Identify the current access token, the workspace it is linked to, and any permissions it has.
AI agents call getv2self to retrieve information from Attio without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about the current authenticated session (access token, workspace, permissions). It performs no modifications, deletions, or external operations—purely a metadata retrieval operation. Severity is low because this information is already implicitly known to the agent using the token, and its disclosure does not directly enable unauthorized actions on its own.
From the tool's definition Tool name 'getv2self' and description 'Identify the current access token, the workspace it is linked to, and any permissions it has' indicates retrieval of metadata about the current authentication context with no side effects.
Documented attack patterns abuse exactly the kind of access getv2self gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Attio, and nothing reaches the server without passing your rules. This is the rule we recommend for getv2self:
{
"version": "1",
"default": "deny",
"tools": {
"getv2self": {}
}
}getv2self is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Identify the current access token, the workspace it is linked to, and any permissions it has. It is categorised as a Read tool in the Attio MCP Server, which means it retrieves data without modifying state.
Register the Attio MCP server in PolicyLayer and add a rule for getv2self: 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 Attio. Nothing to install.
getv2self 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 getv2self 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 getv2self. 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.
getv2self is provided by the Attio MCP server (itsbrex/attio-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Attio, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
57 Attio tools catalogued and risk-classified — across an index of 43,000+ MCP servers.