Read content from a file in the scratchpad workspace.
AI agents call scratchpad_read_file to retrieve information from TTG Scratchpad MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/retrieves data from files without altering state or triggering side effects. It falls squarely within the Read category—the lowest risk classification. The isolated workspace context and activity logging mentioned in the server description provide additional containment and auditability.
From the tool's definition Tool name 'scratchpad_read_file' and description 'Read content from a file in the scratchpad workspace' indicate retrieval of existing file content with no modification or deletion.
Attacks that exploit this kind of access
Read content from a file in the scratchpad workspace. It is categorised as a Read tool in the TTG Scratchpad MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TTG Scratchpad MCP Server MCP server in PolicyLayer and add a rule for scratchpad_read_file: 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 TTG Scratchpad MCP Server. Nothing to install.
scratchpad_read_file 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 scratchpad_read_file 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 scratchpad_read_file. 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.
scratchpad_read_file is provided by the TTG Scratchpad MCP Server MCP server (mrgizmo212/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 →