"An overview of OSINT (Open Source Intelligence)" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Check an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key.
Behind Second Look (preview): a shop's product page as clean data, source checks, price history.
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
Ensemble testing of web pages for accessibility, usability, and standards conformity
Diagnose why an AI agent failed and get the verified fix instantly. Free, no token.
An open-source benchmark of how well LLMs solve nonogram puzzles, from 5x5 to 20x20.
UI Verify is visual regression testing built for coding agents. Connect the MCP server and your agent (Claude Code, Cursor, Codex) pulls a pull request's UI changes into the conversation, views each visual diff, reads the AI judge's verdict of regression vs intended change, and accepts the intended baselines - all over MCP.
Evidence-gated task verification for AI agents. Decompose goals into acceptance criteria, attach proof (screenshot, curl, file), independent LLM judge accepts or rejects. 24 tools. Hosted remote MCP (streamable-http, OAuth 2.1 + DCR).
Reconstruct helps AI coding agents recreate digital products with high visual and functional fidelity, or combine ideas and interface patterns from multiple products into a new experience. Agents work from captured evidence and verify the result against real references instead of guessing from screenshots. The MCP server provides screenshots, element trees, measured layouts, computed styles, typography, assets, routes, recorded user flows and frontend technology insights. It exposes 60 tools, 16 resources and nine workflow skills for inspecting, designing, building and verifying products in the user’s stack. Access uses browser-based OAuth and requires a Reconstruct account. Captured content is treated as untrusted reference data; new capture requests are submitted only when the user asks.
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Does an MCP server work for a stock client? By registry name or URL. Tool drift too. Free, no key.
Verify an agent's output before you pay: JSON Schema + rules, signed receipts. Free during launch.
Check whether AI assistants can reach, read and cite a public website. No account for 4 of 5 tools.
A digital audit for small-business websites: a score out of 100 and the main problems.
AI users run real tasks on your live site and show where they get stuck, with a replay of every step
Check an online store's product catalog before you import it or send it to a shopping feed.
What is known to be broken in an MCP server or API operation, with the check that found it.
Deterministic check of logged service hours: bad dates, impossible totals, duplicates. No AI.
Machine-readable taxonomy of 100+ AI system failure modes spanning factuality, alignment, planning, code generation, and instruction following.
Pay-per-call MCP server. Vetted human experts review AI-generated content (text, images, video, audio, social posts), audit reasoning chains, run prepublish safety checks, and gate high-stakes actions for human approval. 7 paid tools at $1.00 each plus 4 free tools (list_offerings, list_expert_profiles, get_result, verify_certificate). Payment via x402, USDC on Base mainnet. Approved outputs receive an on-chain Taste content certificate downstream agents verify before consuming.
