AI agents use gsd_phase_complete to create or update resources in Gsd — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gsd environment.
This tool creates or modifies data reversibly (Write category). Marking a phase complete changes project metadata and state but does not delete data or execute arbitrary code. It affects project management state, making it medium severity — an AI misusing it could incorrectly advance phases, delaying or disrupting project workflows, but the action can typically be reversed by unmarking or reopening the phase.
From the tool's definition Tool name and description indicate it 'Mark a phase as complete and update roadmap' — this modifies project state by transitioning a phase to a completed status and updating associated roadmap data.
Attacks that exploit this kind of access
Mark a phase as complete and update roadmap. It is categorised as a Write tool in the Gsd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gsd MCP server in PolicyLayer and add a rule for gsd_phase_complete: 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 Gsd. Nothing to install.
gsd_phase_complete 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 gsd_phase_complete 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 gsd_phase_complete. 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.
gsd_phase_complete is provided by the Gsd MCP server (m0-ar/gsd-mcp-server). 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 →