Estimate confidence for each claim using semantic entropy and consistency analysis. Each claim receives a confidence score (0-1) and entropy score (0-1). Low confidence / high entropy indicates the claim should be fact-checked. Args: - claims (array): Claims to score, each with { id, text, source...
AI agents call arsr_score_uncertainty to retrieve information from Mcp Arsr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
arsr_score_uncertainty is a data retrieval and analysis function that computes metrics (confidence/entropy scores) on provided claims without side effects. It does not create, modify, delete, or execute external operations. The tool supports an iterative verification workflow but performs only read-like operations: scoring and estimation. No data is altered, no commands executed, and no irreversible actions occur.
From the tool's definition Tool estimates confidence and entropy scores for claims using semantic analysis. It performs no modifications, deletions, or external operations—purely analytical measurement of existing data.
Attacks that exploit this kind of access
Estimate confidence for each claim using semantic entropy and consistency analysis. Each claim receives a confidence score (0-1) and entropy score (0-1). Low confidence / high entropy indicates the claim should be fact-checked. Args: - claims (array): Claims to score, each with { id, text, source_span } - n_samples (number, optional): Number of rephrasings for entropy (default: 3) Returns: {. It is categorised as a Read tool in the Mcp Arsr MCP Server, which means it retrieves data without modifying state.
Register the Mcp Arsr MCP server in PolicyLayer and add a rule for arsr_score_uncertainty: 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 Mcp Arsr. Nothing to install.
arsr_score_uncertainty 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 arsr_score_uncertainty 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 arsr_score_uncertainty. 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.
arsr_score_uncertainty is provided by the Mcp Arsr MCP server (jayarrowz/mcp-arsr). 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 →