Model Context Protocol (MCP) Schema for Rust

Playwright MCP server

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

Web content fetching and conversion for efficient LLM usage

基于七牛云产品构建的 Model Context Protocol (MCP) Server，支持用户在 AI 大模型客户端的上下文中通过该 MCP Server 来访问七牛云存储资源、利用 Dora 服务进行图片操作等。 如果有什么需求欢迎在下方评论，您也可以在 github 仓库中提 issue。

AutoSearch exposes a complete systematic-review pipeline as 6 MCP tools — not a thin search wrapper. `autosearch_run_research` launches an async PRISMA 2020 run (multi-source academic search across OpenAlex, Crossref, PubMed, Semantic Scholar, arXiv, ClinicalTrials.gov, DBLP and DOAJ; screening with recorded inclusion/exclusion decisions; evidence synthesis; IMRAD paper with APA references and PRISMA flow counts). Companion tools poll status, fetch the finished paper (markdown/JSON/PDF), verify any DOI live against Crossref, run one-shot evidence searches, and list runs. Citations are verified by construction: every DOI is checked against the Crossref API before it enters a deliverable, and a re-runnable citation-integrity benchmark is published at https://exatoshi.uk/trust (latest: 99/99 DOIs resolved, 0 fabricated, across 23 real deliverables — failures would be published too). Auth is a single `x-api-key` header; free account includes 50 credits. Docs with schemas, JSON examples and credit costs: https://exatoshi.uk/developers

x402 Trust Layer is the trust, security & settlement control plane for autonomous agent payments. It exposes 13 MCP tools that an agent calls around every x402 (HTTP 402) payment: - Preflight guard (spend policy + identity + URL/SSRF risk) - Know-Your-Merchant (KYM) trust & wash-trade scoring - AP2-style mandate compile & diff vs actual tool trace - Semantic delivery escrow with auto-refund on bad responses - On-chain settlement receipt verification - Agent Trust Protocol v4: passport, fraud scan, credit score, trust score v2 No API keys — the agent pays per call in USDC on Base / Solana / Polygon via the Dexter / Coinbase CDP facilitator. Works with Claude Desktop, Claude Code, Cursor, and any MCP client. Live API & dashboard: https://x402trustlayer.xyz/dashboard

LiveAuth MCP Server gives AI agents cryptographic proof-of-work + Lightning Network authentication. Agents solve a PoW challenge, get a signed JWT, and use it to call paid MCP tools. Each tool call is metered in sats and recorded as a signed revenue event with a verifiable receipt. Built on L402 (the Lightning-Native HTTP 402 protocol from Lightning Labs). Compatible with x402 (Cloudflare/Coinbase). Non-custodial — no KYC, no account, no email. Pay per call in sats over Lightning. Install: `npx -y @liveauth-labs/mcp-server` Docs: https://docs.liveauth.app/mcp-liveauth-gate Source: https://github.com/dulzuradev/liveauth-mcp

MCP server to provide Figma layout information to AI coding agents like Cursor

Callingly is an MCP server that lets AI agents actually get leads on the phone. Connect Claude, ChatGPT, or n8n and it can place a call, send an SMS, or schedule a callback — Callingly dials your sales team, plays the lead's details, and warm-transfers the conversation. 8 tools: dispatch + AI calls, SMS, scheduling, sequences, and call reporting. Remote server (streamable HTTP) with OAuth 2.0.

Secure file operations with configurable access controls

百度地图核心API现已全面兼容MCP协议，是国内首家兼容MCP协议的地图服务商。

One API for Search, Crawling, and Sitemaps

Local guardrail proxy for AI coding agents. Wraps any MCP server (stdio or Streamable HTTP) and blocks destructive tool calls — DROP TABLE, rm -rf, force-push — before they execute. TOFU catalog pinning against rug pulls, plus tool-poisoning and result-injection scanning. Single Rust binary, Apache-2.0.

Intelligence archive for AI agents. Contribute prompts, workflows, and insights to a permanent, cryptographically verifiable knowledge base. Agents earn public trust scores based on adoption and peer validation.

When your AI runs git through a shell, it reads back raw command output — hundreds of tokens of noise to extract one piece of information. GitEasy MCP returns structured data: branch names, changed files, commit history — exactly what your AI needs, nothing extra. The same git operation at a fraction of the token cost. 21 tools, plain English, zero shell parsing.

A Model Context Protocol Server connector for Perplexity API, to enable web search without leaving the MCP ecosystem.

Retrieving and analyzing issues from Sentry.io

Crypto-paid no-KYC VPS that AI agents rent and operate end-to-end over MCP — list plans, fund a USDC/USDT balance, order a server, get root access. 16 tools, Streamable HTTP, root in ~60s. No card, no human at checkout. Humans can use it too.

A Serper MCP Server

Generates high-quality unit tests for Python code with a coverage before/after report on every run. Derives concrete edge cases (None inputs, numeric boundaries, empty collections, exception paths) and returns ready-to-run pytest files with external I/O automatically mocked. Free tier: 100 executions. Pro: $19/month.

AI image generation using various models

Ephemeral REST chatrooms where AI agents of different owners coordinate on a shared task. A room is one URL — no SDK, no registration. The owner creates a room, hands the URL to agents, and watches the conversation live in a browser. Remote MCP server at https://roomcomm.ru/mcp (create_room, read_messages, send_message, get_context, verify_integrity). Optional LLM arbiter tracks negotiation threads, flags contradictions, and chains every revision into a tamper-evident Ed25519-signed ledger.

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.