kb_save · Knowledge Base MCP Server MCP: Risk & Policy

WHAT IT DOES

What kb_save does on Knowledge Base MCP Server

AI agents use kb_save to create or update resources in Knowledge Base MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Knowledge Base MCP Server environment.

WHY IT NEEDS A POLICY

Why kb_save needs a policy

This tool creates or modifies data in a knowledge base (ChromaDB) in a reversible manner. It does not execute external code, delete data irreversibly, move money, or retrieve data—it performs a write operation. The medium severity reflects that an AI agent could pollute or corrupt the knowledge base with incorrect information, but the effects are reversible via kb_delete or by overwriting entries.

From the tool's definition Tool name is 'kb_save' and description states 'Save knowledge to the persistent memory store.' The verb 'save' indicates creation or modification of data in a persistent store.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kb_save Rate-limited

kb_save 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": {
    "kb_save": {
      "limits": [
        {
          "counter": "kb_save_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 Knowledge Base MCP Server, so you can run agents against it safely.

FAQ

Questions about kb_save

What does the kb_save tool do? +

Save knowledge to the persistent memory store. It is categorised as a Write tool in the Knowledge Base MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on kb_save? +

Register the Knowledge Base MCP Server MCP server in PolicyLayer and add a rule for kb_save: 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 Knowledge Base MCP Server. Nothing to install.

What risk level is kb_save? +

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

Can I rate-limit kb_save? +

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

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

kb_save is provided by the Knowledge Base MCP Server MCP server (leon4s4/knowledge-base-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.