Get a 360° view of a code symbol: its methods, callers, callees, and related execution flows. Essential for exploring class hierarchies.
AI agents call corn_code_context to retrieve information from CornMCP 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 code metadata and relationships—pure read operations on a codebase. There is no indication it modifies, deletes, or executes code. The highest risk would occur if misused to exfiltrate sensitive code patterns, but that is a confidentiality concern, not a functional risk category. It fits squarely in the Read category as a code analysis and navigation utility.
From the tool's definition Tool description states it 'Get[s] a 360° view' and performs exploration of code structure—no modification, deletion, or execution of code is mentioned. The verbs used are passive retrieval: 'get', 'exploring'.
Documented attack patterns abuse exactly the kind of access corn_code_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CornMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for corn_code_context:
{
"version": "1",
"default": "deny",
"tools": {
"corn_code_context": {}
}
}corn_code_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.
Get a 360° view of a code symbol: its methods, callers, callees, and related execution flows. Essential for exploring class hierarchies. It is categorised as a Read tool in the CornMCP MCP Server, which means it retrieves data without modifying state.
Register the Corn MCP server in PolicyLayer and add a rule for corn_code_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 CornMCP. Nothing to install.
corn_code_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 corn_code_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 corn_code_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.
corn_code_context is provided by the Corn MCP server (yuki-20/cornmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 CornMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 CornMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.