Clears the active project and associated API secret from the agent state.
AI agents use deselect-project to create or update resources in Openfort MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openfort MCP Server environment.
This tool modifies agent state by removing the active project and API secret configuration. It is reversible (the project can be re-selected), so it falls under Write rather than Destructive. Misuse could disrupt ongoing operations by deselecting the active project, causing medium severity impact.
From the tool's definition Clears the active project and associated API secret from the agent state
Attacks that exploit this kind of access
Clears the active project and associated API secret from the agent state. It is categorised as a Write tool in the Openfort MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Openfort MCP Server MCP server in PolicyLayer and add a rule for deselect-project: 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 Openfort MCP Server. Nothing to install.
deselect-project 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 deselect-project 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 deselect-project. 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.
deselect-project is provided by the Openfort MCP Server MCP server (openfort-xyz/-deprecated-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →