"Statistics of China's Population" 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.

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

Pay per call via HTTP 402: 5 site audits + a statistics engine as MCP tools, 38 /work jobs, receipts

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

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

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

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

Evidence-bound second-opinion audit of an agent conclusion against caller-supplied evidence.

CUID2 length band, value discarded

wyhash hex length, input discarded

RFC 3986 unreserved charset, input discarded

ARIA role token charset, value discarded

SM3 hex length, input discarded

Integer square-root band, number discarded

yEnc header shape, input discarded

bcrypt $2 hash shape, value discarded

GB18030 4-byte band, input discarded

Lowercase hex charset, input discarded

NDJSON shape check, body discarded