AI agents call query_chains to retrieve information from Ariadne without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches for cross-service chain information based on query parameters. It performs no modifications, deletions, code execution, or financial operations. The blast radius of misuse is minimal — an agent might retrieve sensitive service topology information, but this is a read-only lookup operation.
From the tool's definition Tool description states 'Query cross-service chains' — a retrieval operation. The term 'query' combined with 'by business term or endpoint name' indicates a search/lookup function that retrieves existing microservice dependency information without…
Attacks that exploit this kind of access
Query cross-service chains by business term or endpoint name. It is categorised as a Read tool in the Ariadne MCP Server, which means it retrieves data without modifying state.
Register the Ariadne MCP server in PolicyLayer and add a rule for query_chains: 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 Ariadne. Nothing to install.
query_chains 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 query_chains 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 query_chains. 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.
query_chains is provided by the Ariadne MCP server (whyy9527/ariadne). 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 →