Returns detailed information about a specific function or class as a Markdown string including callers/callees.
AI agents call get_symbol_context to retrieve information from Memex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents contextual information about code symbols from the knowledge graph. It performs a read-only query operation analogous to 'get' or 'fetch'. There is no capability to modify, delete, or execute code. Even in a misuse scenario, an AI agent querying symbol context cannot cause irreversible damage, financial loss, or uncontrolled external execution.
From the tool's definition Tool 'Returns detailed information' about a symbol, serving as a retrieval/query operation. The description indicates it retrieves and formats existing data (function/class metadata, callers, callees) with no mention of modifications, deletions, or side…
Documented attack patterns abuse exactly the kind of access get_symbol_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memex, and nothing reaches the server without passing your rules. This is the rule we recommend for get_symbol_context:
{
"version": "1",
"default": "deny",
"tools": {
"get_symbol_context": {}
}
}get_symbol_context 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.
Returns detailed information about a specific function or class as a Markdown string including callers/callees. It is categorised as a Read tool in the Memex MCP Server, which means it retrieves data without modifying state.
Register the Memex MCP server in PolicyLayer and add a rule for get_symbol_context: 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 Memex. Nothing to install.
get_symbol_context 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_context 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_context. 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_context is provided by the Memex MCP server (stifler7/memex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memex, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Memex tools catalogued and risk-classified — across an index of 43,000+ MCP servers.