- Ollama / vLLM Bridge @setheerwagen/mcp-ollama-vllmCall your local Ollama or vLLM model over MCP with schema-validated JSON output4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- The High Council @muad-yasin/the-high-councilSeveral models from different labs plan in a blind proposal, debate and review loop. Your own keys.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Groq @mrfentmen/groq-mcpMCP server for Groq: fast LLM chat, model list. Needs a free API key.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- SkillFM Beacon @ericm1018/skillfm-ai-health-token-usage-byok-cost-cleanupAI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits for MCP agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Model ID Cheatsheet @aezizhu/model-id-cheatsheetAccurate API model IDs, pricing, and specs for 46 models across 7 AI providers.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MeshMarket @rightonpar-llc/meshmarketThe agent-to-agent capability exchange — rent memory, reasoning and safety, settled per call.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Hydracept @hydracept/hydraceptExecution control plane for agents: capabilities, durable jobs, budgets, receipts, and BYOK.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Model Shunt @yasmanycastillo/model-shuntModel routing for AI agents: delegate bulk reads & boilerplate to cheap worker models.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- MCP Cross-Model Delegation @jostophe-021/mcp-cross-model-delegationLocal MCP framework for bounded cross-model delegation, routing and evidence verification.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Store API @store-api/store-apiGPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- gen-image MCP @yuluo688/gen-image-mcpLocal stdio MCP for OpenAI-compatible and Gemini image generation, editing, and model fallback.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MegaLens @megalens/mcpCode review by AI models from different companies, usually two. Shows where they agree and disagree.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Cluster @clusteragent/cluster-mcpSelf-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- OpenMayhem @openmayhem/openmayhemUse OpenMayhem text, embedding and media models with explicit cost controls.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- X402 Gateway @gentechlabs/x402-gatewayPay-per-call x402 services for agents: risk scoring, DeFi, wallet and market data.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- p-e relay (remote) @it-start/relay-uiRemote MCP access to the p-e relay store. Reads are open; writes and waits are signed.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- InferIndex @inferindex/inferindexLLM API prices across 70+ providers: cheapest offer, comparisons, history and cost estimates.2% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Fattly @industriesfatty-spec/fattlyAI images, video, voiceovers and UGC ads from 50+ models. Official MCP server for fattly.app.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- DexL Agents @dexl-io/agentsPay-per-call AI gateway: models, speech, web search, on-chain reads and NLP tools, via x402.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SayMaker @saymaker/saymaker-mcpGenerate and edit AI images and video on SayMaker: Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana 2.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- dashAI (unofficial) @maarmapa/dashai-mcpTrain, track and query models on a running dashAI instance. Read-oriented, no delete tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- EmpirioLabs AI @empiriolabs/mcpEvery EmpirioLabs model and platform feature as tools: chat, media, search, jobs, GPU Cloud, agents.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ModelShortlist @agenticartists/modelshortlistLocal BYOK MCP for AI model shortlisting using OpenRouter + Artificial Analysis.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Ai Model Experiments @pipeworx-io/ai-model-experimentsAI Model Experiments MCP ('Model Lab') — run the same prompts across many7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
