AI agents call query_architecture to retrieve information from Knocoph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and retrieves information about code structure from a pre-built SQLite knowledge graph. It returns read-only metadata about file-level symbols and their relationships. There are no side effects, no code execution, no destructive operations, and no financial implications. This is a straightforward data retrieval tool, similar to a database SELECT query for navigation purposes.
From the tool's definition Tool provides a 'file-level view' of 'symbols a file defines' and 'cross-file relationships' in a code knowledge graph, enabling 'structural codebase navigation via deterministic graph queries' without reading source files.
Attacks that exploit this kind of access
File-level view. What symbols a file defines and what cross-file relationships it participates in. It is categorised as a Read tool in the Knocoph MCP Server, which means it retrieves data without modifying state.
Register the Knocoph MCP server in PolicyLayer and add a rule for query_architecture: 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 Knocoph. Nothing to install.
query_architecture 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_architecture 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_architecture. 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_architecture is provided by the Knocoph MCP server (jagonzalr/knocoph). 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 →