Skip to main content
Glama
alexgoller

Illumio MCP Server

by alexgoller
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

get-rulesets

Get rulesets and their rules, from draft or active policy, rendered as data: scopes as [{key, value, href}], consumers/providers as {label: {key, value, href}} | {all_workloads: true} | {ip_list: {name, href}} | {label_group: {name…

Instructions

Get rulesets and their rules, from draft or active policy, rendered as data: scopes as [{key, value, href}], consumers/providers as {label: {key, value, href}} | {all_workloads: true} | {ip_list: {name, href}} | {label_group: {name, href}}, ingress_services as {port, proto} or {service: {name, href}}. Allow, deny and override_deny rules share one shape (rule_type). labels matches ruleset SCOPE; actor_labels returns only the rules that NAME those labels as consumer or provider, in any ruleset -- 'the policy that touches app X'. Each ruleset costs one extra request for its deny rules, so filter where you can.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoFilter rulesets by name (supports partial matches)
labelsNoScope filter: key=value or label HREFs, ANDed (['app=shop', 'env=prod'] = rulesets scoped to exactly that app). A pre-encoded JSON string is still accepted.
enabledNoFilter by enabled/disabled status
pversionNoPolicy version to read (default draft). Echoed as policy_version.
actor_sideNoWhich side actor_labels must appear on (default any)
descriptionNoFilter rulesets by description (supports partial matches)
max_resultsNoMaximum number of rulesets to return
actor_labelsNoReturn only rules whose consumers or providers reference ALL of these labels (key=value or HREF). Rulesets with no matching rule are omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.11.0
    • addedInput schema / properties / actor_labels
      Added value: +{
+  "description": "Return only rules whose consumers or providers reference ALL of these labels (key=value or HREF). Rulesets with no matching rule are omitted.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / actor_side
      Added value: +{
+  "description": "Which side actor_labels must appear on (default any)",
+  "enum": [
+    "consumer",
+    "provider",
+    "any"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / labels / description
      Previous value: -"JSON-encoded list of label URIs to filter by scope"New value: +"Scope filter: key=value or label HREFs, ANDed (['app=shop', 'env=prod'] = rulesets scoped to exactly that app). A pre-encoded JSON string is still accepted."
    • addedInput schema / properties / labels / items
      Added value: +{
+  "type": "string"
+}
    • changedInput schema / properties / labels / type
      Previous value: -"string"New value: +"array"
    • addedInput schema / properties / pversion
      Added value: +{
+  "description": "Policy version to read (default draft). Echoed as policy_version.",
+  "enum": [
+    "draft",
+    "active"
+  ],
+  "type": "string"
+}
  2. Changed5 schema fields changedv0.8.0
    • addedInput schema / properties / description
      Added value: +{
+  "description": "Filter rulesets by description (supports partial matches)",
+  "type": "string"
+}
    • changedInput schema / properties / enabled / description
      Previous value: -"Filter by enabled/disabled status (optional)"New value: +"Filter by enabled/disabled status"
    • addedInput schema / properties / labels
      Added value: +{
+  "description": "JSON-encoded list of label URIs to filter by scope",
+  "type": "string"
+}
    • addedInput schema / properties / max_results
      Added value: +{
+  "description": "Maximum number of rulesets to return",
+  "type": "integer"
+}
    • changedInput schema / properties / name / description
      Previous value: -"Filter rulesets by name (optional)"New value: +"Filter rulesets by name (supports partial matches)"
  3. Addedv1.0.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose useful traits: the default is draft, and each ruleset costs an extra request for deny rules, so filtering is advised — a real performance/cost hint. It omits auth/permission needs but covers the salient operational behavior.

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-loaded with the core purpose before diving into return shapes and filter semantics. It is dense and runs long, but each clause (return shape, labels vs actor_labels, cost warning) carries actionable information rather than filler.

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

Completeness4/5

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

With no output schema, the description correctly takes on the return-value burden, documenting scopes, consumers/providers, ingress_services, and rule shapes. Combined with the cost note and filter guidance, an agent has enough to call it correctly, though auth expectations are unstated.

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 baseline is 3, but the description adds genuine meaning by contrasting `labels` (scope match) against `actor_labels` (rules that name the labels), a subtle distinction reinforced with the 'touches app X' framing. This goes beyond restating the schema.

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

Purpose4/5

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

States a specific verb and resource ('Get rulesets and their rules') plus the scope ('from draft or active policy'), clearly distinguishing it from the create/update/delete-ruleset siblings. It doesn't explicitly name a sibling, but the read-only nature is unambiguous.

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 concrete selection guidance: `labels` matches ruleset scope while `actor_labels` targets rules naming those labels, framed as 'the policy that touches app X'. It also advises filtering because of the per-ruleset extra request. No explicit when-not, but the filter semantics are well-routed.

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