AI agents call gsd_state to retrieve information from Gsd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves project metadata without creating, modifying, deleting, or executing external operations. The blast radius of misuse is minimal—an agent querying state cannot corrupt data or trigger harmful actions. It belongs in the Read category with low severity.
From the tool's definition Tool name 'gsd_state' and description 'Get current GSD project state' indicate a retrieval operation with no side effects. The verb 'Get' and context of querying phase, milestone, and next steps are consistent with read-only introspection.
Attacks that exploit this kind of access
Get current GSD project state (phase, milestone, next steps). It is categorised as a Read tool in the Gsd MCP Server, which means it retrieves data without modifying state.
Register the Gsd MCP server in PolicyLayer and add a rule for gsd_state: 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_state is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gsd_state 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_state. 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_state 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 →