- Trustmodel @karlmehta/trustmodel-mcpScore any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Index9 @index9-org/mcpDiscover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- NVIDIA NIM @david-eve-za/nvidia-nim-mcpMCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Evals @cyanheads/evals-mcp-serverAuthor verifiable eval records through a draft→review→revise→submit loop with enforced graders.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Sentor @nikx-tech/sentor-mcpScore sentiment toward specific entities in text. Cluster documents and name topics.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Forge @voxell/forgeMCP server for Forge, Voxell's embedding API. Voxell's Ingot-8B-R3 ranks #1 for English on MTEB.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- glin @akashchatterjee/glinExactly explainable classifiers for agents: train, tune, predict, explain on CSV or Excel.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Calibration Explorer @m-sanchez/calibration-explorerCheck classifier confidence against accuracy, fit temperature scaling and save local reports.Not assessed yet.Runs on your machine, installed from npm.
- OpenNodes @opennodes-io/opennodesDiscover verified AI inference nodes, get the best node+model per task, pre-price chains.Not assessed yet.Runs on your machine, installed from npm.
- mcp-computeflux @computeflux2026isgod/mcp-computefluxOpenAI-compatible multi-model inference via ComputeFlux (Polkadot testnet, TEE-verifiable). stdio.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- DDG Agent Services @daedalusdevelopmentgroup-com/ddg-agent-services-mcpPay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.14% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- jevjam @beremaran/jevjamTyped decisions (choice, score, yes/no) from Laya, Julia-1 and clef-flash on your own GPU4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- LEEVAR reliability battery @forevercrab321-svg/leevarGrade an AI agent's transcripts on 18 reliability tests. Thin evidence is NOT TESTED, not guessed.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- 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.
- AlphaFold @mrfentmen/alphafold-mcpKeyless MCP server for AlphaFold: protein structure predictions by UniProt accession, confidence...6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Laya @dockndevai/mcp-layaSafe-by-default MCP for Laya: fast, local, typed decisions (classify/score/yes-no), 100+ langs.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- TensorCAD @filip-pajalic/tensorcadDesign transformer LLM architectures and report their parameters, FLOPs, memory and cost3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Laya Typed Decisions @perrylink/laya-mcpTyped noul / choice / score judgments from a local Laya model, with token-budget preflight.3% 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.
- RyRank @trigeochiral/ryrankCohere-compatible pay-per-call reranker, no signup, x402/USDC6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Rechtssysteem.ai @rechtssysteem/rechtssysteem-mcpLekkage-vrije voorspelling van Nederlandse rechtszaken, getraind op 609.715 uitspraken9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- ~alter mcp-ollama @true-alter/mcp-ollamaWraps local Ollama models so bulk generation runs on your own hardware, not a paid API.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Model Manager @setheerwagen/mcp-modelmanagerManage your local model machine over MCP: state, model pull/remove, service switch, LoRA training5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- BanditDB @banditdb/mcpPersistent decision memory for agents — learns which action works in which context3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
