redact_artifact · Agent Evidence MCP: Risk & Policy

WHAT IT DOES

What redact_artifact does on Agent Evidence MCP

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

WHY IT NEEDS A POLICY

Why redact_artifact needs a policy

An AI agent can call redact_artifact faster than any human can review — one bad instruction and it creates or modifies resources in Agent Evidence MCP by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

redact_artifact Rate-limited

redact_artifact 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": {
    "redact_artifact": {
      "limits": [
        {
          "counter": "redact_artifact_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 Agent Evidence MCP, so you can run agents against it safely.

FAQ

Questions about redact_artifact

What does the redact_artifact tool do? +

Create a new redacted screenshot artifact from an existing screenshot using one or more rectangular regions. It is categorised as a Write tool in the Agent Evidence MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on redact_artifact? +

Register the Agent Evidence MCP server in PolicyLayer and add a rule for redact_artifact: 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 Agent Evidence MCP. Nothing to install.

What risk level is redact_artifact? +

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

Can I rate-limit redact_artifact? +

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

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

redact_artifact is provided by the Agent Evidence MCP server (xiexie-qiuligao/agent-evidence-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.