build_vectorstore · Combined MCP Server MCP: Risk & Policy

WHAT IT DOES

What build_vectorstore does on Combined MCP Server

AI agents invoke build_vectorstore to trigger actions in Combined MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why build_vectorstore needs a policy

This tool initiates a potentially long-running external operation that processes S3 files and constructs or overwrites a vector store. 'Rebuild' implies the existing index can be overwritten/replaced, which borders on destructive, but since the source data (S3 markdown files) is not deleted and the operation could theoretically be re-run, it is best classified as Execute.

From the tool's definition 'Build or rebuild the knowledge base vector store from S3 markdown files' — triggers an external operation that reads from S3 and constructs/overwrites a vector store index

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

build_vectorstore Rate-limited

build_vectorstore stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "build_vectorstore": {
      "limits": [
        {
          "counter": "build_vectorstore_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Combined MCP Server, so you can run agents against it safely.

FAQ

Questions about build_vectorstore

What does the build_vectorstore tool do? +

Build or rebuild the knowledge base vector store from S3 markdown files. It is categorised as a Execute tool in the Combined MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on build_vectorstore? +

Register the Combined MCP Server MCP server in PolicyLayer and add a rule for build_vectorstore: 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 Combined MCP Server. Nothing to install.

What risk level is build_vectorstore? +

build_vectorstore is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit build_vectorstore? +

Yes. Add a rate_limit block to the build_vectorstore 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.

How do I block build_vectorstore completely? +

Set action: deny in the PolicyLayer policy for build_vectorstore. 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.

What MCP server provides build_vectorstore? +

build_vectorstore is provided by the Combined MCP Server MCP server (manish6007/mcp_servers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.