drift_start
Begin a drift-evaluation run over a board
This record as markdown: /tools/ai-featureboard-featureboard/drift-start.md
What drift_start does on FeatureBoard
AI agents invoke drift_start 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 drift_start is rated High
The tool executes a drift-evaluation process rather than simply reading data or creating metadata. While the operation itself appears reversible and limited in scope, it triggers a computational workflow on the board state. This fits Execute (runs code or triggers external operations) rather than Read (would be 'get_drift_status' or similar).
From the tool's definition Tool description states 'Begin a drift-evaluation run over a board' — this initiates an evaluation process that triggers external operations whose effects depend on board state and content. The word 'run' indicates execution of a defined procedure.
Attacks that exploit this kind of access
The rule that runs drift_start 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 drift_start, this is the rule to start with:
drift_start 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 drift_start call is checked against it from then on.
Questions about drift_start
Begin a drift-evaluation run over a board. 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 drift_start: 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.
drift_start 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 drift_start 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 drift_start. 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.
drift_start 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