recipe_runs
Shows the history of past recipe runs and their results (recorded by recipe_run), so you can reuse, compare, or debug an automation. Pass name for one recipe's runs, or omit for a compact history across all recipes. Pass run_id (with name) to get that run in full detail. Newest first.
This record as markdown: /tools/com-local-mcp-local-mcp/recipe-runs.md
What recipe_runs does on Local
AI agents call recipe_runs to retrieve information from Local 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 | — | Recipe name; omit for runs across all recipes. |
limit | integer | — | Max runs to return (default 20). |
run_id | string | — | Return this one run in full detail (requires name). |
Parameters from the server's own tool schema.
Why recipe_runs is rated Low
This tool retrieves historical records of past automation runs. It is purely a read/query operation with no side effects — it only displays recorded data for review, comparison, or debugging purposes.
From the tool's definition Shows the history of past recipe runs and their results
Attacks that exploit this kind of access
The rule that runs recipe_runs 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_runs, this is the rule to start with:
recipe_runs 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 Local, apply this rule, and every recipe_runs call is checked against it from then on.
Questions about recipe_runs
Shows the history of past recipe runs and their results (recorded by recipe_run), so you can reuse, compare, or debug an automation. Pass name for one recipe's runs, or omit for a compact history across all recipes. Pass run_id (with name) to get that run in full detail. Newest first. It is categorised as a Read tool in the Local MCP Server, which means it retrieves data without modifying state.
recipe_runs accepts 3 parameters: name, limit, run_id. 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_runs: 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_runs 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 recipe_runs 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_runs. 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_runs 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