Categories › AI & Agents › Multi-agent, orchestration & workflows
Free report citation preflight and real-source trials; paid evidence via a local wallet adapter.
Remote server: your requests and data go to batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site. Claude Code: claude mcp add --transport http batchloom-evidence https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
audit_report_citations — Free deterministic audit of caller-supplied report text and structured references using [cite:id] markers. Lists unmarked text blocks, unknotrial_evidence — Try one supported source and one quote with the production extractor. No payment or durable receipt. Shared free quota plus 2 attempts/cliencompare_evidence_snapshots — Compare two supplied evidence snapshots bound to the same input. No fetch, payment or content storage. Unreadable sources and changed/unknowprepare_evidence_request — Validate input, compute its canonical hash and read exact payment/client requirements and receipt storage readiness. Fetches no source, geneget_evidence_contract — Read price, exact supported hosts, limitations and safe purchase recovery. No network crawl or payment.get_evidence_sample — Read a fixed synthetic evidence example. No live fetch, payment or truth guarantee.validate_evidence_request — Check bounded URLs and literal quotes against the fixed host list before purchase. Does not fetch pages or establish source availability. Noget_manifest — Read the free product manifest, source-license price, endpoint limits and purchase/recovery instructions. Does not buy or sign anything.get_sample — Read three free fixed SVG examples. No source toolkit is included.preview_assets — Render one product as up to three SVG assets for free. Arguments are the render input directly, not an input wrapper; maximum 8192 UTF-8 bytvalidate_batch — Validate up to 100 products and 3 formats for free. Arguments are the render input directly. Returns validity, product count, expected assetNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.