recipe_save
Saves a user-authored recipe manifest (JSON) to ~/.local/share/local-mcp/recipes/. Must have a name and a non-empty steps array. Returns {name}.
This record as markdown: /tools/com-local-mcp-local-mcp/recipe-save.md
What recipe_save does on Local
AI agents use recipe_save to create or update resources in Local, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Local environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
manifest | object | Yes | The recipe manifest. |
Parameters from the server's own tool schema.
Why recipe_save is rated Medium
This tool creates or modifies data in a reversible manner by saving recipe manifests to disk. It is Write rather than Execute because it stores structured data rather than running code or triggering operations whose effects depend on arguments.
From the tool's definition Saves a user-authored recipe manifest (JSON) to ~/.local/share/local-mcp/recipes/. The tool creates and persists data to the filesystem.
Attacks that exploit this kind of access
The rule that runs recipe_save 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_save, this is the rule to start with:
recipe_save stays usable, but capped: an agent stuck in a loop can't make hundreds of changes 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_save call is checked against it from then on.
Questions about recipe_save
Saves a user-authored recipe manifest (JSON) to ~/.local/share/local-mcp/recipes/. Must have a name and a non-empty steps array. Returns {name}. It is categorised as a Write tool in the Local MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
recipe_save accepts 1 parameter: manifest. Required: manifest. 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_save: 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_save 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 recipe_save 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_save. 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_save 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.
This server
Across the catalogue