Git-diff impact analysis: detects which source files and line ranges changed (HEAD vs working tree or a custom diff), maps them to graph symbols, and computes the combined blast radius. Ideal for PR review or pre-commit analysis.
AI agents call detect_changes to retrieve information from code-intel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
detect_changes is a pure analysis tool that examines differences between git states and generates impact reports. It retrieves and analyzes existing data (git diffs, symbol mappings, metrics) without creating, modifying, deleting, or executing external operations. This is a classic Read category use case—querying repository state to inform decisions rather than taking action.
From the tool's definition Tool description states it 'detects which source files and line ranges changed' and 'maps them to graph symbols' and 'computes the combined blast radius'—all read-only analysis operations.
Attacks that exploit this kind of access
Git-diff impact analysis: detects which source files and line ranges changed (HEAD vs working tree or a custom diff), maps them to graph symbols, and computes the combined blast radius. Ideal for PR review or pre-commit analysis. It is categorised as a Read tool in the code-intel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the code-intel MCP Server MCP server in PolicyLayer and add a rule for 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 code-intel MCP Server. Nothing to install.
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 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 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.
detect_changes is provided by the code-intel MCP Server MCP server (vohongtho/code-intel-platform). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →