🦊 MCPBench: A Benchmark for Evaluating MCP Servers

Budget & cost control for AI agents: hard per-agent spend caps, rate limits, idempotency, and human-in-the-loop approval — enforced before each LLM call, not after the invoice. One hosted MCP endpoint (no proxy or self-hosting), settled via x402 (USDC on Base).

A deterministic, offline design-intelligence engine for AI coding tools. Replaces improvised UI generation with structured constraints plus a rule-based anti-AI-slop linter. Ships as a Claude Code plugin, a Python package, an MCP server (18 tools), and a 17-IDE installer.

Let AI read, search, and summarize your UpNote notes — and create new ones — right from your chat.

Enable AI agents such as Claude, Co-Pilot, Codex, and other compatible tools to create, manage, and optimize advertising campaigns on ChatGPT.

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

Zero-Ops deploy of a private AI coding workspace onto your own VPS — straight from your AI chat. Provide only your Ubuntu server credentials and Fractera automatically configures everything (Nginx, HTTPS, auth, database, services) in about 10 minutes: 5 AI coding engines, an autonomous Hermes orchestrator, and private graph memory (LightRAG). No terminal, no DevOps. The deployment is IP-first and free; attaching a custom domain with HTTPS is an optional later step. The connector can register the user, recommend a VPS, run and monitor the full deploy, and answer questions about the project via get_project_info.

Automatically create a remote browser to complete your specified tasks, developed based on Browser Use + Sandbox. 自动创建一个远程浏览器，完成你指定的任务，基于Browser Use + Sandbox开发。

Secure file operations with configurable access controls

基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

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

Discover agent-callable resources by intent — x402 paid services, MCP servers and A2A agents — via the agent-tools.cloud directory. 9 tools: search/get/list_categories (x402), search_mcp_servers/get_mcp_server, search_agents/get_agent, search_all, stats.

Open-source memory for AI coding agents. Tell your agent to "remember" something in Cursor, Claude Code, Codex, or Gemini CLI, and Krimto saves it as a plain markdown file in a git repo you own — not rows in a vendor's database. Recall it later in a new chat, a different editor, or on another machine. One npx command, no account, no API key. Apache-2.0, with a user → team → org scope hierarchy so a team can share memory while personal notes stay private. Run: npx @krimto-labs/krimto init

MCP server for interacting with Neon Management API and databases

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

Browser automation and web scraping

Control your Instagram from Claude — publish photos, reels, carousels, read insights, manage comments and DMs. 14 tools via Instagram Login API. One-click free Render deploy for Claude Web and mobile.

AI image generation using various models

Appendix turns any AI health conversation into a board-certified physician's opinion — with a real prescription when clinically appropriate. Search medical literature and submit a clinical encounter for review, all from your agent.

One API for Search, Crawling, and Sitemaps

Discover verified deep-tech engineering bounties from any AI agent. Every bounty is funded in Stripe escrow before listing, and every submission is AI-verified before the buyer sees it. One tool: search_bounties.

Location services, directions, and place details

AI Agent 岗位模拟面试 MCP Server —— 基于 FAISS + bge-base-zh-v1.5 构建的 RAG 知识库，为 AI Agent 技术面试提供语义检索、分级题库和个性化学习路径。

summarize chat message

Give your AI agents native, governed access to Salesforce. 700+ purpose-built tools spanning every Salesforce object — Accounts, Leads, Opportunities, Cases, Campaigns, Orders, and more — all protected by DataGrout's enterprise security layer.

The workspace that thinks with you. Think, make, collaborate, and publish. Alongside your own personal AI. A living home for all your projects, ideas, memories, files, & meetings.

CryptoQuant MCP gives AI agents direct access to institutional-grade on-chain and market data across Bitcoin, Ethereum, XRP, stablecoins, and ERC20 tokens — covering 245 endpoints across exchange flows, miner data, network indicators, derivatives, fund data, and more. Built for analysts and developers who need defensible, data-driven answers, not approximations. Query real-time metrics like exchange netflow, MVRV, SOPR, realized price bands, funding rates, and miner revenue directly inside any MCP-compatible agent — no manual data export, no dashboard switching. Backed by CryptoQuant's professional research team, whose institutional-grade analysis is also accessible via the MCP through research and QuickTake endpoints. Supported assets: BTC, ETH, XRP, Stablecoins, ERC20, TRX Data categories: Exchange flows, miner flows, market indicators, network data, derivatives, fund data, lightning network, mempool, DeFi, AMM/DEX data

Plan, implement, and validate software changes using a virtual computer equipped with a full coding agent, development tools, browsers, and file access. Coding Agent by OpenHelm enables your agent to carry out work such as: • Implementing new features • Fixing bugs • Refactoring codebases • Updating documentation • Creating and validating pull requests What makes OpenHelm the best solution for this: • AI monitors implementation progress and verifies work against the intended outcome • Can investigate code, documentation, issues, and related systems using a real browser • Multi-step workflows support planning, coding, testing, validation, and iteration • Operates within a secure remote environment designed for autonomous development work For software teams looking to accelerate execution, OpenHelm provides an environment where development tasks can be completed from start to finish with minimal supervision.