AI agents call list_requests to retrieve information from Paraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and displays signing request data without creating, modifying, deleting, or executing operations. The 'list' verb combined with 'optional filters' indicates a passive data query. The blast radius of misuse is minimal—an attacker could enumerate or view signing requests they may not be authorized to see, but cannot modify state or trigger signing workflows.
From the tool's definition Tool name 'list_requests' and description 'List signing requests with optional filters' indicate data retrieval with no modification. This is a query/list operation typical of Read category tools.
Attacks that exploit this kind of access
List signing requests with optional filters. It is categorised as a Read tool in the Paraph MCP Server, which means it retrieves data without modifying state.
Register the Paraph MCP server in PolicyLayer and add a rule for list_requests: 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 Paraph. Nothing to install.
list_requests 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 list_requests 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 list_requests. 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.
list_requests is provided by the Paraph MCP server (servants-of-the-server-fire/paraph-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 →