Detect uncommitted changes and analyze their risk level. Shows changed symbols, affected processes, and risk assessment.
AI agents call corn_detect_changes 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 analysis and reporting on existing code state. It reads git/version control metadata to identify what has changed and assesses risk, but does not execute changes, delete data, or trigger external operations. The risk assessment output is informational only. The blast radius of misuse is minimal—an agent could only obtain visibility into uncommitted changes, not alter them or cause side effects.
From the tool's definition The tool "detects uncommitted changes and analyze their risk level" with outputs of "changed symbols, affected processes, and risk assessment." These are read-only retrieval operations that query version control state without modifying code or executing…
Documented attack patterns abuse exactly the kind of access corn_detect_changes 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_detect_changes:
{
"version": "1",
"default": "deny",
"tools": {
"corn_detect_changes": {}
}
}corn_detect_changes 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.
Detect uncommitted changes and analyze their risk level. Shows changed symbols, affected processes, and risk assessment. 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_detect_changes: 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_detect_changes 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_detect_changes 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_detect_changes. 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_detect_changes 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.