diff_environments
Diff the SOFTWARE environment between a good run and a bad one — torch / CUDA / NCCL / driver / flash-attn versions, env vars — and flag combinations known to be broken. Feed it pip freeze, nvidia-smi, env output (or the whole job log; it extracts what it needs). Use this when compare_runs points...
This record as markdown: /tools/denpex-mcp/diff-environments.md
What diff_environments does on Denpex
AI agents invoke diff_environments to trigger actions in Denpex. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
badRun | string | Yes | The same artifacts from the failing run. |
goodRun | string | Yes | Artifacts from the last good run (pip freeze / nvidia-smi / env, or the full log). |
failureLogs | string | — | Optional: the failure output itself, for fingerprinting. |
Parameters from the server's own tool schema.
Why diff_environments is rated High
diff_environments triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs diff_environments safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Denpex, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For diff_environments, this is the rule to start with:
diff_environments 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Denpex, apply this rule, and every diff_environments call is checked against it from then on.
Questions about diff_environments
Diff the SOFTWARE environment between a good run and a bad one — torch / CUDA / NCCL / driver / flash-attn versions, env vars — and flag combinations known to be broken. Feed it pip freeze, nvidia-smi, env output (or the whole job log; it extracts what it needs). Use this when compare_runs points at a version change, or when a job breaks after an image rebuild. It is categorised as a Execute tool in the Denpex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
diff_environments accepts 3 parameters: badRun, goodRun, failureLogs. Required: badRun, goodRun. The full parameter table on this page comes from the server's own tool schema.
Register the Denpex MCP server in PolicyLayer and add a rule for diff_environments: 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 Denpex. Nothing to install.
diff_environments is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the diff_environments 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.
Set action: deny in the PolicyLayer policy for diff_environments. 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.
diff_environments is provided by the Denpex MCP server (denpex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Denpex, and thousands of servers like it.
Across the catalogue