"Analysis of Grafana Dashboards" 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).

UI VerifyA

ai.uiverify

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.

Machine-readable taxonomy of 100+ AI system failure modes spanning factuality, alignment, planning, code generation, and instruction following.

Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.

Compare two versions of a JSON row list: what was added, removed or changed, field by field.

Ensemble testing of web pages for accessibility, usability, and standards conformity

Checks the structural integrity of translated resource dictionaries against a source dictionary y...

RFC 3986 unreserved charset, input discarded

ESLint rules key count, body discarded

GB18030 4-byte band, input discarded

bcrypt $2 hash shape, value discarded

ARIA role token charset, value discarded

CUID2 length band, value discarded

wyhash hex length, input discarded

SM3 hex length, input discarded

Lowercase hex charset, input discarded

Cookie name charset, value discarded

Regex compile check, pattern discarded

XML well-formed check, body discarded

Integer square-root band, number discarded