AI agents call vercel-blob-head to retrieve information from Mcp Gmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a HEAD request equivalent to retrieve blob metadata without downloading the full content. This is a read-only operation with no capability to modify, execute, or delete data. The narrow scope and lack of side effects justify low severity classification.
From the tool's definition Tool name is 'vercel-blob-head' and description states 'Get metadata for a blob without downloading its content.' This is a retrieval operation that queries metadata only, with no modification or side effects.
Attacks that exploit this kind of access
Get metadata for a blob without downloading its content. It is categorised as a Read tool in the Mcp Gmail MCP Server, which means it retrieves data without modifying state.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for vercel-blob-head: 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 Mcp Gmail. Nothing to install.
vercel-blob-head 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 vercel-blob-head 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 vercel-blob-head. 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.
vercel-blob-head is provided by the Mcp Gmail MCP server (@monsoft/mcp-gmail). 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 →