cja_run_report · Adobe Cja MCP: Risk & Policy

WHAT IT DOES

What cja_run_report does on Adobe Cja

AI agents invoke cja_run_report to trigger actions in Adobe Cja. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why cja_run_report needs a policy

Although the description is empty, the tool name 'run_report' in the context of an Adobe Customer Journey Analytics server suggests executing analytical queries whose effects depend on arguments (filters, date ranges, dimensions). This is categorized as Execute rather than Read because 'run' implies active execution of an operation, potentially with logging, API calls, or state changes in the analytics system.

From the tool's definition Tool name 'cja_run_report' combined with sibling context showing read operations (list_*, get_*) and data creation operations (create_*). The 'run_report' verb indicates execution of a potentially complex analytical operation with side effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cja_run_report Rate-limited

cja_run_report stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cja_run_report": {
      "limits": [
        {
          "counter": "cja_run_report_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about cja_run_report

What does the cja_run_report tool do? +

cja_run_report. It is categorised as a Execute tool in the Adobe Cja MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cja_run_report? +

Register the Adobe Cja MCP server in PolicyLayer and add a rule for cja_run_report: 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 Adobe Cja. Nothing to install.

What risk level is cja_run_report? +

cja_run_report is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit cja_run_report? +

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

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

cja_run_report is provided by the Adobe Cja MCP server (markhilton/adobe-cja-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.