Skip to main content
Glama
alexgoller

Illumio MCP Server

by alexgoller
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

update-workload

Update a workload in Illumio PCE by href or name, changing only the attributes you provide (hostname, labels, IPs, enforcement mode).

Instructions

Update a workload in the PCE. Identify by href (preferred) or name. Provide only fields you want to change. WRITE OPERATION: changes PCE state. In clients that gate tool calls (Claude Desktop, Claude Code), this pauses for the user to approve it -- the call has not failed and must not be retried while waiting.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hrefNoWorkload href (e.g., /orgs/1/workloads/xxxx). Preferred identifier.
nameNoWorkload name to find (alternative to href). If updating, this finds the workload.
labelsNoLabels to assign (replaces existing labels). Each item has 'key' and 'value'.
hostnameNoNew hostname for the workload
new_nameNoNew name for the workload
descriptionNoNew description for the workload
ip_addressesNoNew IP addresses (replaces existing interfaces)
enforcement_modeNoEnforcement mode to set

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changedv0.8.0
    • addedInput schema / properties / description
      Added value: +{
+  "description": "New description for the workload",
+  "type": "string"
+}
    • addedInput schema / properties / enforcement_mode
      Added value: +{
+  "description": "Enforcement mode to set",
+  "enum": [
+    "visibility_only",
+    "full",
+    "idle",
+    "selective"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / hostname
      Added value: +{
+  "description": "New hostname for the workload",
+  "type": "string"
+}
    • addedInput schema / properties / href
      Added value: +{
+  "description": "Workload href (e.g., /orgs/1/workloads/xxxx). Preferred identifier.",
+  "type": "string"
+}
    • addedInput schema / properties / ip_addresses / description
      Added value: +"New IP addresses (replaces existing interfaces)"
    • addedInput schema / properties / labels / description
      Added value: +"Labels to assign (replaces existing labels). Each item has 'key' and 'value'."
    • removedInput schema / properties / labels / items / key
      Removed value: -{
-  "type": "string"
-}
    • addedInput schema / properties / labels / items / properties
      Added value: +{
+  "key": {
+    "type": "string"
+  },
+  "value": {
+    "type": "string"
+  }
+}
    • addedInput schema / properties / labels / items / type
      Added value: +"object"
    • removedInput schema / properties / labels / items / value
      Removed value: -{
-  "type": "string"
-}
    • addedInput schema / properties / name / description
      Added value: +"Workload name to find (alternative to href). If updating, this finds the workload."
    • addedInput schema / properties / new_name
      Added value: +{
+  "description": "New name for the workload",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "name",
-  "ip_addresses"
-]
  2. Addedv1.0.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden for behavioral disclosure, and it does this exceptionally well. It explicitly flags this as a WRITE OPERATION that changes PCE state, and explains the user-approval gating behavior in Claude Desktop/Claude Code, including the critical warning not to retry while the call is paused.

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

Conciseness5/5

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

The description is compact and front-loaded: the core action, identifier strategy, partial-update behavior, and the critical write/approval warning all appear in a few purposeful sentences. No filler or repetition of schema details.

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 mutation with 8 optional parameters, no required fields, and no output schema, the description covers everything needed to call it correctly: how to identify the target, how to specify partial changes, and what to expect during an approval-gated write operation. The absence of return-value details is acceptable without an output schema and given the clear operational warning.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already documents all 8 parameters. The description adds meaningful selection semantics by stating that href is the preferred identifier, name is an alternative for finding the workload, and only provided fields will be changed. This exceeds the baseline expected when schema coverage is complete.

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?

The description states a specific verb ('Update') and a specific resource ('a workload in the PCE'), and clarifies how to identify the target via href or name. This is sufficient to distinguish it from sibling tools like create-workload, delete-workload, and update-label.

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?

The description gives clear practical usage context: identify by href (preferred) or name, and provide only the fields to change. It does not explicitly call out when not to use this tool in favor of create-workload or delete-workload, but the update semantics are stated clearly enough that an agent can infer the appropriate scope.

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