pressuredesk_evaluate_tool
Return a read-only BUY / WAIT / AVOID spend-gate packet before an agent pays for a target API, MCP endpoint, or tool.
This record as markdown: /tools/dev-autonomyforge-pressuredesk-pressuredesk/pressuredesk-evaluate-tool.md
What pressuredesk_evaluate_tool does on PressureDesk
AI agents call pressuredesk_evaluate_tool to retrieve information from PressureDesk without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
task | string | — | Buyer task or agent intent that explains why the target might be worth paying for. |
target | string | Yes | Paid API, x402 endpoint, MCP server, or tool URL to evaluate before spend. |
priceUsd | number | — | Quoted target price in USD for this one prospective call. |
Parameters from the server's own tool schema.
Why pressuredesk_evaluate_tool is rated Low
This tool queries spend-gate recommendations for paid APIs and endpoints. It provides decision-support data (BUY/WAIT/AVOID recommendations) to inform payment decisions, but does not itself execute payments, modify data, or trigger external operations. The explicit 'read-only' designation and the gatekeeping purpose (to advise before payment) confirm this is a data retrieval function with no side effects.
From the tool's definition Tool description explicitly states 'read-only' and 'Return a read-only BUY / WAIT / AVOID spend-gate packet before an agent pays'.
Attacks that exploit this kind of access
The rule that runs pressuredesk_evaluate_tool safely
PolicyLayer is an MCP gateway: it sits between your AI agents and PressureDesk, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pressuredesk_evaluate_tool, this is the rule to start with:
pressuredesk_evaluate_tool is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect PressureDesk, apply this rule, and every pressuredesk_evaluate_tool call is checked against it from then on.
Questions about pressuredesk_evaluate_tool
Return a read-only BUY / WAIT / AVOID spend-gate packet before an agent pays for a target API, MCP endpoint, or tool. It is categorised as a Read tool in the PressureDesk MCP Server, which means it retrieves data without modifying state.
pressuredesk_evaluate_tool accepts 3 parameters: task, target, priceUsd. Required: target. The full parameter table on this page comes from the server's own tool schema.
Register the PressureDesk MCP server in PolicyLayer and add a rule for pressuredesk_evaluate_tool: 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 PressureDesk. Nothing to install.
pressuredesk_evaluate_tool 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 pressuredesk_evaluate_tool 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 pressuredesk_evaluate_tool. 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.
pressuredesk_evaluate_tool is provided by the PressureDesk MCP server (https://pressuredesk.autonomyforge.dev/mcp/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on PressureDesk, and thousands of servers like it.
This server
Across the catalogue