Fetch the complete Odds-API.io API documentation.
AI agents call get_documentation to retrieve information from Odds-API 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 documentation—informational content with no ability to modify, delete, execute code, or affect financial systems. The word 'Fetch' confirms a read-only operation. Even in the context of a sports betting API server, documentation access poses minimal risk as it cannot execute trades, modify data, or trigger external operations.
From the tool's definition Tool name 'get_documentation' and description 'Fetch the complete Odds-API.io API documentation' indicate retrieval of static reference material with no side effects.
Attacks that exploit this kind of access
Fetch the complete Odds-API.io API documentation. It is categorised as a Read tool in the Odds-API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Odds-API MCP Server MCP server in PolicyLayer and add a rule for get_documentation: 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 Odds-API MCP Server. Nothing to install.
get_documentation 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_documentation 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_documentation. 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_documentation is provided by the Odds-API MCP Server MCP server (odds-api-io/odds-api-mcp-server). 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 →