Search and investigate previous versions of your codebase. Compare checkpoint vs current working directory (with full unified diffs), compare two checkpoints against each other, retrieve any file
AI agents call vigil_diff to retrieve information from Claude Vigil without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
vigil_diff is purely informational. It retrieves and displays differences between versions and allows inspection of historical file content. No side effects, no mutations, no deletions, no execution. The tool enables safe examination of project history, consistent with the server's purpose of 'safe recovery' via non-destructive operations.
From the tool's definition Tool performs 'Search and investigate previous versions', 'Compare checkpoint vs current working directory', 'compare two checkpoints against each other', and 'retrieve any file' — all read-only operations returning diffs and file contents without modifying,…
Documented attack patterns abuse exactly the kind of access vigil_diff gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Vigil, and nothing reaches the server without passing your rules. This is the rule we recommend for vigil_diff:
{
"version": "1",
"default": "deny",
"tools": {
"vigil_diff": {}
}
}vigil_diff 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.
Search and investigate previous versions of your codebase. Compare checkpoint vs current working directory (with full unified diffs), compare two checkpoints against each other, retrieve any file. It is categorised as a Read tool in the Claude Vigil MCP Server, which means it retrieves data without modifying state.
Register the Claude Vigil MCP server in PolicyLayer and add a rule for vigil_diff: 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 Claude Vigil. Nothing to install.
vigil_diff 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 vigil_diff 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 vigil_diff. 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.
vigil_diff is provided by the Claude Vigil MCP server (vvkmnn/claude-vigil-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Vigil, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Claude Vigil tools catalogued and risk-classified — across an index of 43,000+ MCP servers.