This record as markdown: /tools/firebase-genkit/slowwork.md
What slowWork does on Genkit MCP
AI agents invoke slowWork to trigger actions in Genkit MCP. 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.
Why slowWork is rated High
The tool executes a simulated long-running background process. While described as a simulation, it actively runs/executes an operation. The description is vague, which lowers confidence. Background execution can consume resources or block operations, warranting medium severity. Categorized as Execute since it runs a background operation rather than reading, writing, or deleting data.
From the tool's definition 'Simulate long background work' — triggers an execution/operation that runs in the background
Attacks that exploit this kind of access
The rule that runs slowWork safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Genkit MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For slowWork, this is the rule to start with:
slowWork 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 Genkit MCP, apply this rule, and every slowWork call is checked against it from then on.
Questions about slowWork
Simulate long background work. It is categorised as a Execute tool in the Genkit MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Genkit MCP server in PolicyLayer and add a rule for slowWork: 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 Genkit MCP. Nothing to install.
slowWork 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 slowWork 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 slowWork. 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.
slowWork is provided by the Genkit MCP server (genkit-ai/genkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Genkit, and thousands of servers like it.
Across the catalogue