Wrap raw HTML into a standard Tri‑Tender output object that the
AI agents call final_output to retrieve information from Tri-Tender Pricing MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool wraps existing HTML into a structured output object, which is a read/transform operation with no writes, deletions, or external side effects. Confidence is moderate because the description is truncated and incomplete, but the described behavior suggests pure formatting.
From the tool's definition 'Wrap raw HTML into a standard Tri-Tender output object' — this is a data transformation/formatting operation with no side effects
Attacks that exploit this kind of access
Wrap raw HTML into a standard Tri‑Tender output object that the. It is categorised as a Read tool in the Tri-Tender Pricing MCP MCP Server, which means it retrieves data without modifying state.
Register the Tri-Tender Pricing MCP server in PolicyLayer and add a rule for final_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 Tri-Tender Pricing MCP. Nothing to install.
final_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 final_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 final_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.
final_output is provided by the Tri-Tender Pricing MCP server (sendsta/tri_tender_pricing_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 →