Split a draft response into individually verifiable atomic claims. Each claim is a single factual statement that can be independently fact-checked. Opinions, hedges, and meta-commentary are excluded. If is_refusal is true (from arsr_draft_response output) and original_query is provided, claims wi...
AI agents call arsr_decompose_claims 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.
This tool performs text analysis and decomposition, producing structured metadata about claims within existing content. It has no side effects, creates no persistent changes, and does not execute external operations or access protected resources. It is fundamentally a read/query operation on the draft response provided as input.
From the tool's definition Tool description states it 'split[s] a draft response into individually verifiable atomic claims' and 'extracts' claims.
Attacks that exploit this kind of access
Split a draft response into individually verifiable atomic claims. Each claim is a single factual statement that can be independently fact-checked. Opinions, hedges, and meta-commentary are excluded. If is_refusal is true (from arsr_draft_response output) and original_query is provided, claims will be extracted from the query instead of the draft. Args: - draft (string): The response text to decompose - original_query (string, optional): The user. 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_decompose_claims: 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_decompose_claims 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_decompose_claims 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_decompose_claims. 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_decompose_claims 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 →