Search for code-level symbols (variables, functions, classes) by name and see their relationships, usage patterns, and evolution. Use this to find where a specific function/class is defined, how it\
AI agents call get_semantic_insights to retrieve information from In Memoria without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes metadata about code structure and symbol relationships. It reads semantic information from the codebase without creating, modifying, deleting, or executing any code. The search and lookup operations are passive information retrieval with no side effects.
From the tool's definition Tool performs 'Search for code-level symbols' and retrieves 'their relationships, usage patterns, and evolution.' The verbs are query/search operations with no modification, deletion, or execution capability described.
Documented attack patterns abuse exactly the kind of access get_semantic_insights gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and In Memoria, and nothing reaches the server without passing your rules. This is the rule we recommend for get_semantic_insights:
{
"version": "1",
"default": "deny",
"tools": {
"get_semantic_insights": {}
}
}get_semantic_insights is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for code-level symbols (variables, functions, classes) by name and see their relationships, usage patterns, and evolution. Use this to find where a specific function/class is defined, how it\. It is categorised as a Read tool in the In Memoria MCP Server, which means it retrieves data without modifying state.
Register the In Memoria MCP server in PolicyLayer and add a rule for get_semantic_insights: 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 In Memoria. Nothing to install.
get_semantic_insights 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_semantic_insights 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_semantic_insights. 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_semantic_insights is provided by the In Memoria MCP server (pi22by7/in-memoria). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 In Memoria tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 In Memoria tools catalogued and risk-classified — across an index of 42,500+ MCP servers.