MCP 服务器目录
共收录 7530 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。
docweave-mcp
AI与LLMGenerate and read PDFs for AI agents: a generate_pdf and a read_pdf tool, priced per document.
Artel
AI与LLMSelf-hosted shared-memory & coordination mesh for AI agent fleets. You host it; agents connect.
vectordecisions-mcp-server
AI与LLMAI Governance MCP Server - GATRI trust scoring, kill-switch, EU AI Act compliance for Claude
agent-trust-mcp
AI与LLMERC-8004 agent trust scores via x402: free preview + paid USDC-on-Base signed scores (5 chains)
pulsefeed-x402
AI与LLMVerify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
AgentGo
AI与LLMRun Codex and Claude Code on your computer from an MCP client, and track or continue their runs.
contextual-mcp-server
AI与LLMRAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes.
BLEA
AI与LLMSafe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
nodedex
AI与LLMYour project's decision history for agents: decisions, dead-ends, constraints - queryable, local.
nodeflare-mcp
AI与LLMBlockchain JSON-RPC on 23 EVM chains for AI agents - free tier, API key, or x402 pay-per-call.
projectmind
AI与LLMPersistent project memory for AI coding agents: one compact digest instead of re-reading the repo.
getregdata
AI与LLMBusiness-registry data for agents: one-call Poland KYB verdict, UBO, insolvency, adverse media
NomaCMS MCP Server
AI与LLMMCP server for NomaCMS. Manage collections, fields, content, assets, and webhooks via AI agents.
InsAIts - AI Communication Security Monitor
AI与LLMRuntime AI-to-AI security monitor. 23 anomaly types, OWASP MCP Top 10 coverage.
Jev agent tools
AI与LLMEvidence-oriented code questions, diff review and test selection via a Jev endpoint.
ai-connector-for-revit
AI与LLM+50 tools to inspect, select, edit and document elements in live Revit models.
ragdrift-mcp
AI与LLMDiagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
ragmetric-mcp
AI与LLMRAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.
streamparse
AI与LLMParse partial / truncated / messy JSON for LLM tool calls and structured outputs.
omni-oracle
AI与LLMAgent-First Data Bazaar. 136 Tools for DeFi, Derivatives, Governance, Alpha & Utilities.
aurora-agent
AI与LLMFIBER decision-context compiler with honest omission accounting: 259 evidence-bearing MCP tools.
QA Radar
AI与LLMTells AI agents which files to test first — churn, coverage, and test mapping as risk scores.
socialfanout-mcp
AI与LLMOne safe tool for your AI agent to publish to every social network via the Social Fanout API.
SIMA MCP Server
AI与LLMRead-only MCP server for SIMA Solana AI agent protection discovery. No API keys required.