Update a project
AI agents use update_project to create or update resources in Quarterback — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Quarterback environment.
This tool modifies project data reversibly. Users can typically undo or re-update projects, making it a Write operation rather than Destructive. The blast radius depends on project scope and permissions—unauthorized updates could disrupt multi-project orchestration—but the impact is generally containable and reversible, warranting medium severity.
From the tool's definition The tool is named 'update_project' with description 'Update a project', indicating modification of existing project data.
Attacks that exploit this kind of access
Update a project. It is categorised as a Write tool in the Quarterback MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Quarterback MCP server in PolicyLayer and add a rule for update_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 Quarterback. Nothing to install.
update_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 update_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 update_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.
update_project is provided by the Quarterback MCP server (bobbyrgoldsmith/quarterback). 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 →