AI agents call compare_apis to retrieve information from OathScore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only data retrieval operation that queries the OathScore database to return comparative quality metrics. No side effects occur; the tool only presents information to help agents select between APIs. The severity is low because misuse would at worst return misleading quality comparisons, not cause financial loss, execute code, or destroy data.
From the tool's definition Tool performs a comparison query of API quality scores with 'comma-separated names' as input. The description indicates it retrieves and displays existing rating data (scores 0-100) without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Compare quality scores of two or more APIs side-by-side. Pass comma-separated names, e.g. 'polygon,twelvedata'. It is categorised as a Read tool in the OathScore MCP Server, which means it retrieves data without modifying state.
Register the OathScore MCP server in PolicyLayer and add a rule for compare_apis: 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 OathScore. Nothing to install.
compare_apis 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 compare_apis 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 compare_apis. 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.
compare_apis is provided by the OathScore MCP server (moxiespirit/oathscore). 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 →