MCP servers for building, orchestrating and running autonomous AI agents, multi-agent systems and LLM tooling. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.
Security scan results for the Adapters MCP server.
Security scan results for the Tools MCP server.
Security scan results for the Gitlab MCP server.
Security scan results for the Figma Developer MCP server.
Security scan results for the Nx MCP server.
Security scan results for the N8n Nodes MCP server.
Security scan results for the Transports MCP server.
Security scan results for the Mdk MCP server.
Security scan results for the Resend MCP server.
Security scan results for the Cloudbase MCP server.
Security scan results for the Gcloud MCP server.
Security scan results for the Github Copilot App Modernization MCP server.
Security scan results for the Florentine Ai MCP server.
Security scan results for the Brightdata MCP server.
Security scan results for the T2000 MCP server.
Security scan results for the Blockrun MCP server.
Security scan results for the Agent Browser MCP server.
Security scan results for the Ateam Ai MCP server.
Security scan results for the N8n Nodes Mcp Client MCP server.
Security scan results for the Element MCP server.
Security scan results for the Genexus MCP server.
Security scan results for the Freee MCP server.
Security scan results for the Ix Mcp React MCP server.
Security scan results for the Aiterm MCP server.
AI & Agents MCP servers expose agent frameworks, orchestration engines and LLM tooling to AI assistants through the Model Context Protocol. Instead of a single chat loop, an assistant such as Claude or Cursor connected to one of these servers can create, coordinate and monitor autonomous agents: orchestrators in the LangChain, CrewAI or AutoGen ecosystems, vector memory stores, model gateways and evaluation harnesses.
Three uses dominate in practice. An assistant can spawn and coordinate sub-agents, splitting a research or coding task across specialized workers and merging the results. It can keep persistent agent memory, writing state to a vector store and recalling it across sessions. And it can route work through model gateways for batch inference, tool-call chains or automated evaluations. Because agent tooling usually wraps other services, these servers often bundle capabilities you would otherwise find under API Development or Files & Storage: HTTP clients, credential handling, workspace file access.
The security risks in this category are structural, because an orchestration server sits inside every agent loop. A malicious or over-permissioned one can read full conversation context, inject instructions into delegated agents, burn your LLM provider keys, or chain tool calls that end in code execution and silent outbound traffic. Prompt injection also amplifies here: one poisoned tool description can propagate to every sub-agent it touches. Before installing:
A hostile or careless one can: agent orchestration servers routinely see provider keys, conversation context and tool outputs, which is exactly what exfiltration needs. Stick to servers whose Trust Score, capability profile and findings you have actually reviewed, and grant the narrowest permissions your workflow allows.