Polarion MCP Server

getLlms

Read-only

Retrieve configured Large Language Models on Polarion to verify AI availability and select a valid model for generation. Paginated; empty result signals no LLM configured.

Instructions

Returns the Large Language Models configured on this Polarion server for its built-in AI features (ID and name), paginated. Call it before generateCompletion to pick a valid model; an empty list means no LLM is configured and AI actions will fail.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`page_size_`	No	Maximum number of items to return in this page (e.g. `100`). Use together with `page[number]` to paginate through a large result set.
`page_number_`	No	1-based page number to fetch when the result set is paginated (e.g. `2` for the second page). Combine with `page[size]`; omit to fetch the first page.

Output Schema

TableJSON Schema

Name	Required	Description
`data`	No
`meta`	No
`included`	No	Related entities might be returned, see <a href="https://docs.sw.siemens.com/en-US/doc/230235217/PL20250606201928474.polarion_help_sc.xid2134849/xid2134871" target="_blank">REST API User Guide</a>.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.2.0Sep 17, 2026

changedInput schema / properties / page_number_ / description

Previous value: -"Specify the page number to be returned. Counting starts from 1. See <a href=\"https://docs.sw.siemens.com/en-US/doc/230235217/PL20250606201928474.polarion_help_sc.xid2134849/xid2134871\" target=\"_blank\">REST API User Guide</a> for details."New value: +"1-based page number to fetch when the result set is paginated (e.g. `2` for the second page). Combine with `page[size]`; omit to fetch the first page."

changedInput schema / properties / page_size_ / description

Previous value: -"Limit the number of entities returned in a single response. See <a href=\"https://docs.sw.siemens.com/en-US/doc/230235217/PL20250606201928474.polarion_help_sc.xid2134849/xid2134871\" target=\"_blank\">REST API User Guide</a> for details."New value: +"Maximum number of items to return in this page (e.g. `100`). Use together with `page[number]` to paginate through a large result set."

Changed1 schema field changedv1.1.0Sep 11, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "data": {
+      "items": {
+        "properties": {
+          "attributes": {
+            "properties": {
+              "name": {
+                "example": "myLlm",
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "id": {
+            "example": "myLlm",
+            "type": "string"
+          },
+          "links": {
+            "type": "object"
+          },
+          "meta": {
+            "properties": {
+              "errors": {
+                "items": {
+                  "properties": {
+                    "detail": {
+                      "description": "Human-readable explanation specific to this occurrence of the problem.",
+                      "example": "Unexpected token, BEGIN_ARRAY expected, but was : BEGIN_OBJECT (at $.data)",
+                      "type": "string"
+                    },
+                    "source": {
+                      "properties": {
+                        "parameter": {
+                          "description": "String indicating which URI query parameter caused the error.",
+                          "example": "revision",
+                          "type": "string"
+                        },
+                        "pointer": {
+                          "description": "JSON Pointer to the associated entity in the request document.",
+                          "example": "$.data",
+                          "type": "string"
+                        },
+                        "resource": {
+                          "description": "Resource causing the error.",
+                          "properties": {
+                            "id": {
+                              "example": "MyProjectId/id",
+                              "type": "string"
+                            },
+                            "type": {
+                              "example": "type",
+                              "type": "string"
+                            }
+                          },
+                          "type": "object"
+                        }
+                      },
+                      "type": "object"
+                    },
+                    "status": {
+                      "description": "HTTP status code applicable to this problem.",
+                      "example": "400",
+                      "type": "string"
+                    },
+                    "title": {
+                      "description": "Short, human-readable summary of the problem.",
+                      "example": "Bad Request",
+                      "type": "string"
+                    }
+                  },
+                  "type": "object"
+                },
+                "type": "array"
+              }
+            },
+            "type": "object"
+          },
+          "type": {
+            "enum": [
+              "llms"
+            ],
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "included": {
+      "description": "Related entities might be returned, see <a href=\"https://docs.sw.siemens.com/en-US/doc/230235217/PL20250606201928474.polarion_help_sc.xid2134849/xid2134871\" target=\"_blank\">REST API User Guide</a>.",
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "meta": {
+      "properties": {
+        "totalCount": {
+          "format": "int32",
+          "type": "integer"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

AddedSep 7, 2026

TDQS

A4.5/5.0

Behavior4/5

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

The readOnlyHint annotation already covers the safety profile, and the description adds meaningful context beyond that: the tool is paginated, returns only configured models, and an empty result signals that AI features are unavailable. This goes beyond a bare 'list models' statement while not over-describing.

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 two concise sentences with no filler. The core purpose is front-loaded, and the usage guidance is delivered immediately after, each sentence earning its place.

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 simple read-only list operation with no required parameters, an output schema present, and readOnlyHint/openWorldHint annotations, the description is complete. It covers what is returned, how results are paginated, and what an empty result means for downstream AI actions.

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

Parameters3/5

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

Schema description coverage is 100%, so the parameters `page_size_` and `page_number_` are already fully documented. The description only mentions pagination generically and adds no new parameter-level meaning, so a baseline score of 3 is appropriate.

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 ('Returns'), a specific resource (Large Language Models configured on this Polarion server), and the exact output fields (ID and name). It also distinguishes itself from the related sibling `generateCompletion` by positioning itself as the prerequisite lookup, so an agent can tell what it does and what it is not.

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

Usage Guidelines5/5

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

The description explicitly tells the agent when to use this tool: before `generateCompletion`, to pick a valid model. It also explains the consequence of an empty list (no LLM configured and AI actions will fail), which gives clear decision-making context even without naming an alternative tool.

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

Deploy Server