start_checks
Fire-and-forget: spawn a DETACHED background run of the project
This record as markdown: /tools/ai-featureboard-featureboard/start-checks.md
What start_checks does on FeatureBoard
AI agents invoke start_checks to trigger actions in FeatureBoard. 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 start_checks is rated High
The tool executes a background process/job spawn operation, which is a side effect that runs code or triggers external operations. While the description is sparse, 'spawn a DETACHED background run' clearly indicates execution of some automation workflow. This is not merely a read (no data retrieval), write (not creating/modifying data reversibly), or destructive action.
From the tool's definition Tool description: 'Fire-and-forget: spawn a DETACHED background run of the project' — this triggers execution of an external operation (background process spawning) whose effects depend on the project state and configuration.
Attacks that exploit this kind of access
The rule that runs start_checks safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FeatureBoard, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For start_checks, this is the rule to start with:
start_checks 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 FeatureBoard, apply this rule, and every start_checks call is checked against it from then on.
Questions about start_checks
Fire-and-forget: spawn a DETACHED background run of the project. It is categorised as a Execute tool in the FeatureBoard MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FeatureBoard MCP server in PolicyLayer and add a rule for start_checks: 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 FeatureBoard. Nothing to install.
start_checks 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 start_checks 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 start_checks. 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.
start_checks is provided by the FeatureBoard MCP server (https://github.com/valentil/featureboard-mcp/releases/download/v0.7/featureboard.plugin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FeatureBoard, and thousands of servers like it.
Across the catalogue