Skip to main content
Glama
john-broadway

Proximo

by john-broadway
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

proximo_call

Run governed POST/PUT/DELETE requests for Proxmox infrastructure with dry-run planning by default, explicit confirmation to execute, and receipt-backed audit or undo.

Instructions

MUTATION: run a governed POST/PUT/DELETE. Dry-run by default: without confirm=true it returns the plan (verdict, consent id, current, change) and mutates nothing. Refused unless the operator is armed AND the address carries an authored blast-radius tier. Every call, refused or executed, is receipted. A task-backed call is waited on (wait=N s, default 60, max 600; 0 submits only) and reports finished, failed or timed out under 'task'. method=undo with path=<undo.id> puts that receipt's capture back through the vendor's PUT, plan first; withheld or unpublished keys come back as skipped.

Input Schema

NameRequiredDescriptionDefault
argsNo
pathYes
waitNo
planeYes
methodYes
confirmNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv0.46.2
    • addedInput schema / properties / args
      Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Args"
+}
    • removedInput schema / properties / arguments
      Removed value: -{
-  "anyOf": [
-    {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "The tool's arguments as an object, e.g. {'vmid': 100, 'action': 'reboot'}. Get the shape from proximo_tool_schema. Omit/null for a no-arg tool."
-}
    • addedInput schema / properties / confirm
      Added value: +{
+  "default": false,
+  "title": "Confirm",
+  "type": "boolean"
+}
    • addedInput schema / properties / method
      Added value: +{
+  "title": "Method",
+  "type": "string"
+}
    • addedInput schema / properties / path
      Added value: +{
+  "title": "Path",
+  "type": "string"
+}
    • addedInput schema / properties / plane
      Added value: +{
+  "enum": [
+    "pve",
+    "pbs",
+    "pmg",
+    "pdm"
+  ],
+  "title": "Plane",
+  "type": "string"
+}
    • removedInput schema / properties / tool
      Removed value: -{
-  "description": "Exact tool name to run, e.g. 'pve_guest_power' (from proximo_find_tools). Non-resident names are fine.",
-  "type": "string"
-}
    • addedInput schema / properties / wait
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Wait"
+}
    • changedInput schema / required
      Previous value: -[
-  "tool"
-]New value: +[
+  "plane",
+  "method",
+  "path"
+]
    • addedInput schema / title
      Added value: +"_callArguments"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "_callDictOutput",
+  "type": "object"
+}
  2. Changed2 schema fields changedv0.32.0
    • addedInput schema / properties / arguments / description
      Added value: +"The tool's arguments as an object, e.g. {'vmid': 100, 'action': 'reboot'}. Get the shape from proximo_tool_schema. Omit/null for a no-arg tool."
    • addedInput schema / properties / tool / description
      Added value: +"Exact tool name to run, e.g. 'pve_guest_power' (from proximo_find_tools). Non-resident names are fine."
  3. Addedv0.31.1

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=false; the description carries everything else an agent needs: mutation is gated by arming and blast-radius tier, every call is receipted, dry-run returns verdict/consent id/current/change, task polling bounds, and undo replays a receipt's capture with skipped keys withheld.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the mutation/dry-run fact, then the gating condition, then task and undo behavior — a sensible priority order. Some sentences are dense run-ons (the task-backed call clause) but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-parameter governed mutation tool with an output schema and only a readOnlyHint annotation, the description covers safety gating, dry-run payload shape, asynchronous task results, and undo semantics. An agent can invoke it correctly without further reading.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does: confirm=true to execute, wait semantics (default 60, max 600, 0 submits only), method=undo with path=<undo.id>, and method/plane/path as a governed vendor call. Only 'args' and the plane enum values go unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with 'MUTATION: run a governed POST/PUT/DELETE', naming the exact verb class and resource scope, which cleanly separates it from proximo_read, proximo_plan and proximo_find. The dry-run-by-default and undo modes are stated as part of the same core purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives strong when/when-not conditions: dry-run unless confirm=true, refused unless the operator is armed and the address has an authored blast-radius tier, and wait=0 to submit without polling. It does not explicitly reference proximo_plan or proximo_read as the read-only/preview path, so the routing between siblings is left partly implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools