AI agents call get_index 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.
This tool retrieves platform metadata (endpoints, available APIs) for informational purposes. No data is created, modified, deleted, or executed—it only queries and returns structural information about the Decixa platform. The blast radius of misuse is minimal since it only exposes what APIs exist, not the data or capabilities to invoke them destructively.
From the tool's definition Tool name 'get_index' and description 'Fetch the Decixa agent index' indicate retrieval of metadata about available endpoints without modification. The word 'Fetch' and 'overview' are typical of read-only operations.
Attacks that exploit this kind of access
Fetch the Decixa agent index — a machine-readable overview of the platform including available endpoints,. 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 get_index: 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.
get_index 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_index 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_index. 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_index 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 →