Find all symbols that call or reference the specified symbol by its numeric ID.
AI agents call knowledge_get_callers to retrieve information from Knowledge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries the knowledge base to return caller information for a symbol. It does not create, modify, delete, or execute any operations—it simply navigates and returns data from the existing codebase graph. The narrow, deterministic purpose (finding callers of a symbol) and read-only nature place it firmly in the Read category with low severity.
From the tool's definition Tool 'finds all symbols that call or reference' a specified symbol—a query operation with no modification or deletion. No side effects mentioned.
Attacks that exploit this kind of access
Find all symbols that call or reference the specified symbol by its numeric ID. It is categorised as a Read tool in the Knowledge MCP MCP Server, which means it retrieves data without modifying state.
Register the Knowledge MCP server in PolicyLayer and add a rule for knowledge_get_callers: 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 Knowledge MCP. Nothing to install.
knowledge_get_callers 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 knowledge_get_callers 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 knowledge_get_callers. 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.
knowledge_get_callers is provided by the Knowledge MCP server (paulthesecond/knowledgebase-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 →