Append a single entry to a log at the given path. Logs are append-only —
AI agents use append_log to create or update resources in Scratchpad — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scratchpad environment.
The tool adds new entries to a log file but does not modify or delete existing data. It is a write operation (creating new log entries) that is reversible in the sense that log entries can be deleted separately. The append-only nature limits blast radius — misuse results in unwanted log entries, not data loss or code execution.
From the tool's definition Append a single entry to a log at the given path. Logs are append-only
Attacks that exploit this kind of access
Append a single entry to a log at the given path. Logs are append-only —. It is categorised as a Write tool in the Scratchpad MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scratchpad MCP server in PolicyLayer and add a rule for append_log: 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 Scratchpad. Nothing to install.
append_log 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 append_log 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 append_log. 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.
append_log is provided by the Scratchpad MCP server (mikepressure/scratchpad-mcp). 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 →