Retrieve the output of a completed function execution. Returns the raw output data from a purchased function. Works after the escrow has been settled (RELEASED or REFUNDED).
AI agents call get_delivery_output to retrieve information from Theagora MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (output from a completed execution) without modifying, deleting, or executing anything. It is clearly a Read operation. Severity is medium rather than low because the retrieved output could contain sensitive data or the results of arbitrary function executions purchased on the marketplace, which an agent could misuse if access controls are insufficient.
From the tool's definition Tool name 'get_delivery_output' and description 'Retrieve the output of a completed function execution. Returns the raw output data' indicate a retrieval operation with no side effects. The tool only reads data after escrow settlement.
Attacks that exploit this kind of access
Retrieve the output of a completed function execution. Returns the raw output data from a purchased function. Works after the escrow has been settled (RELEASED or REFUNDED). It is categorised as a Read tool in the Theagora MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Theagora MCP Server MCP server in PolicyLayer and add a rule for get_delivery_output: 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 Theagora MCP Server. Nothing to install.
get_delivery_output 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 get_delivery_output 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 get_delivery_output. 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.
get_delivery_output is provided by the Theagora MCP Server MCP server (theagoralabs/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 →