AI agents use gsd_insert_phase 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.
The tool modifies project structure by inserting a new phase, which aligns with Write category (creates or modifies data reversibly). Not destructive since phases can be removed; not Execute since it doesn't run code or trigger external operations—it organizes workflow phases. Medium severity because inserting misplaced phases could disrupt project workflow, but the effect is recoverable.
From the tool's definition Tool description states 'Insert urgent work as decimal phase between existing phases', indicating it creates/adds a new phase element to the project structure. This is a reversible modification of project state.
Attacks that exploit this kind of access
Insert urgent work as decimal phase between existing phases. 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_insert_phase: 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_insert_phase 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_insert_phase 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_insert_phase. 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_insert_phase 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 →