AI agents use save_auth_profile to create or update resources in Blop — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Blop environment.
The tool saves (writes) authentication profile data, which is a reversible modification. It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). However, the lack of description creates uncertainty. Given the authentication context and potential impact on access control if misused by an AI agent, this warrants 'high' severity. The empty description lowers confidence from 0.
From the tool's definition Tool name is 'save_auth_profile'; description is empty. Context indicates this is a release confidence control plane that handles 'auditable go/no-go decisions' and authentication sessions (sibling tool 'capture_auth_session').
Attacks that exploit this kind of access
save_auth_profile. It is categorised as a Write tool in the Blop MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Blop MCP server in PolicyLayer and add a rule for save_auth_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 Blop. Nothing to install.
save_auth_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 save_auth_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 save_auth_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.
save_auth_profile is provided by the Blop MCP server (n2400813g/blop-mcp). 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 →