portkey-admin-mcp

create_integration

Create an AI-provider integration to serve as the source for workspace providers. Configure backend, keys, and pricing to manage provider access.

Instructions

Create an AI-provider integration that becomes the source for workspace providers. ai_provider_id identifies the backend; provider-specific fields configure Azure, Bedrock, Vertex, or custom hosts. For workspace-scoped integrations, create_default_provider controls automatic provider creation. key is write-only, but secret_mappings can resolve it or configuration fields from Secret References at runtime. pricing_adjustments apply negotiated discounts or markups to cost accounting; tags attach key-value labels that list_integrations can filter on. Use update_integration_models and update_integration_workspaces after creation; returns the new integration id and slug.

Input Schema

TableJSON Schema

Name	Required	Description
`key`	No	API key for the provider (if required)
`name`	Yes	Human-readable name for the integration
`slug`	No	URL-friendly identifier (auto-generated from name if not provided)
`tags`	No	Integration tags, or null to create without tags
`aws_region`	No	AWS region (for AWS Bedrock)
`api_version`	No	API version (for Azure OpenAI)
`custom_host`	No	Custom base URL for the provider
`description`	No	Optional description of the integration
`workspace_id`	No	Workspace ID for workspace-scoped integrations
`resource_name`	No	Resource name (for Azure OpenAI)
`vertex_region`	No	GCP region (for Vertex AI)
`ai_provider_id`	Yes	ID of the AI provider (e.g., 'openai', 'anthropic', 'azure-openai', 'aws-bedrock', 'vertex-ai')
`deployment_name`	No	Deployment name (for Azure OpenAI)
`secret_mappings`	No	Unique runtime Secret Reference mappings; mapping key allows the key field to be omitted
`aws_access_key_id`	No	AWS access key ID (for AWS Bedrock)
`vertex_project_id`	No	GCP project ID (for Vertex AI)
`pricing_adjustments`	No	Negotiated discount or markup multipliers for cost accounting
`aws_secret_access_key`	No	AWS secret access key (for AWS Bedrock)
`default_provider_slug`	No	Custom slug for the automatically created workspace provider
`create_default_provider`	No	Create a provider automatically for a workspace-scoped integration; defaults to true

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	Whether the tool call succeeded and returned structured data
`data`	No	Structured success payload when ok is true
`error`	No	Structured error payload when ok is false

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.13.0Oct 3, 2026

addedInput schema / properties / tags

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Integration tags, or null to create without tags"
+}

Changed2 schema fields changedv0.12.2Oct 2, 2026
- removedInput schema / properties / secret_mappings / items / properties / secret_key / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedInput schema / properties / secret_mappings / items / properties / secret_key / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changed4 schema fields changedAug 9, 2026

addedInput schema / properties / create_default_provider

Added value: +{
+  "description": "Create a provider automatically for a workspace-scoped integration; defaults to true",
+  "type": "boolean"
+}

addedInput schema / properties / default_provider_slug

Added value: +{
+  "description": "Custom slug for the automatically created workspace provider",
+  "maxLength": 255,
+  "pattern": "^[a-zA-Z0-9_-]+$",
+  "type": "string"
+}

addedInput schema / properties / pricing_adjustments

Added value: +{
+  "anyOf": [
+    {
+      "properties": {
+        "multiplier": {
+          "description": "Per-unit multipliers applied over Portkey catalog pricing",
+          "properties": {
+            "additional_units": {
+              "anyOf": [
+                {
+                  "additionalProperties": {
+                    "anyOf": [
+                      {
+                        "minimum": 0,
+                        "type": "number"
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  },
+                  "propertyNames": {
+                    "type": "string"
+                  },
+                  "type": "object"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Multipliers keyed by Portkey pricing unit, such as web_search or file_search"
+            },
+            "cache_read_audio_input_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Cache-read audio input token price multiplier"
+            },
+            "cache_read_image_input_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Cache-read image input token price multiplier"
+            },
+            "cache_read_input_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Cache-read input token price multiplier"
+            },
+            "cache_read_text_input_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Cache-read text input token price multiplier"
+            },
+            "cache_write_image_input_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Cache-write image input token price multiplier"
+            },
+            "cache_write_input_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Cache-write input token price multiplier"
+            },
+            "cache_write_text_input_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Cache-write text input token price multiplier"
+            },
+            "default": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Fallback multiplier for pricing units; 1 is unchanged, 0.8 is a 20% discount"
+            },
+            "image": {
+              "anyOf": [
+                {
+                  "properties": {
+                    "default": {
+                      "anyOf": [
+                        {
+                          "minimum": 0,
+                          "type": "number"
+                        },
+                        {
+                          "type": "null"
+                        }
+                      ],
+                      "description": "Default image-generation price multiplier"
+                    }
+                  },
+                  "type": "object"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Image-generation pricing multipliers"
+            },
+            "prediction_accepted_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Accepted predicted-output token price multiplier"
+            },
+            "prediction_rejected_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Rejected predicted-output token price multiplier"
+            },
+            "reasoning_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Reasoning token price multiplier"
+            },
+            "request_audio_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Audio input token price multiplier"
+            },
+            "request_image_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Image input token price multiplier"
+            },
+            "request_text_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Text input token price multiplier"
+            },
+            "request_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Input token price multiplier"
+            },
+            "response_audio_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Audio output token price multiplier"
+            },
+            "response_image_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Image output token price multiplier"
+            },
+            "response_text_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Text output token price multiplier"
+            },
+            "response_token": {
+              "anyOf": [
+                {
+                  "minimum": 0,
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Output token price multiplier"
+            }
+          },
+          "type": "object"
+        }
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Negotiated discount or markup multipliers for cost accounting"
+}

addedInput schema / properties / secret_mappings

Added value: +{
+  "description": "Unique runtime Secret Reference mappings; mapping key allows the key field to be omitted",
+  "items": {
+    "properties": {
+      "secret_key": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Optional key to select from a multi-value secret"
+      },
+      "secret_reference_id": {
+        "description": "Secret Reference UUID or slug accessible to the workspace",
+        "type": "string"
+      },
+      "target_field": {
+        "description": "Integration field populated at runtime: key or configurations.<field>",
+        "type": "string"
+      },
+      "value_format": {
+        "anyOf": [
+          {
+            "enum": [
+              "string",
+              "json"
+            ],
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Treat the resolved value as a plain string or parsed JSON"
+      }
+    },
+    "required": [
+      "target_field",
+      "secret_reference_id"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Addedv1.0.1May 7, 2026
RemovedMay 1, 2026
First observedJan 1, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations cover the safety profile (not read-only, not idempotent, not destructive), and the description adds meaningful context beyond them: key is write-only, secret_mappings resolve the key or config fields at runtime, and the call returns the new id and slug. It doesn't mention failure modes, permission requirements, or rate limits, but the added disclosure is substantive.

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?

Dense but well front-loaded, leading with the core action and role before describing parameters and follow-ups. Every sentence carries information, though the paragraph is heavy enough that a reader must work to separate creation semantics from workflow advice.

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?

For a 20-parameter creation tool with an output schema, the description covers the essential semantics plus post-creation steps and return values, so an agent has enough to invoke it correctly. Minor gaps around provider-specific field combinations (e.g., which fields are required per ai_provider_id) leave a little room.

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 semantics: what ai_provider_id selects, which fields are provider-specific (Azure/Bedrock/Vertex/custom hosts), the write-only nature of key, and the discount/markup effect of pricing_adjustments. This goes beyond restating schema text.

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?

States a specific verb and resource ('Create an AI-provider integration') and clarifies its role as the source for workspace providers, which distinguishes it from sibling create_provider and create_mcp_integration. An agent can identify the artifact being created without opening the schema.

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?

Provides clear downstream workflow guidance ('Use update_integration_models and update_integration_workspaces after creation') and notes that tags feed list_integrations filtering. It lacks an explicit when-not or a direct contrast against create_provider/create_mcp_integration, so it stops short of full routing guidance.

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

Deploy Server