MCP Servers

Find MCP servers that connect AI assistants to useful tools and data. Explore what each server does, its setup and its documentation.

Submit an MCP

2703 servers · Page 116 of 226

Server Attestation

Layer-2 supply-chain hardening for MCP servers — Ed25519-signed tool manifests, runtime spawn-attestation, default-deny argument sanitizer.

Hook Conformance

Test-harness CLI that audits any MCP server for Claude Code v2.1.118 mcptool lifecycle-hook readiness — idempotency, latency, determinism…

Rce Guard

Foundation Pillar 9: Layer-3 RCE defense for MCP servers via policy synthesis + behavioral CVE replay + cross-server canary tracking.

llm-cost

Llm-cost is a zero-dependency MCP server that gives assistants current per-million-token pricing for 69 LLM models across 17 providers and does cost… 6 tools…

Otel

W3C Trace Context bridge for the Model Context Protocol — propagate traces through MCP meta (SEP-414) and emit OpenTelemetry spans so Host → MCP…

Superargs

![Superargs: Update MCP server args from the chat](https://raw.githubusercontent.com/supercorp-ai/superargs/main/superargs.png) **Superargs** allows setting up MCP server args during runtime. Provide arguments to any **MCP server** during…

Cache Kit

Leak-safe caching for the Model Context Protocol's SEP-2549 cache hints (ttlMs + cacheScope) — set them right server-side, and never serve a private…

Explore agent skills

MCP Servers FAQ

What is an MCP server?

An MCP server exposes tools or data through the Model Context Protocol so a compatible AI client can use them. Each project has its own installation, authentication and permission requirements.

How do I install an MCP server?

Open a server’s page for its getting-started notes, compatibility and sources, then follow the original project’s documentation for your AI client.

What should I check before installing one?

Entries link to the original documentation. Check access requirements, costs and maintenance there before installing, and grant a server only the access it needs.