Perform a direct similarity search against the Vercel AI SDK documentation index.
AI agents call direct-query to retrieve information from Vercel Ai Docs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from a documentation index using similarity search. It is a read-only operation that queries existing data without creating, modifying, executing, or deleting anything. The natural language search interface and documentation retrieval have minimal blast radius if misused by an AI agent—worst case being retrieval of incorrect or irrelevant documentation sections.
From the tool's definition Tool performs 'direct similarity search' against documentation index with no modification or execution capabilities described.
Documented attack patterns abuse exactly the kind of access direct-query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vercel Ai Docs, and nothing reaches the server without passing your rules. This is the rule we recommend for direct-query:
{
"version": "1",
"default": "deny",
"tools": {
"direct-query": {}
}
}direct-query 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.
Perform a direct similarity search against the Vercel AI SDK documentation index. It is categorised as a Read tool in the Vercel Ai Docs MCP Server, which means it retrieves data without modifying state.
Register the Vercel Ai Docs MCP server in PolicyLayer and add a rule for direct-query: 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 Vercel Ai Docs. Nothing to install.
direct-query 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 direct-query 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 direct-query. 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.
direct-query is provided by the Vercel Ai Docs MCP server (ivanamador/vercel-ai-docs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Vercel Ai Docs, 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.
3 Vercel Ai Docs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.