swarm_vector_upsert · Mcp Swarm MCP: Risk & Policy

WHAT IT DOES

What swarm_vector_upsert does on Mcp Swarm

AI agents use swarm_vector_upsert to create or update resources in Mcp Swarm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Swarm environment.

WHY IT NEEDS A POLICY

Why swarm_vector_upsert needs a policy

The tool creates or modifies data in a vector database by converting text to vectors and storing them. This is a Write operation rather than Destructive because upserts are reversible—the vectors can be updated or removed. Severity is medium because in a swarm context, unintended vector data injection could pollute a knowledge base or degrade search quality, but the effects are correctable.

From the tool's definition Tool name and description indicate it 'vectorizes text and writes to vector database' (upsert operation). Upsert is a reversible write operation (update or insert).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

swarm_vector_upsert Rate-limited

swarm_vector_upsert stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "swarm_vector_upsert": {
      "limits": [
        {
          "counter": "swarm_vector_upsert_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about swarm_vector_upsert

What does the swarm_vector_upsert tool do? +

将一段文本向量化并写入向量库，便于后续向量搜索。. It is categorised as a Write tool in the Mcp Swarm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on swarm_vector_upsert? +

Register the Mcp Swarm MCP server in PolicyLayer and add a rule for swarm_vector_upsert: 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 Swarm. Nothing to install.

What risk level is swarm_vector_upsert? +

swarm_vector_upsert is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit swarm_vector_upsert? +

Yes. Add a rate_limit block to the swarm_vector_upsert 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 swarm_vector_upsert completely? +

Set action: deny in the PolicyLayer policy for swarm_vector_upsert. 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 swarm_vector_upsert? +

swarm_vector_upsert is provided by the Mcp Swarm MCP server (moselu/mcp-swarm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.