AI agents call get_symbol_detail to retrieve information from Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves source code information from the codebase knowledge graph. It performs a lookup operation only, returning data about code symbols without creating, modifying, deleting, or executing anything. The 'Return' verb and read-only nature clearly indicate a Read category classification with low severity, as misuse would only expose existing code information rather than cause harm.
From the tool's definition Tool description states 'Return the source code and location for a single function, class, or method by name' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Return the source code and location for a single function, class, or method by name. It is categorised as a Read tool in the Context MCP Server, which means it retrieves data without modifying state.
Register the Context MCP server in PolicyLayer and add a rule for get_symbol_detail: 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 Context. Nothing to install.
get_symbol_detail 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_symbol_detail 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_symbol_detail. 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_symbol_detail is provided by the Context MCP server (vibhasdutta/context-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 →