"An MCP that effectively manages other MCPs" 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.
Turn messy exports into clean, consistent data agents can trust, with every change logged.
Designed test case pack audit, delivered per API call as an atom service on Conduit Atoms.
Scan an AI agent's instructions and tools for behavior risks and generate probes that test them.
Free MCP server that audits any public URL: technical SEO, Core Web Vitals, indexing checks.
Applied ML validation, delivered per API call as an atom service on Conduit Atoms.
Database design review audit, delivered per API call as an atom service on Conduit Atoms.
Defined-flow auditor, delivered per API call as an atom service on Conduit Atoms.
Frontend implementation audit: a deliverable delivered per API call as an independent atom.
Assumption audit, delivered per API call as an atom service on Conduit Atoms.
C engineering review, delivered per API call as an atom service on Conduit Atoms.
Rag retrieval evaluation tuning, delivered per API call as an atom service on Conduit Atoms.
Direction, award-tier motion blocks and a local check for coding agents that build websites.
Agent evaluation scorecard, delivered per API call as an atom service on Conduit Atoms.
Adversarial testing for AI agents that move money: engine battery, Ed25519-sealed verdict reports.
Debug CORS: send the real preflight, get Chrome's exact error and the headers that fix it.
Local-first sync design audit: a deliverable delivered per API call as an independent atom service.
Agentic coding practice verdict, delivered per API call as an atom service on Conduit Atoms.
Agent safety guardrail audit, delivered per API call as an atom service on Conduit Atoms.
Correctness verification certificate, delivered per API call as an atom service on Conduit Atoms.
Release-readiness verdict, delivered per API call as an atom service on Conduit Atoms.
Zero knowledge claim audit, delivered per API call as an atom service on Conduit Atoms.
Efficient web build standard audit: a deliverable delivered per API call as an atom service.
Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Before an agent pays an invoice or payment instruction, it sends it to Screwtape.ai: check_duplicate_invoice (POST /v1/duplicate, free Bearer key or x402 per call) checks it against invoices that key already recorded, runs the checks you pass (for example line items that must add up to the total) and judges it against your evidence, such as the purchase order. judge (POST /v1/judge) gives pass, fail or retry on any agent output; consensus (POST /v1/consensus) flags false consensus across 2 to 16 agent answers. Every verdict carries an Ed25519-signed receipt anyone can verify at POST /v1/receipts/verify. judge and consensus can be paid per call with x402 ($0.005 USDC on Base or Solana, no account); a free key gives 10 calls per UTC day.
Full-stack build audit: a deliverable delivered per API call as an independent atom service.
Prediction model leakage/calibration audit, per API call as an atom service on Conduit Atoms.
Generate synthetic random user data for testing, demos, and development without using real persona.
The beta program platform for hardware and IoT teams, who run structured betas with their own testers. Connect your AI assistant to build tasks and steps, screen applicants, triage tickets, read results and track tester progress. Actions that reach testers return a preview first and take effect only after confirmation. Sign in with OAuth, with read-only or read and write access. Stomio does not recruit testers.
12 free MCP tools for local validation of emails, URLs, IP addresses, IBANs, dates, UUIDs, JSON and other structured inputs. No API key or external verification service required.
Website monitoring for AI assistants: catches pages that look broken even when the site is up.
Cloud Android 14 phones that Claude, Claude Code, Cursor and Codex can use over MCP. Ready in ~15 s. Plain-English tasks return pass/fail, steps, screenshots and video. 1¢ per phone-minute, AI included, 100 free minutes a month.
Disposable, receive-only email inboxes for AI agents. Create an address, wait for the verification email, and get the one-time code or magic link back as structured fields. Long-polling wait_for_email with sender and subject filters, attachments, sanitised HTML, and restore for later password resets. OAuth 2.1, hosted in the EU, cannot send email.
Check an online store's product catalog before you import it or send it to a shopping feed.
Verify an artifact an AI agent produced — schema, emptiness, provenance and mandate authority — before you accept the work or pay for it. Ed25519-signed and verifiable without this service; 20 checks a day free, then 0.005 USDC per call over x402.
Assign Linear, Jira or GitHub issues to an AI coding agent team that plans, builds, reviews, tests.
Runs an eight-stage isolation test against your staging Supabase and issues a signed attestation. Needs a RowAttest API key: Authorization: Bearer rak_... (create one on the API keys page in the app).
Configure mobile bug reporting and investigate saved bug reports with your coding assistant. Manage apps and reporter settings, get Android/iOS/React Native setup guidance, and read report metadata, screenshots and logs. OAuth with an existing BugScreen account and workspace. Docs: https://www.bugscreen.app/docs/mcp
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
Free audit that tests whether AI agents can find your pricing, sign-up and contact pages, and whether AI crawlers can read your site. Score out of 100. It offers tools scan_site, get_index_rank and list_index.
Diagnose why an AI agent failed and get the verified fix instantly. Free, no token.
Check that your AI is being logical. Free tool that mathematically catches contradictions in agent reasoning. No account needed. Also offers paid guardrails that converts natural language to formal verification proofs, that anyone can check succinctly.
Audit and build email signatures that survive Gmail, Outlook desktop and Apple Mail.
An open-source benchmark of how well LLMs solve nonogram puzzles, from 5x5 to 20x20.
FREE first read, no sign-up: test an EA, trading bot, indicator or MT4/MT5 report for luck and costs
Cheapest LLM that passes each task: cost per successful task and pass rate on public datasets.
Check how ready an online store is for AI shopping agents, and read public benchmarks.
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Real cost per AI result, LLM prices, switch costs, shutdown dates, A/B test sizes and judge checks.
Check an MCP tool or agent before you use it: daily census, work record, signed receipts. Free tier.
Hosted EPUBCheck: check an EPUB file against the EPUB specification and list every error.
Checks whether a web page is ready for AI agents and whether an MCP server meets directory rules
Countersign by Signalry: live checks of an agent's done claim. First call: start {subject}
Check whether a website works for AI agents before visiting it, and the steps that worked.
Cheapest LLM that passes each task: cost per successful task and pass rate on public datasets.
Read your Yellowhead Diagnostics, scans and action items in an AI assistant, and start Diagnostics.
Independent arithmetic verification for AI agents — checks that the numbers in a finished table add up, lists every mismatched cell, and returns a signed verification receipt. Checks arithmetic consistency only; does not verify source data.
Disposable email inboxes for agents and tests: create an address, wait for the email. No signup.
Backtests with costs, a held-out test that counts once, a score that counts every version tried.
Runs an eight-stage isolation test against your staging Supabase and issues a signed attestation.
Check an agent skill before you install it: which of your skills will it clash with?