run_with_credential · Psamvault MCP: Risk & Policy

WHAT IT DOES

What run_with_credential does on Psamvault

AI agents invoke run_with_credential to trigger actions in Psamvault. 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 run_with_credential needs a policy

This tool runs arbitrary shell commands (Execute category), which is the most severe applicable risk. The ability to execute arbitrary commands with injected credentials creates critical blast radius: an AI agent could run destructive, malicious, or unintended commands against external systems using stored API keys.

From the tool's definition Tool name 'run_with_credential' combined with description '[🔑 API Key Operations] Run an arbitrary shell command with a credential injected as an' indicates execution of arbitrary shell commands with injected credentials.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_with_credential Rate-limited

run_with_credential 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": {
    "run_with_credential": {
      "limits": [
        {
          "counter": "run_with_credential_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 Psamvault, so you can run agents against it safely.

FAQ

Questions about run_with_credential

What does the run_with_credential tool do? +

[🔑 API Key Operations] Run an arbitrary shell command with a credential injected as an. It is categorised as a Execute tool in the Psamvault MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_with_credential? +

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

What risk level is run_with_credential? +

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

Can I rate-limit run_with_credential? +

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

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

run_with_credential is provided by the Psamvault MCP server (psam-717/psamvault-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.