konsulto_attach_evidence · Konsulto MCP: Risk & Policy

WHAT IT DOES

What konsulto_attach_evidence does on Konsulto

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

WHY IT NEEDS A POLICY

Why konsulto_attach_evidence needs a policy

The tool creates or adds attachments to an audit system, which is a reversible modification of data. It does not execute external code, delete data irreversibly, or move money. While uploads can affect system state, this is categorized as Write rather than Execute because the tool's primary function is to persist files/content rather than trigger arbitrary code execution.

From the tool's definition "Upload a file (or inline content) as an attachment in the active audit." — explicitly performs file upload and content attachment operations that modify the audit state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

konsulto_attach_evidence Rate-limited

konsulto_attach_evidence 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": {
    "konsulto_attach_evidence": {
      "limits": [
        {
          "counter": "konsulto_attach_evidence_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 Konsulto, so you can run agents against it safely.

FAQ

Questions about konsulto_attach_evidence

What does the konsulto_attach_evidence tool do? +

Upload a file (or inline content) as an attachment in the active audit. It is categorised as a Write tool in the Konsulto MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on konsulto_attach_evidence? +

Register the Konsulto MCP server in PolicyLayer and add a rule for konsulto_attach_evidence: 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 Konsulto. Nothing to install.

What risk level is konsulto_attach_evidence? +

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

Can I rate-limit konsulto_attach_evidence? +

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

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

konsulto_attach_evidence is provided by the Konsulto MCP server (konsulto/konsulto-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.