recipe_run
Executes a recipe end to end: binds params, runs each step's tool in order via the registry, persists the run (see recipe_runs), and returns each step's result plus any markers_path. Recipes with state-changing steps (write/send/delete) PREVIEW first — call again with confirm:true to execute; rea...
This record as markdown: /tools/com-local-mcp-local-mcp/recipe-run.md
What recipe_run does on Local
AI agents invoke recipe_run to trigger actions in Local. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | |
params | object | — | Param overrides (merged over the recipe defaults). |
confirm | boolean | — | Set true to execute a recipe that has state-changing steps; read-only recipes ignore it. |
Parameters from the server's own tool schema.
Why recipe_run is rated High
This tool orchestrates execution of recipes that can invoke multiple other tools from the registry, including state-changing operations. While it includes a preview/confirmation mechanism for destructive operations, the core function is to execute arbitrary recipe steps in sequence.
From the tool's definition Tool description states it 'Executes a recipe end to end' and 'runs each step's tool in order via the registry'.
Attacks that exploit this kind of access
The rule that runs recipe_run safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For recipe_run, this is the rule to start with:
recipe_run stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every recipe_run call is checked against it from then on.
Questions about recipe_run
Executes a recipe end to end: binds params, runs each step's tool in order via the registry, persists the run (see recipe_runs), and returns each step's result plus any markers_path. Recipes with state-changing steps (write/send/delete) PREVIEW first — call again with confirm:true to execute; read-only recipes run immediately. A step that errors stops the run and is reported. It is categorised as a Execute tool in the Local MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
recipe_run accepts 3 parameters: name, params, confirm. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for recipe_run: 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 Local. Nothing to install.
recipe_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the recipe_run 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 recipe_run. 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.
recipe_run is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
Across the catalogue