Read-only Hyperliquid, funding-rate and cross-exchange perpetual spread tools.
AI research grounded in 300M scientific works — every citation a verifiable DOI.
Pull change requests from your Amendor board into your coding agent to build and open PRs.
Full Agent Swarm API and MCP server with local SQLite storage for multi-agent orchestration.
Read-only MCP server for Akamai CDN — properties, EdgeWorkers, DNS, network lists.
Operate Unblu deployments: health checks, conversation ops, and 300+ API endpoints.
LOLBAS, GTFOBins, and process parent-child lookups for detection engineering agents.
Classify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents.
MCP server for Dev Proxy that enables AI assistants to interact with Dev Proxy.
LinkedIn for AI assistants — search, profiles, jobs, feed, messaging, and gated writes.
A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand.
MCP server for searching Pexels stock photos, videos, and curated collections.
An MCP server that provides AI travel recommendations from Asian expats.
Autonomous UI debugging MCP server: an agent drives the browser/desktop, reports bugs + UX issues.
MCP server for Polarion ALM — read and write documents and work items.
Connect AI tools to OmniFocus on macOS to find, review, and safely update tasks and projects.
Russian construction market: 3,395 contractors, 20,322 projects, 24 search/analytics tools.
Crash-proof LLM pipelines. Resumes from failure without a database.
Model Context Protocol server for Swell e-commerce platform integration with AI assistants.
Secure MCP server for YouTube intelligence — 18 tools, OAuth2, OWASP Top 10 controls.
Homebox home inventory: search, intake, warranties, attachments, locations, tags, QR labels.
Expose deterministic ChainWeaver flows as MCP tools without LLM calls between steps.
MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.
AI contract scope violation detector. Detect scope creep, draft responses.
About AI & Agents MCP servers
This category collects servers that make agents better at being agents. You will find orchestration layers that run multi-step pipelines, routers that hand a task to the right model or sub-agent, evaluation and tracing tools, prompt and skill libraries, and bridges that let one assistant call another. Some wrap commercial model APIs; others are thin coordination layers around open-source frameworks.
Because these servers often sit between your agent and other systems, look closely at where data flows and what is logged. Prefer servers that document their tool contracts clearly, support streaming where relevant, and can run locally when the workload is sensitive. Many are new and move quickly, so check the repository's recent activity before relying on one in production.