MCP 服务器目录
共收录 31066 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。
VulnFeed
安全Dependency vulnerability scanner with EPSS scoring. 9 MCP tools. Free tier + x402.
D.O.A.I. Signal Relay
AI与LLMIntelligence subscription protocol for AI agents. Scored, filtered AI intelligence signals via MCP.
code-context
数据库Local code search for AI coding agents: hybrid keyword + semantic + SQL over an index in your repo.
mcp-server
数据库Keyword, semantic, hybrid, and SQL retrieval for AI agents, local or on Infino Cloud.
Inflectiv
搜索Search, build and manage Inflectiv datasets and AI agents, plus ChainAware on-chain intelligence.
Influence
开发工具Plan social campaigns, draft and review posts, schedule approved publishing, and read Insights.
CryptoAgentMail
通讯协作Hosted email MCP for AI agents with inboxes, send/receive, memory, recovery, and credits.
InfluxDB 3
数据库Official InfluxDB 3 MCP server: query, write and manage Core, Enterprise and Cloud databases.
unlocalhost
AI与LLMDeploy localhost to a private, authenticated link from your AI coding agent.
dns-aid
AI与LLMDiscover and publish AI agents via DNS using SVCB records (RFC 9460)
mcp-browser-research
浏览器自动化Web browsing & research for AI agents — fetch/read pages, structured extraction, Exa search.
mcp-calendar
通讯协作Google Calendar for AI agents — list/create/delete events and free-busy via OAuth token.
mcp-clickhouse
数据库Read-only ClickHouse for AI agents — analytics queries, table inspection, sizes, health.
mcp-codeaudit
AI与LLMSecurity audit for AI agents — scan code/diffs for leaked secrets, check deps via OSV.
mcp-data
数据库Tabular data for AI agents — load CSV/JSON/XLSX, query, group-by, stats (no database).
mcp-elasticsearch
搜索Read-only Elasticsearch/OpenSearch for AI agents — search, indices, mappings, count, health.
mcp-email
搜索Email for AI agents — read inbox (IMAP), search, and send (SMTP).
mcp-fetch
AI与LLMSSRF-safe URL fetch for AI agents — clean markdown/text/HTML/JSON, plus guarded REST calls.
mcp-filesystem
AI与LLMHardened filesystem for AI agents — jailed root, read-only default, traversal/symlink-safe.
mcp-git
AI与LLMRead-only Git inspection for AI agents — log, show, diff, status, blame, grep. No writes.
mcp-github
搜索GitHub for AI agents — repos, files, code search, issues, PRs, commits. Read-only default.
mcp-image
AI与LLMImage generation & editing for AI agents (Runware) — text-to-image, bg removal, upscale.
mcp-jp-doc-intel
AI与LLMJapanese document AI for agents — invoice/meishi extraction, OCR, classification (hosted API).
mcp-kafka
AI与LLMRead-only Kafka for AI agents — topics, offsets, consumer groups, peek messages, health.