Query code patterns in the knowledge graph
AI agents call query_patterns to retrieve information from Sourcesage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from the codebase knowledge graph without creating, modifying, deleting, or executing any operations. It is a safe read operation with no side effects. The low severity reflects minimal blast radius—querying patterns cannot harm the codebase or system.
From the tool's definition Tool name 'query_patterns' with description 'Query code patterns in the knowledge graph' indicates a retrieval operation. The verb 'Query' combined with the read-only nature of searching/retrieving patterns from a knowledge graph without modification.
Attacks that exploit this kind of access
Query code patterns in the knowledge graph. It is categorised as a Read tool in the Sourcesage MCP Server, which means it retrieves data without modifying state.
Register the Sourcesage MCP server in PolicyLayer and add a rule for query_patterns: 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 Sourcesage. Nothing to install.
query_patterns 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_patterns 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_patterns. 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_patterns is provided by the Sourcesage MCP server (mcpflow/sourcesage). 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 →