Zoeb Nomi
Server Details
Checks RAG citations against their sources (CrossSource method), plus claim checks. Read-only, free.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- zoeb-nomi/zoebnomi-mcp
- GitHub Stars
- 0
- Server Listing
- zoebnomi
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
fit_to_role is clearly distinct (JD-to-evidence mapping), and check_citations vs. verify_claim are separated by input shape: one takes an answer plus a `sources` list, the other checks a single claim against zoebnomi.com. Still, at surface level both are 'fact-check this text' tools, so an agent could occasionally pick the wrong one without reading past the first clause.
All three names are verb-first snake_case (check_citations, fit_to_role, verify_claim), which reads as one deliberate convention throughout. No camelCase mixing, no noun-only names, no versioned duplicates.
Three tools is on the lean side, but the domain (a personal/professional site plus citation checking) is narrow enough that each tool covers a genuinely different job. Nothing looks padded or redundant.
The surface covers verification, citation auditing and role-fit, but there is no way to retrieve or search the underlying site content broadly — verify_claim is explicitly a word lookup that 'cannot see negation', and no profile/summary or raw-source tool exists to fill that gap. Deliberate exclusions (compensation, availability, location) are fine, but the missing read path means agents can hit dead ends when they need context rather than a yes/no on a specific claim.
Available Tools
3 toolscheck_citationsCheck citations (CrossSource)ARead-onlyIdempotentInspect
Check whether each inline citation in an answer is supported by the source it points to, using CrossSource's method and failure taxonomy (supported, right_doc_wrong_passage, wrong_document, unsupported_claim). Cites to ids not in sources and citations where another passage clearly covers the claim are decided deterministically. Everything else returns needs_judgment with the CrossSource judge prompt to apply. Set use_client_model to have your client model judge those, where the client supports MCP sampling.
Inputs: answer (required), sources (required), use_client_model, include_judge_prompts.
fit_to_roleMap a job description to public workARead-onlyIdempotentInspect
Map a job description to Zoeb Nomi's public work (zoebnomi.com) with quoted evidence, and list requirements with no public evidence as gaps. Never answers compensation, availability, location or work authorization.
Inputs: job_description (required).
verify_claimVerify a claim about Zoeb NomiARead-onlyIdempotentInspect
Check a claim or number about Zoeb Nomi against what zoebnomi.com states. Returns found, number_mismatch or not_found, with the site quote, source URL, evidence link, n and date where the site gives them. Use the returned quote, not your own paraphrase. A word lookup: it cannot see negation, so read the quote.
Inputs: claim (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Free read-only checks for evidence of AI use in text, links, images, saved prompts and C2PA.
Exact source text, not summaries: check citations and quotes in one call; read pages and PDFs.
Free mechanical checks for AI text: unnamed counts, dangling references, bad arithmetic, misquotes.
Citation and retraction checker for AI agents. Give it DOIs, PubMed or arXiv ids and it says whether each paper exists and whether it was retracted, withdrawn or corrected, using Crossref and Retraction Watch. It also searches publisher articles and open research papers, shows the x402 price in USDC an agent pays to read or cite each one, and traces a passage to the page it was copied from. Free, read-only, no account.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to check a drafted answer against supplied sources or a document before stating or acting on it, returning claim-level support status, contradictions, omissions, and a verdict.MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents and users to extract factual claims from text, URLs, files, or AI answers and judge each against live web sources with confidence, evidence, and citations. It also integrates with MCP-capable clients so claims can be checked before an answer is shown.72 npmApache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables agents to verify their own output mid-task by checking every claim against provided sources, returning supported, partial, unsupported, or contradicted verdicts with exact citations.MIT
- AlicenseNot gradedqualityBmaintenanceEnables users to verify citations and bibliographies and to check whether source documents support factual claims, using local inference, exact evidence provenance, and deterministic verdicts.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.