Read raw source code from an indexed repository. Returns full file or a line range. Use after corn_code_search to view files.
AI agents call corn_code_read 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 performs a pure read operation on indexed source code. It retrieves data (full files or line ranges) with no side effects, modification capabilities, or code execution. This is a standard query/fetch operation with minimal risk. Severity is low as unauthorized code reading poses information disclosure risk but no direct operational harm.
From the tool's definition Tool name contains 'read' and description states 'Read raw source code from an indexed repository. Returns full file or a line range.' The tool retrieves and queries source code without modification, creation, deletion, or execution of any code.
Documented attack patterns abuse exactly the kind of access corn_code_read 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_read:
{
"version": "1",
"default": "deny",
"tools": {
"corn_code_read": {}
}
}corn_code_read 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.
Read raw source code from an indexed repository. Returns full file or a line range. Use after corn_code_search to view files. 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_read: 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_read 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_read 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_read. 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_read 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.