Look up API reference documentation for a Reflex symbol.
AI agents call search_api_reference to retrieve information from Reflex Docs MCP Server 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 operation that queries and retrieves documentation data without modifying, executing code, deleting data, or moving money. It has minimal blast radius—the worst outcome of misuse would be retrieving unintended documentation sections.
From the tool's definition The tool 'search_api_reference' is explicitly for 'Look up API reference documentation for a Reflex symbol'.
Attacks that exploit this kind of access
Look up API reference documentation for a Reflex symbol. It is categorised as a Read tool in the Reflex Docs MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Reflex Docs MCP Server MCP server in PolicyLayer and add a rule for search_api_reference: 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 Reflex Docs MCP Server. Nothing to install.
search_api_reference 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 search_api_reference 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 search_api_reference. 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.
search_api_reference is provided by the Reflex Docs MCP Server MCP server (itsmeadarsh2008/reflex-docs-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 →