"Cursor Not Losing Memory or State" matching MCP connectors:

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).

Check if your MCP server is ready to publish on the MCP Registry, Smithery, or npm.

Runs your code against a contract; returns HELD or BROKE at the exact input. Deterministic.

PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.

End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic.

Audits MCP tool definitions for patterns that make models call tools wrong or mis-fill args.

WCAG-Compliance/wcagc-mcp lets an assistant run real axe-core accessibility scans through the user's own wcagc account, rather than guessing accessibility from markup it can see. Tools cover a single URL or PDF, a full-site crawl, saved multi-step journeys, and violation trends.

AI-native mock API server with MCP. Create REST/SOAP mocks from Claude, Cursor, or Windsurf.

MCP server for e-mail testing: create disposable inboxes, wait for delivery, and extract e-mail content or links - all from your AI agent or test automation workflow. Get a free API key on https://app.zyntra.app/

Scan your MCP server for EU AI Act Art. 50 compliance, tool quality, OAuth hygiene, and security issues before you ship. Developer $19/mo, Team $49/mo. A technical preflight check, not legal advice.

Generate SBOMs, scan vulnerabilities, and analyze dependencies from local projects or Git repos.

NaN - DO not use, test.

Compare two JSON files deeply without worrying about key or array order. Detect missing, extra, an…