Every server in the registry, with its latest security score.
Screen and score stocks with the Quality Screener engine: filters, custom scores, and history.
qcqx-project-manage MCP Server — 将项目管理能力暴露给 AI Agent（Cursor、Claude Desktop 等）
MCP server for accessing Strava API
Paid-per-call data for agents: trading calendars, futures, macro, LEI, VAT, risk events (x402)
Grantd MCP server: let your AI agent act on a user's behalf across third-party APIs via OAuth.
Persistent memory for AI agents - save once, recall in every session, project and tool.
Look up or compare free-tier developer tools, with the catch spelled out.
Persistent memory for Claude via weighted, interconnected knowledge nodes.
Offline spell checker + BYOK grammar for AI assistants. Works with Claude Desktop, ChatGPT, Cursor.
Look up real FRED (Federal Reserve Economic Data) series and historical observations.
AI agent ecosystem research, DeFi analysis, and market research tools
PDF, image, video, OCR, screenshot, SQL, QR and text tools for agents. No API key, no signup.
Offline MCP server for planning structured project specs — validate, render, and checklist tools.
Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
Inter-agent communication for multi-agent Claude Code workflows.
Image risk, EXIF/IPTC/XMP, reverse-image backlinks, content, watermark, OCR via PicDefense.io.
MCP server for Nerve blockchain JSON-RPC & REST API for AI Agents
Search, preview, and measure Umbra open SAR from any MCP client. Umbra ships no search API.
Model Context Protocol server for Refgrow affiliate program management API
Publish Markdown as a shareable web page, with document graphs
Run alias-based queries against PostgreSQL, MySQL, MongoDB and Oracle without exposing credentials.
Local-first temporal knowledge graph with six read-only MCP tools and human-reviewed writes.
Search youth opportunities (scholarships, fellowships, internships) from any AI assistant.
Verify REWORK credentials: is this delivered work genuinely the author's?
Routes to the best predicted fit from configured metadata/evidence after hard-capability filtering.
12,826–12,850 of 55,999 servers
