VeriRef / Referencing

Referencing Reference

The MCP endpoint that grounds and verifies every claim your AI Engine produces.

01 · Overview

Overview

Referencing is an MCP endpoint that any MCP-compatible LLM (Claude, ChatGPT, Gemini, Copilot) can connect to. It exposes a set of tools for verifying claims, extracting structured data, and managing a workspace-scoped library of trusted sources — all with a full audit trail.

https://mcp.varsaai.com/referencing
02 · Authentication

Bearer tokens & scopes

All requests require an Authorization: Bearer <token> header. Tokens are minted per-workspace from the app and carry one or more veriref:* scopes:

  • veriref:verify — verify_* tools
  • veriref:extract — extract_* tools
  • veriref:library.read / veriref:library.write — library_* tools
  • veriref:admin — admin_* tools
03 · Tools

Tools reference

ToolDescriptionInputs
verify_runVerify every claim in a passage against approved sources.text, vertical?, source_ids?
verify_claimVerify a single claim and return supporting/refuting sources.claim, vertical?
verify_statusPoll the status of an async verify run.run_id
verify_cancelCancel an in-flight verify run.run_id
verify_reportReturn the full audit report for a completed run.run_id, format?
verify_sourcesList sources considered for a run, with match scores.run_id
extract_runExtract structured claims, entities and citations from unstructured text.text, schema?
extract_claimsExtract atomic factual claims for downstream verification.text
extract_entitiesNamed-entity extraction (drug, company, ticker, statute…).text, vertical?
extract_citationsExtract inline and footnote citations from a document.text
extract_tablesParse embedded tables into structured rows.text|pdf_url
library_saveSave a verified source or clip to the workspace library.source, tags?, notes?
library_searchSemantic + keyword search across saved library items.query, filters?
library_getFetch a single library item with its full metadata.item_id
library_updateUpdate tags, notes or verification status on an item.item_id, patch
library_deleteDelete a library item (soft-deleted for 30 days).item_id
library_listList library items with pagination and filters.cursor?, filters?
admin_usageReturn credit consumption and tool call counts.period?
admin_scopesList the caller's active scopes.
admin_keysManage bearer tokens for the workspace.action, key_id?
admin_auditReturn the workspace audit trail.since?, cursor?
admin_workspaceRead workspace settings (members, plan, region).
04 · Sources

Sources by vertical

Life Sciences

  • PubMed
  • Europe PMC
  • openFDA
  • ClinicalTrials.gov
  • WHO ICTRP

Finance

  • SEC EDGAR
  • FRED
  • IMF
  • World Bank
  • FDIC
  • FCA
  • Companies House
  • FINRA BrokerCheck

Legal

  • CourtListener
  • Legislation.gov.uk
  • EUR-Lex
  • USPTO
  • BAILII

Insurance

  • NAIC
  • EIOPA
  • NHTSA
  • FEMA
05 · Rate limits & credits

Rate limits & credits

Each plan includes a monthly credit allowance. One verify_run consumes credits based on the number of claims verified and sources retrieved. Rate limits are 60 requests/minute per token by default, raised on request for Business and Enterprise workspaces.

When you exceed a limit the endpoint responds 429 rate_limited with a Retry-After header. See Pricing for plan credit allowances.

06 · Errors

Error codes

401 unauthorizedMissing or invalid bearer token.
403 scope_deniedToken lacks the required veriref:* scope.
404 not_foundThe referenced run_id or item_id does not exist.
409 conflictRun is already terminal (completed/cancelled).
422 invalid_inputPayload failed schema validation.
429 rate_limitedRate or credit limit exceeded — see Retry-After header.
500 internal_errorUnexpected server error. Safe to retry with backoff.
503 unavailableA downstream source is temporarily unreachable.
07 · Changelog

Changelog

2026-07-19 — Initial public reference published.