"A router for MCP (Model Context Protocol) tools" matching MCP servers:

Enables a Codex orchestrator to obtain a deterministic, local recommendation for a model and reasoning effort for a delegated coding task, without inference calls or API keys.

A Python-based server for managing and analyzing code context for AI-assisted development. Provides real-time code analysis, project structure analysis, dependency tracking, and secure API endpoints.

Routes each prompt to the best-fitting Claude model via a local, zero-cost classifier, exposing a single smart_prompt tool for MCP clients.

Enables users to route Codex desktop chats to subscription models or their own OpenAI-compatible providers by adding Base URLs, API keys, and model catalogs from an in-app settings panel. Keeps keys DPAPI-encrypted, supports Responses and Chat Completions with streaming and tool calls, and needs no separate configuration app or Windows autostart.

Provides a bulk_read_files tool that reads specified files and forwards them to a remote backend for summarization, so agents receive concise summaries instead of raw file contents.

Enables agents to load instruction modules on demand from linked git repos, keeping the always-loaded AGENTS.md slim. It syncs each module's repo before reading and returns the module text with the commit it was read at.

Routes model requests to Sol, Terra, or Luna via OpenClaw Gateway's Codex auth profile, with strict validation and no fallback.

Summarizes Slack activity and GitLab merge requests with OpenAI to help generate daily standups, weekly reports, or quarterly check-ins.

A Model Context Protocol (MCP) server designed to easily dump your codebase context into Large Language Models (LLMs).

A local-first MCP server and CLI that gives coding agents structured project memory, task contracts, context packs, backlog workflows, and verification evidence, storing data in reviewable Markdown/YAML with a fast SQLite index.

A conversational application server that integrates LLM capabilities via Ollama with vector memory context, supporting multiple users, sessions, automatic history summarization, and a plugin system for executing real actions.

Enables AI agents to perform local video, audio, and file operations inside an isolated workspace, including cutting/concat videos, extracting audio, transcribing, and managing files, with typed responses and background job support.

Enables agents to compress JPEG, PNG, and WebP images to a target byte size, split PDFs by page or ranges, and remove image metadata while processing local files without sending file bytes over the network.

An MCP server that integrates AI retrievals with NASA's Common Metadata Repository (CMR), allowing users to search NASA's catalog of Earth science datasets through natural language queries.

A lazy router for Claude Code skills that exposes a library of skills through search, load, and reindex MCP tools, reducing context usage by only loading skills on demand.

A centralized gateway platform for aggregating and managing multiple Model Context Protocol (MCP) servers through a single Electron-based interface. It provides enterprise-grade security features including policy-based access control, human-in-the-loop approval workflows, and comprehensive audit logging.

A lightweight MCP server for semantic search over markdown knowledge bases, enabling AI coding agents to index, search, and answer questions from local markdown documents.

A server that allows users to query and analyze cloud cost data from Cloudzero using natural language through Large Language Models.

Enables AI agents and their users to submit, route, and monitor training jobs across free-tier GPU clouds (Kaggle, Colab, Lightning, local MPS) through a local daemon that tracks quota, explains routing decisions, and gates long or secret-reading agent jobs behind human approval.

Deterministic dependency + CVE context for AI coding tools, over the Model Context Protocol. A ~0.85 MB pure-Rust MCP server.

Discovers local model runtimes such as Ollama, LM Studio, and LocalAI, and exposes their endpoint metadata to MCP clients like Copilot.

Enables repo-scoped expert consultation from Claude Code by compressing difficult questions into structured briefings and routing them through ai-browser-bridge to ChatGPT web, with per-project activation and safeguards.

This MCP server lets agents route natural-language requests to the best matching workflow or tool using weighted lexical scoring and two-gate abstention. It returns ranked candidates with match evidence or explicitly refuses when confidence or score falls below calibrated thresholds.

Exposes product-style completion tools (OpenAI chat-completions-shaped and Anthropic messages-shaped) that are fulfilled by sampling the host agent's own LLM over MCP, so no model API keys are ever needed. Also offers a model listing endpoint aliasing the host's model.

Enables AI coding agents to offload large file reads and boilerplate code generation to cheaper or local worker models through MCP, reducing token consumption and keeping context clean.

Enables agents to retrieve their current identity from IDENTITY.md and route durable lessons, preferences, rules, and corrections to the appropriate standing file over MCP stdio.

Lets AI agents inspect local or remote videos by reading metadata, detecting shots and cuts, extracting frames as images, and checking keyframes for seeking and streaming, all via local FFmpeg without an API key.

Enables agents to connect through a single gateway that has a decision model pick which MCP tools and playbooks are relevant to each request, so the LLM only sees the few schemas it needs, and to then invoke those tools on the underlying servers. This cuts tool-selection cost and prompt size dramatically when many MCP servers are connected.

Enables Claude Code and Codex Herdr workers to get local, advisory routing decisions by selecting a client, model, effort tier, and worker launch instruction for a stage, and by ranking a short list of bounded next actions. Decisions come from a selectable local backend (Laya or a local Kev model), returning confidence and uncertainty without executing anything or granting permissions.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables running a project's agent definitions from .github/agents/ against a model the user explicitly names, instead of inheriting whatever model the IDE session happens to use. It reads the agent file as the system prompt, executes a bounded tool loop against a configurable inference gateway, enforces a tiered model allow-list, and reports which model actually ran.

Context Forge is a vendor-neutral continuity layer for AI tools. It stores project context in Markdown and JSON, retrieves task-scoped context, and leaves structured handoffs so another model can continue without being taught the project again.

Tracks protocol adherence and maintains audit trails for Claude sessions, providing tools for logging steps, activities, and violations, and computing compliance scores.

Enables AI agents to programmatically create, inspect, edit, validate, and headlessly render traditional 2D hand-drawn animation projects, including frames, layers, audio, camera keyframes, spritesheets, and video or GIF exports.

Enables MCP clients to chat through multiple LLM API keys with automatic rotation and failover, discover free and available models, inspect key health and routing, refresh catalogues, ensure a local proxy, and generate OpenCode/Kiro/skill configuration.

Enables AI assistants to directly manage Anki flashcards, decks, notetypes, tags, and media, with support for batch operations, searches, and deck exports via file-based input/output.

A comprehensive MCP server for managing AI-assisted Dungeons & Dragons campaigns, featuring tools for character sheets, combat tracking, and world-building. It enables players and DMs to interact with 5e game mechanics and query personal PDF rulebooks using RAG capabilities.

Open-source MCP server for Autodesk Revit 2022 to 2027: read, audit and edit live models with 89 tools, one Undo entry per change, and a workstation read-only lock.

Enables language models to receive external randomness so the same prompt can produce different answers while still following the user's request.

Enables agents to keep long-term local memory without bloating the context window by searching a compact keyword index of summaries first and then pulling the full original record only when needed by its ID. It also lets agents save new memories and link related records through JSON-returning MCP tools.