portkey-admin-mcp

create_workspace

Provision a workspace to isolate resources, API keys, and team members, with optional slug, rate limits, and usage limits.

Instructions

Create a workspace to isolate resources, API keys, and team members. If slug is omitted it is auto-generated from the name; returns the new workspace id, name, and slug.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Name of the workspace
`slug`	No	URL-friendly slug (auto-generated if not provided)
`users`	No	Existing user IDs to add
`metadata`	No	Custom metadata key-value pairs
`is_default`	No	Set as default workspace (1 = yes, 0 = no)
`description`	No	Description of the workspace
`rate_limits`	No	Initial workspace rate-limit settings
`usage_limits`	No	Initial workspace usage-limit settings

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 changedv0.12.2Oct 2, 2026

changedInput schema / properties / usage_limits / items / properties / next_usage_reset_at / anyOf

Previous value: -[
-  {
-    "format": "date-time",
-    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "format": "date-time",
+    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

Changed3 schema fields changedv0.11.5Sep 8, 2026

addedInput schema / properties / rate_limits

Added value: +{
+  "description": "Initial workspace rate-limit settings",
+  "items": {
+    "properties": {
+      "type": {
+        "description": "Whether the limit counts requests or tokens",
+        "enum": [
+          "requests",
+          "tokens"
+        ],
+        "type": "string"
+      },
+      "unit": {
+        "description": "Rate window: requests per day, hour, or minute",
+        "enum": [
+          "rpd",
+          "rph",
+          "rpm"
+        ],
+        "type": "string"
+      },
+      "value": {
+        "description": "Maximum count in the selected rate window",
+        "maximum": 9007199254740991,
+        "minimum": 0,
+        "type": "integer"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / usage_limits

Added value: +{
+  "description": "Initial workspace usage-limit settings",
+  "items": {
+    "properties": {
+      "alert_threshold": {
+        "description": "Percentage of the limit that triggers an alert",
+        "exclusiveMinimum": 0,
+        "type": "number"
+      },
+      "credit_limit": {
+        "description": "Maximum cost or token usage for the workspace",
+        "exclusiveMinimum": 0,
+        "type": "number"
+      },
+      "next_usage_reset_at": {
+        "anyOf": [
+          {
+            "format": "date-time",
+            "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Next reset timestamp in ISO 8601 format"
+      },
+      "periodic_reset": {
+        "anyOf": [
+          {
+            "enum": [
+              "monthly",
+              "weekly"
+            ],
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Built-in weekly or monthly reset cadence"
+      },
+      "periodic_reset_days": {
+        "anyOf": [
+          {
+            "maximum": 365,
+            "minimum": 1,
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Custom reset cadence in days, from 1 through 365"
+      },
+      "type": {
+        "description": "Whether the limit measures cost or tokens",
+        "enum": [
+          "cost",
+          "tokens"
+        ],
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / users

Added value: +{
+  "description": "Existing user IDs to add",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

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

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare it is a non-read-only, non-idempotent, open-world create, so the safety profile is covered. The description adds real value by disclosing the slug auto-generation fallback and stating the returned fields (id, name, slug), which helps the agent chain calls. It does not mention permission requirements or whether the operation can fail on duplicates.

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?

Two front-loaded sentences with no filler; the core action leads and the fallback behavior follows. Slight redundancy in restating return values that the output schema already covers.

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 create tool with 8 parameters including nested rate_limits and usage_limits objects, the description is thin on defaults and constraints, but the full-coverage schema and an output schema carry that load. Annotations plus the stated return fields make it sufficient to call correctly.

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%, including the slug auto-generation note, so the schema already documents parameters thoroughly. The description's restatement of the slug fallback and return fields adds only marginal meaning beyond the schema; baseline 3 applies.

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 ("Create a workspace") plus the functional intent ("isolate resources, API keys, and team members"), which tells an agent what the object is for. It does not explicitly contrast with siblings like update_workspace or create_scim_workspace_mapping, but the create verb 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 Guidelines2/5

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

There is no when-to-use guidance, no note about required permissions or account context, and no mention of an alternative tool for related operations. The only conditional (slug omitted) is a behavioral detail, not usage guidance.

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

Deploy Server