put · KevoDB MCP Server MCP: Risk & Policy

WHAT IT DOES

What put does on KevoDB MCP Server

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

WHY IT NEEDS A POLICY

Why put needs a policy

The 'put' operation creates or modifies key-value pairs in the database. This is a classic Write operation—it has side effects but they are reversible. The presence of 'delete' in sibling tools confirms data can be undone. Medium severity reflects that misuse could corrupt or pollute the database, but impact is scoped to individual key-value pairs and the database remains operable.

From the tool's definition Tool name 'put' and description 'Store a key-value pair in KevoDB' indicate data creation/modification. The operation is reversible via delete() (present in sibling tools), making it Write rather than Destructive.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

put Rate-limited

put 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": {
    "put": {
      "limits": [
        {
          "counter": "put_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 KevoDB MCP Server, so you can run agents against it safely.

FAQ

Questions about put

What does the put tool do? +

Store a key-value pair in KevoDB. It is categorised as a Write tool in the KevoDB 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 put? +

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

What risk level is put? +

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

Can I rate-limit put? +

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

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

put is provided by the KevoDB MCP Server MCP server (kevodb/kevo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.