Score one stored opportunity for a profile; returns a single Match dict.
AI agents call score_opportunity to retrieve information from Bandiradar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and evaluates a stored opportunity against a profile, producing a scoring result. It retrieves and ranks data (no side effects on storage or external systems). The context (monitoring funding opportunities) involves no financial transactions—only information retrieval and ranking. This is a Read operation with low severity.
From the tool's definition Tool 'score_opportunity' returns a Match dict result without creating, modifying, deleting, executing external operations, or moving money. The verb 'score' indicates computation/evaluation over existing data.
Attacks that exploit this kind of access
Score one stored opportunity for a profile; returns a single Match dict. It is categorised as a Read tool in the Bandiradar MCP Server, which means it retrieves data without modifying state.
Register the Bandiradar MCP server in PolicyLayer and add a rule for score_opportunity: 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 Bandiradar. Nothing to install.
score_opportunity 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 score_opportunity 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 score_opportunity. 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.
score_opportunity is provided by the Bandiradar MCP server (mayai-it/bandiradar). 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 →