AI agents call get_changed_files to retrieve information from Markview 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 the state of a git repository to report which files have changed. It does not modify, delete, or execute any operations—it only reads and reports data. Listing changed files is a standard inspection operation with no side effects or destructive capability.
From the tool's definition Tool name is 'get_changed_files' and description states 'List all changed files in a git repository'. The verb 'list' and action of retrieving file status are informational queries with no side effects.
Attacks that exploit this kind of access
List all changed files in a git repository (staged, unstaged, and untracked). It is categorised as a Read tool in the Markview MCP Server, which means it retrieves data without modifying state.
Register the Markview MCP server in PolicyLayer and add a rule for get_changed_files: 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 Markview. Nothing to install.
get_changed_files 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_changed_files 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_changed_files. 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_changed_files is provided by the Markview MCP server (mcp-server-markview). 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 →