Writes to local state. Records that the user went outside, increments total touches, and either extends or resets the daily streak based on the gap since the last entry. Mutates ~/.touch-grass/state.json (streak, longestStreak, totalTouches, history). NOT idempotent — each call adds an entry. Err...
AI agents use log_touch_grass to create or update resources in Touch Grass — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Touch Grass environment.
This tool creates and modifies local state in a JSON file — a reversible write operation. It does not delete data irreversibly, execute code, or involve financial transactions. The blast radius is minimal since it only affects a small local state file tracking outdoor break streaks.
From the tool's definition Writes to local state. Records that the user went outside, increments total touches, and either extends or resets the daily streak. Mutates ~/.touch-grass/state.json (streak, longestStreak, totalTouches, history). NOT idempotent — each call adds an entry.
Attacks that exploit this kind of access
Writes to local state. Records that the user went outside, increments total touches, and either extends or resets the daily streak based on the gap since the last entry. Mutates ~/.touch-grass/state.json (streak, longestStreak, totalTouches, history). NOT idempotent — each call adds an entry. Errors (e.g., disk full, permission denied on ~/.touch-grass) surface as structured tool errors with isError=true; the streak is not partially updated on failure.\n\n. It is categorised as a Write tool in the Touch Grass MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Touch Grass MCP server in PolicyLayer and add a rule for log_touch_grass: 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 Touch Grass. Nothing to install.
log_touch_grass is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the log_touch_grass 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 log_touch_grass. 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.
log_touch_grass is provided by the Touch Grass MCP server (nalediym/touch-grass). 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 →