through a stdio MCP bridge: Vibe can consult Claude for pure-thinking guidance, while Claude Code can delegate well-specified implementation tasks to a Vibe agent working in the project.
Implements human-like cognitive architecture for enhanced AI reasoning through dual-process thinking, memory systems, emotional processing, and metacognitive monitoring. Enables users to process thoughts with biological-like cognitive processes including intuitive and deliberative reasoning modes.
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.
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.
MCP server that delegates bounded subtasks to NVIDIA NIM sub-agents, enabling context offload and parallel fan-out for coding assistants like Claude Code and Cursor.
An MCP server giving coding agents context-window-aware code search and safe, atomic multi-file edits — built to cut token usage on large codebases without sacrificing correctness.
Enables LLMs to apply Martin Fowler's 71+ refactoring patterns to codebases through a pluggable, language-agnostic architecture. Supports previewing and applying refactorings, analyzing code smells, and inspecting code structure with safe-by-default operations.
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 delegating coding tasks to isolated Claude Code subprocesses billed against a GLM Coding Plan, with tools to delegate, await, continue, list, cancel, and inspect runs.
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.
Provides TypeScript and JavaScript code refactoring operations using ts-morph, allowing AST-based symbol renaming, file/folder renaming, reference searching, and path alias removal when integrated with editor extensions like Cursor.
An MCP server that allows coding agents to search the Swift Package Index and retrieve GitHub READMEs without requiring an API key. It features comprehensive search filters for stars, platforms, and licenses, providing token-efficient responses optimized for LLM comprehension.
Exposes the four Ejentum cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call. Drop-in scaffolding that catches LLM failure modes like sycophancy, hallucination, and reasoning shortcuts.
Provides a persistent memory and governance layer that allows AI coding agents to query documented architecture rules and validate code against team standards. It enables agents to verify compliance across categories like security and testing before suggesting changes to ensure consistency across development sessions.
This server lets MCP clients delegate coding tasks to a locally installed Qwen Code CLI, enabling second opinions, parallel work, and clean separation from the main context.
Enables Claude Code to use GLM (Zhipu) as a cheap, full-capability subagent for file editing, code generation, and bash commands, with automatic routing between Opus and GLM based on task complexity.
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.
A generic OpenAI-compatible subagent MCP server that lets Claude Code delegate coding grunt-work to a local model via a tool-calling agent loop, with configurable concurrency and backend.
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.
An autonomous, extensible LLM build orchestrator. Give it a repo and a goal; it decomposes the goal into tasks, edits code, and gates every change on build/tests/lint, reverting regressions. Polygot, cost-aware model selection, pluggable via entry points. Ships as an MCP server so any client can drive it in plain English.
Enables coding agents to write repository documents (READMEs, RFCs, design docs, ADRs) from verified codebase facts, using a separate model for drafting and agent fact-checking for accuracy.
Lets MCP clients delegate tasks to the Google Antigravity CLI, including starting and continuing conversations and listing models, while returning structured results over stdio.
Delegates coding tasks to the locally installed Kimi Code CLI, reusing its auth, models, and configuration while adding tools for sessions, replies, model discovery, live turn steering, and history access.
MCP server that lets Claude Code drive the local Codex CLI as a sub-agent for concurrent queries and optional file/shell actions, using the CLI's existing login and sessions.
Long-term memory for Claude Desktop and Claude Code over plain markdown files on your machine. It returns nothing when the corpus has no answer, naming the terms that appear nowhere — no least-bad match dressed as an answer. And it verifies cited commit SHAs against git, so an agent can tell what actually shipped from what was only discussed and abandoned. Local; nothing is transmitted.
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.
Enables AI coding agents like Claude Code or Codex to delegate tasks to a DeepSeek Harness subagent with its own context window, providing tools for task delegation, result waiting, continuation, and supervision with sandboxed execution.
Lets AI agents create and drive Claude Code cloud sessions natively over stdio, exposing typed tools to start a session from a task description, queue follow-up messages into an existing session, and check the CLI's sign-in state. Each tool maps to a fixed Claude Code CLI invocation with strict schemas and structured JSON results, so agents never write shell commands or run local sessions.
A stdio MCP server that lets Claude Code delegate coding tasks to an OpenCode instance (optionally attached to an internal LLM gateway), with follow-up replies, status polling, output/diff retrieval, cancellation, and cleanup handled in a single session. It supports managed or attach modes, sandbox and approval policies, parallel fan-out delegations, and read-only review workflows.
Enables ChatGPT or other MCP clients to control native Codex sessions on Windows, providing tools for thread management, turns, observation, steering, and responding to approvals.
Enables code execution in isolated Docker containers with persistent IPython, Node.js, or R kernels, supporting file import/export and cross-session transfers via MCP tools.
Production-ready MCP server starter templates in TypeScript and Python. Includes tool, resource, and prompt patterns with Claude Desktop integration configs.
Enables remote control of AI coding assistants (Claude Code/Codex) via Telegram, allowing you to manage long-running tasks, send commands, and receive notifications from anywhere. Supports unattended mode with smart polling for up to 7 days and multi-session management.
MCP server for running external coding agents as background tasks inside Claude Code. Supports multiple backends including Codex, Grok, GLM, DeepSeek, and more.
Enables Claude Code to dispatch opencode CLI tasks as background processes with immediate task handle return, status polling, and result retrieval, avoiding tmux and log parsing issues.
Get a second opinion on your code from every coding agent you have. Claude Code, Codex and Grok review each other's diffs and answer each other's questions, even inside a session that's already running. Uses the CLIs you're signed in to, no API keys.
Helps Claude Code clean up messy repositories: find dead code, duplicate logic, oversized files, and circular dependencies, then apply fixes with optional tests and rollback.
Two AIs. One answer. ChatGPT and Claude discuss with each other until they agree, through your own signed-in CLIs: no API keys. Both read your project (never change it) and search the web. Plugin for Claude Code, Codex, Claude Desktop and the ChatGPT app.
Provides coding agents live access to shadcn-style component registries, enabling them to search, compare, and fetch real component source code for UI composition.