This record as markdown: /tools/io-tinyfn-tinyfn/friendly-roast.md
What friendly_roast does on TinyFn
AI agents call friendly_roast to retrieve information from TinyFn without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Name to roast |
Parameters from the server's own tool schema.
Why friendly_roast is rated Low
This tool produces output (a friendly roast message) but does not read from, write to, delete, or modify any persistent data. It does not execute external commands or trigger operations with unpredictable side effects. It is a pure generative utility, classifying it as Read—specifically, a retrieval/generation function with no side effects.
From the tool's definition Tool name 'friendly_roast' and description 'Generate a friendly roast' indicate this tool retrieves or generates text content without modifying data, executing code, or causing side effects.
Attacks that exploit this kind of access
The rule that runs friendly_roast safely
PolicyLayer is an MCP gateway: it sits between your AI agents and TinyFn, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For friendly_roast, this is the rule to start with:
friendly_roast is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect TinyFn, apply this rule, and every friendly_roast call is checked against it from then on.
Questions about friendly_roast
Generate a friendly roast. It is categorised as a Read tool in the TinyFn MCP Server, which means it retrieves data without modifying state.
friendly_roast accepts 1 parameter: name. The full parameter table on this page comes from the server's own tool schema.
Register the TinyFn MCP server in PolicyLayer and add a rule for friendly_roast: 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 TinyFn. Nothing to install.
friendly_roast 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 friendly_roast 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 friendly_roast. 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.
friendly_roast is provided by the TinyFn MCP server (https://api.tinyfn.io/mcp/all/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on TinyFn, and thousands of servers like it.
This server
Across the catalogue