"A server for finding information about Bitbucket, the Git repository hosting service" matching MCP connectors:

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

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).

Rule engine with built-in simulation. 55 MCP tools for complete business rule lifecycle management.

Promotion gate for AI agents: leakage audits, exact-statistics verdicts, and a live report card.

Webhook relay for AI agents: keyless quickstart, event inspection, replay, mock payloads.

Hire a real human for real-world verification, product testing, AI output review, and errands.

Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.

Check AI work against requirements and return structured verdicts, findings, and repair steps.

Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax.

Generate realistic, FK-consistent synthetic test data for your databases from your AI assistant.

Generate deterministic placeholder image URLs and packs for docs, staging, testing, and AI agents.

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

Test the voice agents you run: scored transcripts, pass/fail verdicts, latency and WER metrics.

Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.

MCP server for the Fail Modes taxonomy — a knowledge base of AI system failure modes

Scan URLs for WCAG 2.1 violations, generate AI fixes, and produce VPAT 2.5 compliance reports.

Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only.

MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.

Read-only verifier for 25 ProofRelay MCP tools and non-confidential evidence bundles.