AI agents call compare_environment_snapshots to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads two snapshot files, compares their contents, and generates a report of differences. It has no side effects, creates no persistent changes, and does not execute code or modify system state. It is a pure data analysis operation, making it a Read category tool with low severity.
From the tool's definition The tool 'compare_environment_snapshots' performs a comparison operation on two existing JSON files and reports hash drift—it retrieves and analyzes data without modifying or deleting anything.
Attacks that exploit this kind of access
Compare two local environment snapshot JSON files and report runtime, git, manifest, lockfile, and config hash drift. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for compare_environment_snapshots: 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 Todos. Nothing to install.
compare_environment_snapshots 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 compare_environment_snapshots 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 compare_environment_snapshots. 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.
compare_environment_snapshots is provided by the Todos MCP server (@hasna/todos). 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 →