TokenLab MCP Server

Create response (OpenAI Responses API)

create_response

Creates a response using the OpenAI Responses API format. Supports models, input, tools, instructions, and streaming options.

Instructions

Create response (OpenAI Responses API) Creates a response using the native OpenAI Responses API shape. The model details must advertise the Responses request format and a same-protocol route must be currently available; model names and providers do not imply availability. Unknown request fields are forwarded on a best-effort basis and remain subject to the selected provider's support.

Input Schema

TableJSON Schema

Name	Required	Description
`text`	No	Text formatting options.
`input`	No	Input content as a string or structured item array.
`model`	Yes	Model to use
`store`	No	Whether the response is stored for later retrieval.
`tools`	No	Tools available to the model. Tool types and combinations are validated by the selected service.
`top_p`	No	Nucleus sampling probability.
`prompt`	No	Reference to a reusable prompt template and variables.
`include`	No	Additional response sections to include when supported.
`metadata`	No	Request metadata.
`reasoning`	No	Reasoning configuration.
`background`	No	Whether to run the response asynchronously.
`truncation`	No	Truncation strategy for long conversations.
`temperature`	No
`tool_choice`	No	Tool choice policy or explicit tool selection.
`instructions`	No	System instructions
`service_tier`	No	Service tier hint for compatible providers.
`stream_options`	No	Responses streaming options.
`max_output_tokens`	No	Maximum output tokens
`parallel_tool_calls`	No	Whether the model may issue parallel tool calls.
`previous_response_id`	No	ID of a previous response to continue.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed28 schema fields changedv0.6.4Jul 25, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

addedInput schema / properties / background

Added value: +{
+  "description": "Whether to run the response asynchronously.",
+  "type": "boolean"
+}

changedInput schema / properties / input / oneOf

Previous value: -[
-  {
-    "description": "Single string input.",
-    "type": "string"
-  },
-  {
-    "description": "Structured input items for the conversation.",
-    "items": {},
-    "type": "array"
-  }
-]New value: +[
+  {
+    "description": "Single string input.",
+    "type": "string"
+  },
+  {
+    "description": "Structured input items for the conversation.",
+    "type": "array"
+  }
+]

removedInput schema / properties / max_output_tokens / maximum
```
Removed value: -9007199254740991
```
removedInput schema / properties / max_output_tokens / minimum
```
Removed value: --9007199254740991
```
changedInput schema / properties / metadata / additionalProperties
```
Previous value: -{}New value: +true
```
removedInput schema / properties / metadata / properties
```
Removed value: -{}
```

addedInput schema / properties / previous_response_id

Added value: +{
+  "description": "ID of a previous response to continue.",
+  "type": "string"
+}

addedInput schema / properties / prompt

Added value: +{
+  "additionalProperties": true,
+  "description": "Reference to a reusable prompt template and variables.",
+  "type": "object"
+}

addedInput schema / properties / reasoning

Added value: +{
+  "additionalProperties": true,
+  "description": "Reasoning configuration.",
+  "type": "object"
+}

removedInput schema / properties / reasoning_effort

Removed value: -{
-  "description": "Reasoning effort hint for compatible models.",
-  "type": "string"
-}

removedInput schema / properties / seed

Removed value: -{
-  "description": "Seed for deterministic-compatible providers.",
-  "maximum": 9007199254740991,
-  "minimum": -9007199254740991,
-  "type": "integer"
-}

removedInput schema / properties / service_tier / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / service_tier / type
```
Added value: +[
+  "string",
+  "null"
+]
```

addedInput schema / properties / store

Added value: +{
+  "description": "Whether the response is stored for later retrieval.",
+  "type": "boolean"
+}

removedInput schema / properties / stream

Removed value: -{
-  "const": false,
-  "description": "MCP tool calls return one final result; omit stream or set it to false.",
-  "type": "boolean"
-}

changedInput schema / properties / stream_options / additionalProperties
```
Previous value: -falseNew value: +true
```
changedInput schema / properties / text / additionalProperties
```
Previous value: -{}New value: +true
```
removedInput schema / properties / text / properties
```
Removed value: -{}
```

changedInput schema / properties / tool_choice / oneOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "additionalProperties": {},
-    "properties": {},
-    "type": "object"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "additionalProperties": true,
+    "type": "object"
+  }
+]

changedInput schema / properties / tools / description

Previous value: -"Tools available to the model. For hosted image_generation tools that use the default image tool model or explicitly set model: gpt-image-2, TokenLab removes unsupported input_fidelity before forwarding because GPT Image 2 already treats image inputs as high fidelity. Do not send background: transparent for that tool; TokenLab does not silently remove it because that changes output semantics."New value: +"Tools available to the model. Tool types and combinations are validated by the selected service."

changedInput schema / properties / tools / items / additionalProperties
```
Previous value: -{}New value: +true
```
removedInput schema / properties / tools / items / properties
```
Removed value: -{}
```

addedInput schema / properties / top_p

Added value: +{
+  "description": "Nucleus sampling probability.",
+  "type": "number"
+}

addedInput schema / properties / truncation

Added value: +{
+  "description": "Truncation strategy for long conversations.",
+  "type": "string"
+}

removedInput schema / properties / truncation_strategy

Removed value: -{
-  "description": "Truncation strategy for long conversations when supported.",
-  "type": "string"
-}

removedInput schema / properties / user

Removed value: -{
-  "description": "End-user identifier.",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "model",
-  "input"
-]New value: +[
+  "model"
+]

Changed23 schema fields changedv0.3.1Jul 10, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / include / description

Previous value: -"Additional response sections to include."New value: +"Additional response sections to include when supported."

removedInput schema / properties / input / anyOf

Removed value: -[
-  {
-    "minLength": 1,
-    "type": "string"
-  },
-  {
-    "items": {
-      "additionalProperties": {},
-      "properties": {},
-      "type": "object"
-    },
-    "minItems": 1,
-    "type": "array"
-  }
-]

changedInput schema / properties / input / description

Previous value: -"Responses API input as text or native structured input items."New value: +"Input content as a string or structured item array."

addedInput schema / properties / input / oneOf

Added value: +[
+  {
+    "description": "Single string input.",
+    "type": "string"
+  },
+  {
+    "description": "Structured input items for the conversation.",
+    "items": {},
+    "type": "array"
+  }
+]

changedInput schema / properties / instructions / description

Previous value: -"Optional system/developer instructions."New value: +"System instructions"

changedInput schema / properties / max_output_tokens / description

Previous value: -"Optional output token cap."New value: +"Maximum output tokens"

changedInput schema / properties / max_output_tokens / minimum
```
Previous value: -1New value: +-9007199254740991
```

changedInput schema / properties / metadata / description

Previous value: -"Optional request metadata."New value: +"Request metadata."

changedInput schema / properties / model / description

Previous value: -"Public TokenLab model ID."New value: +"Model to use"

removedInput schema / properties / model / minLength
```
Removed value: -1
```

changedInput schema / properties / reasoning_effort / description

Previous value: -"Reasoning-effort hint for compatible models."New value: +"Reasoning effort hint for compatible models."

changedInput schema / properties / seed / description

Previous value: -"Optional deterministic seed."New value: +"Seed for deterministic-compatible providers."

changedInput schema / properties / service_tier / description

Previous value: -"Optional service-tier hint."New value: +"Service tier hint for compatible providers."

addedInput schema / properties / stream

Added value: +{
+  "const": false,
+  "description": "MCP tool calls return one final result; omit stream or set it to false.",
+  "type": "boolean"
+}

addedInput schema / properties / stream_options

Added value: +{
+  "additionalProperties": false,
+  "description": "Responses streaming options.",
+  "properties": {
+    "include_obfuscation": {
+      "description": "When true, request obfuscated tokens in Responses stream events from compatible upstreams.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

removedInput schema / properties / temperature / description
```
Removed value: -"Optional sampling temperature."
```

changedInput schema / properties / text / description

Previous value: -"Optional native text formatting configuration."New value: +"Text formatting options."

removedInput schema / properties / tool_choice / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "additionalProperties": {},
-    "properties": {},
-    "type": "object"
-  }
-]

addedInput schema / properties / tool_choice / oneOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "additionalProperties": {},
+    "properties": {},
+    "type": "object"
+  }
+]

changedInput schema / properties / tools / description

Previous value: -"Native Responses API tool definitions."New value: +"Tools available to the model. For hosted image_generation tools that use the default image tool model or explicitly set model: gpt-image-2, TokenLab removes unsupported input_fidelity before forwarding because GPT Image 2 already treats image inputs as high fidelity. Do not send background: transparent for that tool; TokenLab does not silently remove it because that changes output semantics."

changedInput schema / properties / truncation_strategy / description

Previous value: -"Optional truncation strategy."New value: +"Truncation strategy for long conversations when supported."

changedInput schema / properties / user / description

Previous value: -"Optional end-user identifier."New value: +"End-user identifier."

Changed17 schema fields changedv0.3.0Jul 10, 2026

addedInput schema / properties / include

Added value: +{
+  "description": "Additional response sections to include.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / input / anyOf

Added value: +[
+  {
+    "minLength": 1,
+    "type": "string"
+  },
+  {
+    "items": {
+      "additionalProperties": {},
+      "properties": {},
+      "type": "object"
+    },
+    "minItems": 1,
+    "type": "array"
+  }
+]

changedInput schema / properties / input / description

Previous value: -"Responses API input text."New value: +"Responses API input as text or native structured input items."

removedInput schema / properties / input / minLength
```
Removed value: -1
```
removedInput schema / properties / input / type
```
Removed value: -"string"
```
changedInput schema / properties / max_output_tokens / maximum
```
Previous value: -8192New value: +9007199254740991
```

addedInput schema / properties / metadata

Added value: +{
+  "additionalProperties": {},
+  "description": "Optional request metadata.",
+  "properties": {},
+  "type": "object"
+}

addedInput schema / properties / parallel_tool_calls

Added value: +{
+  "description": "Whether the model may issue parallel tool calls.",
+  "type": "boolean"
+}

addedInput schema / properties / reasoning_effort

Added value: +{
+  "description": "Reasoning-effort hint for compatible models.",
+  "type": "string"
+}

addedInput schema / properties / seed

Added value: +{
+  "description": "Optional deterministic seed.",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}

addedInput schema / properties / service_tier

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Optional service-tier hint."
+}

addedInput schema / properties / temperature

Added value: +{
+  "description": "Optional sampling temperature.",
+  "type": "number"
+}

addedInput schema / properties / text

Added value: +{
+  "additionalProperties": {},
+  "description": "Optional native text formatting configuration.",
+  "properties": {},
+  "type": "object"
+}

addedInput schema / properties / tool_choice

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "additionalProperties": {},
+      "properties": {},
+      "type": "object"
+    }
+  ],
+  "description": "Tool choice policy or explicit tool selection."
+}

addedInput schema / properties / tools

Added value: +{
+  "description": "Native Responses API tool definitions.",
+  "items": {
+    "additionalProperties": {},
+    "properties": {},
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / truncation_strategy

Added value: +{
+  "description": "Optional truncation strategy.",
+  "type": "string"
+}

addedInput schema / properties / user

Added value: +{
+  "description": "Optional end-user identifier.",
+  "type": "string"
+}

First observedv0.2.0Jul 9, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already indicate non-read-only, open-world, non-idempotent, non-destructive. Description adds context about unknown field forwarding and model availability, but no additional behavioral traits like cost or rate limits.

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

Conciseness3/5

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

Two dense sentences with redundant title repetition. Information is valuable but could be more structured and concise.

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?

Given high schema coverage and annotations, description covers key behavioral aspects. Lacks overview of typical use cases vs. siblings, but sufficient for tool understanding.

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 95%, so baseline 3 applies. Description does not add parameter-level information beyond what the schema provides.

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 clearly states it creates a response using the OpenAI Responses API, distinguishing it from siblings like create_chat_completion by specifying the required model advertisement and route availability.

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 conditions for use (model must advertise Responses format, same-protocol route available) and describes best-effort forwarding of unknown fields, but does not explicitly state when not to use or name alternatives.

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

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hedging8563/tokenlab-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server