AI agents call discover to retrieve information from Decixa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'discover' tool queries and returns a ranked list of APIs matching an intent. It performs information retrieval only, with no side effects such as data modification, code execution, or resource consumption. While it helps agents select APIs, the tool itself does not execute those APIs or trigger external operations. This is consistent with Read category tools that retrieve or query data.
From the tool's definition Tool description states 'List APIs ranked by intent. Returns multiple candidates' — a read-only retrieval operation with no modification or execution of external systems.
Attacks that exploit this kind of access
List APIs ranked by intent. Returns multiple candidates so the agent can choose. It is categorised as a Read tool in the Decixa MCP Server, which means it retrieves data without modifying state.
Register the Decixa MCP server in PolicyLayer and add a rule for discover: 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 Decixa. Nothing to install.
discover 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 discover 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 discover. 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.
discover is provided by the Decixa MCP server (koki-socialgist/decixa-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 →