- Token Optimizer @ooples/token-optimizer-mcpContext-window optimization: caching, compression & smart file tools that cut tokens 60-90%.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.541 GitHub stars.
- Claudexor @razzant/claudexorRoute coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.501 GitHub stars.
- Blockrun @blockrunai/blockrun-mcpWeb search, deep research, prediction markets & crypto data for AI agents. Pay per call via x402.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.391 GitHub stars.
- Codex Bridge @fanch-hui/codex-bridgeConnect MCP clients to local Codex Bridge agents, projects, approvals and workspace tools.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.252 GitHub stars.
- Codex Bridge @yeyuancc0-glitch/codex-bridgeConnect MCP clients to local Codex Bridge agents, projects, approvals and workspace tools.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.249 GitHub stars.
- SandBase @sandbaseai/cliConnect MCP clients to 2,000+ AI models without managing provider API keys.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.188 GitHub stars.
- OpenClaw MCP Server @freema/openclaw-mcpMCP server bridging Claude.ai/Desktop with self-hosted OpenClaw via OAuth 2.1.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.186 GitHub stars.
- AISIX AI Gateway @api7/aisixSelf-hosted AI gateway that governs MCP servers, LLM traffic, and A2A agents behind one endpoint3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.184 GitHub stars.
- Rubber Duck @nesquikm/rubber-duckBridge to multiple LLMs and CLI agents: councils, debates, voting, and more6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.178 GitHub stars.
- Prism @dcostenco/prism-mcpMoved to io.github.dcostenco/prism-coder — install prism-mcp-server v20+ from npm.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.158 GitHub stars.
- Prism Coder @dcostenco/prism-coderSession memory for coding agents: local-first recall, drift detection, on-device inference.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.158 GitHub stars.
- freellmpool @0xzr/freellmpoolOpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.122 GitHub stars.
- Lm @houtini-ai/lmConnect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.121 GitHub stars.
- OpenRouter Multimodal @stabgan/openrouter-multimodalChat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.96 GitHub stars.
- SuperCMO @supercmohq/supercmoMarketing media generation — image, video, voice — for AI agents. BYO keys.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.74 GitHub stars.
- Brainstorm @spranab/brainstorm-mcpMulti-model AI brainstorming debates with code review and quick perspectives4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.71 GitHub stars.
- Agy Bridge @sshahzaiib/agy-bridgeDelegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.57 GitHub stars.
- Jev Use @shitianfang/jev-useTyped yes/no, pick-one and score judgments from Jev in one batched call; typed escalation back.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.56 GitHub stars.
- RunAPI @runapi-builder/runapi-mcp130+ AI models for image, video, music, and audio — 18 model families, one RunAPI account.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.55 GitHub stars.
- Mediagen @cripacx/mediagenGenerate images and video from text prompts across Gemini, OpenAI and Kie AI.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.52 GitHub stars.
- Credit Optimizer v5 for Manus AI @rafsilva85/credit-optimizerOptimizes Manus AI credit usage by 30-75% via intelligent model routing and smart testing.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.51 GitHub stars.
LLM access & routing MCP servers
A server here gives access to many AI models through one API, routes or compares models, or tracks model usage and token costs.
Not here: servers that merely use an AI model to do something else.
464 remote432 localTagged by Odel's AI, which can make mistakes
Most popular in LLM access & routing
By GitHub stars, at most two per publisher- Number 1: Claude Flow@ruvnet/claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.73,814 GitHub stars.
- Number 2: Pollinations@pollinations/pollinationsAccess Pollinations models and API capabilities through agent tools.Not assessed yet.A remote server; it needs your API key.5,183 GitHub stars.
- Number 3: GoModel@enterpilot/gomodelSelf-hosted gateway aggregating upstream MCP servers behind one authenticated HTTP endpoint.15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1,228 GitHub stars.
