AI agents use gsd_set_profile 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 modifies a profile setting, which is a form of configuration data mutation. It is not Read (no query), not Execute (no code/command execution), not Destructive (changes are reversible via another gsd_set_profile call), and not Financial. Write is appropriate for configuration changes.
From the tool's definition Tool name 'gsd_set_profile' and description 'Switch model profile' indicate modification of configuration state. The verb 'set' combined with 'profile' (a configuration entity) and 'switch' suggests reversible state change.
Attacks that exploit this kind of access
Switch model profile. 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_set_profile: 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_set_profile 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_set_profile 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_set_profile. 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_set_profile 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 →