Fact-check any claim with full evidence chain, confidence breakdown, and source reliability scores. WHEN TO USE: After any agent (including yourself) makes a factual claim about earnings, revenue, market movements, mergers, acquisitions, or any financial data. Also use proactively to verify assum...
AI agents call veroq_verify to retrieve information from Veroq without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
veroq_verify is a read-only verification and fact-checking tool that retrieves and analyzes evidence to validate claims. It has no side effects beyond returning analysis results—it neither modifies data, executes operations, nor commits financial actions. Despite the financial domain, the tool itself performs only query and analysis functions, making it a Read category risk with low severity.
From the tool's definition Tool description states it 'fact-check[s] any claim' and 'proves claims with evidence' with returns limited to verdict, confidence, and evidence. No mention of modifying, deleting, executing code, or financial transactions.
Attacks that exploit this kind of access
Fact-check any claim with full evidence chain, confidence breakdown, and source reliability scores. WHEN TO USE: After any agent (including yourself) makes a factual claim about earnings, revenue, market movements, mergers, acquisitions, or any financial data. Also use proactively to verify assumptions before making recommendations. This is the TRUST tool — it proves claims with evidence. RETURNS: • verdict: supported | contradicted | partially_supported | unverifiable • confidence: 0-1 with 4-factor breakdown (source_agreement, source_quality, recency, corroboration_depth) • evidence_chain: array of {source, snippet, url, position, reliability} — actual quotes from real sources • receipt: hashable verification proof (id, claim_hash, verdict_hash, sources_hash) • Checks 200+ verified sources first, falls back to live web search — NOTHING returns. It is categorised as a Read tool in the Veroq MCP Server, which means it retrieves data without modifying state.
Register the Veroq MCP server in PolicyLayer and add a rule for veroq_verify: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Veroq. Nothing to install.
veroq_verify is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the veroq_verify rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for veroq_verify. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
veroq_verify is provided by the Veroq MCP server (veroq-ai/veroq-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →