MCP 服务器目录

共收录 7330 个 MCP(Model Context Protocol)服务器,给 AI Agent 接上浏览器、数据库、搜索等工具能力。

Eval Engine API

AI与LLM

Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.

v0.1.0

sovereign-engine

AI与LLM

15 paid AI agent primitives via x402 (USDC on Base). Pay-per-call MCP server.

v0.4.0 invertedhoologan/sovereign-engine

AbaPay

AI与LLM

Non-custodial stablecoin bill-pay rails on Celo & Base for AI agents, settled on-chain via MCP.

v1.1.0 investorphem/AbaPay

invigil

AI与LLM

Linters check your code. Invigil checks whether your repo is legible — to newcomers and AI agents.

v1.7.1

Obolus

AI与LLM

Disposable Algorand wallet for AI agents. Pay x402 resources in USDC, no human provisioning.

v0.2.3 inviti8/Obolus

CLIO Arxiv

AI与LLM

ArXiv MCP server implementation using Model Context Protocol

v2.2.3 iowarp/clio-kit

CLIO Chronolog

AI与LLM

ChronoLog MCP server implementation using Model Context Protocol

v2.0.1 iowarp/clio-kit

CLIO Compression

AI与LLM

Compression MCP server implementation using Model Context Protocol

v2.2.3 iowarp/clio-kit

CLIO Hdf5

AI与LLM

HDF5 FastMCP - Scientific Data Access for AI Agents | CLIO Kit MCP Server

v2.2.3 iowarp/clio-kit

CLIO Lmod

AI与LLM

Lmod MCP - Environment Module Management for LLMs with comprehensive module operations

v2.2.3 iowarp/clio-kit

CLIO Node Hardware

AI与LLM

Node Hardware MCP - Comprehensive Hardware Monitoring and System Analysis for LLMs with...

v2.2.3 iowarp/clio-kit

CLIO Pandas

AI与LLM

Pandas MCP - Advanced Data Analysis for LLMs with comprehensive pandas operations

v2.2.3 iowarp/clio-kit

CLIO Parallel Sort

AI与LLM

Parallel Sort MCP - High-Performance Log File Processing for LLMs with advanced sorting and analysis

v2.2.3 iowarp/clio-kit

CLIO Scientific Catalog

AI与LLM

Operator-owned scientific dataset discovery for remote agents

v1.1.2 iowarp/clio-kit

CLIO Spack

AI与LLM

Structured Spack discovery and installation tools for scientific agents

v2.1.0 iowarp/clio-kit

agent-guard

AI与LLM

Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

v0.2.1 ipezygj/agent-guard

evalgate

AI与LLM

Statistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).

v0.4.1 ipezygj/evalgate

numguard

AI与LLM

Verify a number before an agent asserts it — evals, backtests (Deflated Sharpe), signed receipts.

v0.1.1 ipezygj/numguard

Agent Memory MCP

AI与LLM

Memory, docs, and repo context layer for engineering agents.

v0.13.4 ipiton/agent-memory-mcp

Iris

AI与LLM

Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.

v0.20.0 iris-eval/mcp-server

MemoryGuard

AI与LLM

Local-first governed MCP memory backend for coding agents.

v0.7.12 irisxc4/memoryguard

mcp

AI与LLM

Read-only Hyperliquid data for AI agents: fills, candles, funding, liquidations, wallet analytics.

v0.9.0 ironflowsh/mcp

secret-safe-env

AI与LLM

Write secrets into .env without the agent ever seeing the value - Windows masked dialog (繁中 UI)

v0.1.2 irrenwill/secret-safe-env

forage

AI与LLM

Self-improving tool discovery for AI agents. Find, install, and use new MCP servers automatically.

v0.1.1 isaac-levine/forage