"A service for financial news and stock market data" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Conformance checker for MCP servers. Free, no key, verdicts recomputable and re-measured daily.
Run EPUBCheck for EPUB specification errors and compare two exports.
Parse WebVTT, SRT, or TTML for conformance, timing, overlaps, line length, and reading speed.
Lint a SKILL.md for frontmatter, structure, secrets and size. All 6 tools free.
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
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.
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Audit any email signature and build ones that survive real email clients. check_email_signature takes the HTML of an existing signature and returns a verdict for Gmail web, Gmail Android, Gmail iOS, Outlook 365, Outlook desktop (Windows), Apple Mail and iOS Mail, plus every problem found with the rule it breaks and how to fix it. Free, no account needed. email_client_compatibility_matrix answers what a given client supports across 12 HTML and CSS features that decide whether a signature holds up: tables, flex and grid, style blocks, background-image, base64 images, border-radius, letter-spacing, text-transform, web fonts, max-width, td margins and image sizing. create_email_signature returns ready-to-paste HTML built to those rules: tables only, inline CSS, absolute pixel widths, email-safe fonts, and images by absolute URL rather than base64, which Gmail refuses to render. Also available as a free web tool at signatureforever.com/en/check. Built by VARGER Group LLC.
Load testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.
Verify before your agent acts on data it paid for. Signed verdicts, checkable offline, via x402.
Accessibility and WCAG data for your own websites: fix lists, live checks, and fix validation.
Author and validate Calaf workspace seeds against the app's real importer. No account needed.
Generate synthetic random user data for testing, demos, and development without using real persona.
Simulate, test, and analyze cloud architectures without deploying real infrastructure. Cloud World Model enables AI agents to model cloud environments, evaluate architecture behavior and costs, run failure and chaos simulations, and explore infrastructure scenarios across cloud providers.
Workflow planning, recovery checkpoints, coordination, fixtures, and compatibility tools for agents.
Moderated usability testing: read sessions, notes, transcripts, reports, and draft test scenarios.
Test-inbox API for email and SMS: create inboxes, long-poll messages, extract OTPs and links.
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).
Free platform to test MCP clients without installing anything. Create mock tools with dynamic templates, configurable delays, conditions (if/then), and response sequences. Supports JSON-RPC 2.0 over Streamable HTTP. Built-in text_echo and json_echo tools. Rate-limited tiers: anonymous (5 calls/min, 1 mock tool), registered (10 calls/min, 4 mock tools), premium (60 calls/min, unlimited). Zero setup — no install, no registration required. More info: https://www.testmcp.dev
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
