14,252 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
The internet's infrastructure graph for AI agents - 46B nodes and edges, free trial via 2 HTTP calls. Runs locally from the @whisper-security/whisper-graph-mcp npm package. Needs 1 environment variable to run.
★not rated 1 3mo agoA
tokens not measured
originalApache-2.0
MCP server for Routara — OpenAI-compatible LLM, image & video APIs at api.routara.ai. Runs locally from the routara-mcp npm package. Needs 1 environment variable to run.
★not rated 1 24d agoA
tokens not measured
originalMIT
MCP server "climate-ipcc-rag" as configured in AswaniSahoo/climate-risk-agent. Runs in Docker (ghcr.io/aswanisahoo/climate-ipcc-rag-mcp:0.1.0). Needs 3 environment variables to run.
★not rated 1 15d agoA
tokens not measured
originalMIT
A locally run MCP server that collects trending lists from more than 55 online platforms, including Weibo, Zhihu, Bilibili, and GitHub. It can provide this information for language-model or RAG workflows, where an AI answers using retrieved source data.
★not rated 1 7mo agoA
tokens not measured
originalMIT
Keyphrases MCP server - Model Context Protocol server to extract keyphrases from a text using a BERT model. Runs locally from the keyphrases-mcp Python package.
★not rated 1 1y agoA
tokens not measured
originalMIT
MCP server for self-hosted AI agent memory, semantic search, vector RAG, and Montycat. Runs locally from the memocat-mcp Python package. Needs 2 environment variables to run.
★not rated 1 2mo agoA
tokens not measured
originalMIT
CLI and MCP server for tracing which neurons and attention heads drive a language model's output, built on TransformerLens. Runs locally from the neuronscope-cli Python package.
★not rated 1 5d agoA
tokens not measured
originalMIT
Adorbis AI MCP server. One key, 40+ models, auto-routed. Runs locally from the @adorbistech/mcp-server npm package. Needs 1 environment variable to run.
Use when creating, modifying, validating, running, or reviewing CQ ML experiments that use cq.yaml, pcq contract scripts, RunRecord artifacts, or CQ worker execution.
MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking. Runs locally from the nvidia-nim-mcp npm package. Needs 7 environment variables to run.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor. Runs locally from the @index9/mcp npm package. Needs 1 environment variable to run.
★not rated 1 5mo agoA
tokens not measured
archived
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f. Remote server at anthropic-google-auth-oauthlib-mc-70ac16.getvda.ai.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Give your agent eyes. Search video, images, and audio via the Mixpeek multimodal retrieval API. Runs locally from the @mixpeek/mcp npm package. Needs 3 environment variables to run.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop. Runs locally from the @nugehs/aiglare npm package.
★not rated 1 4mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: