← chatgpt-webui-mcp

chatgpt-webui-mcp 0.1.5

npm · chatgpt-webui-mcp · current release

9
Tools
0
Resources
0
Templates
0
Prompts

Observation

Observed 2026-08-22T10:08:26.686Z using mcpSecurity-inventory. Status: succeeded. Negotiated protocol: 2025-06-18.

Server capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools 9

ToolCategoryAnnotationsRisk
chatgpt_webui_askSend a prompt to ChatGPT WebUI using session token auth and return assistant text.
Input schema
{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Prompt to send."
    },
    "model": {
      "type": "string",
      "description": "Model slug override. Examples: gpt-5-2, gpt-5-2-pro, gpt-5-1-instant, research. Ignored when deep_research=true."
    },
    "model_mode": {
      "type": "string",
      "enum": [
        "auto",
        "instant",
        "thinking",
        "pro"
      ],
      "description": "Quick model mode selector that maps to GPT-5.2 variants."
    },
    "reasoning_effort": {
      "type": "string",
      "enum": [
        "none",
        "standard",
        "extended"
      ],
      "description": "UI reasoning control. Mainly relevant for thinking-capable models."
    },
    "deep_research": {
      "type": "boolean",
      "description": "Enable Deep Research flow. When true, model selection switches to research mode."
    },
    "deep_research_site_mode": {
      "type": "string",
      "enum": [
        "search_web",
        "specific_sites"
      ],
      "description": "Optional Deep Research sites mode override."
    },
    "create_image": {
      "type": "boolean",
      "description": "Enable image-generation mode in ChatGPT UI."
    },
    "wait_timeout_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Max wait for response completion in milliseconds (supports long GPT-5.2 Pro runs)."
    },
    "workspace": {
      "type": "string",
      "description": "Preferred workspace label if ChatGPT shows workspace selection (e.g. PRO, Personal)."
    },
    "conversation_id": {
      "type": "string",
      "description": "Optional conversation id to continue an existing chat."
    },
    "parent_message_id": {
      "type": "string",
      "description": "Optional parent message id for continued conversation state."
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
—— · ——
chatgpt_webui_ask_async_resultGet result for a background ask job. Optionally wait for completion by providing wait_timeout_ms.
Input schema
{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "description": "Job id returned by chatgpt_webui_ask_async_start."
    },
    "wait_timeout_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Optional max wait for completion before returning current state."
    },
    "poll_interval_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Polling interval while waiting. Default: 2000ms."
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
—— · ——
chatgpt_webui_ask_async_startStart a background ChatGPT ask job and return immediately with a job id. Use this for long-running tasks like Deep Research and Pro runs.
Input schema
{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Prompt to send."
    },
    "model": {
      "type": "string",
      "description": "Model slug override. Examples: gpt-5-2, gpt-5-2-pro, gpt-5-1-instant, research. Ignored when deep_research=true."
    },
    "model_mode": {
      "type": "string",
      "enum": [
        "auto",
        "instant",
        "thinking",
        "pro"
      ],
      "description": "Quick model mode selector that maps to GPT-5.2 variants."
    },
    "reasoning_effort": {
      "type": "string",
      "enum": [
        "none",
        "standard",
        "extended"
      ],
      "description": "UI reasoning control. Mainly relevant for thinking-capable models."
    },
    "deep_research": {
      "type": "boolean",
      "description": "Enable Deep Research flow. When true, model selection switches to research mode."
    },
    "deep_research_site_mode": {
      "type": "string",
      "enum": [
        "search_web",
        "specific_sites"
      ],
      "description": "Optional Deep Research sites mode override."
    },
    "create_image": {
      "type": "boolean",
      "description": "Enable image-generation mode in ChatGPT UI."
    },
    "wait_timeout_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Max wait for response completion in milliseconds (supports long GPT-5.2 Pro runs)."
    },
    "workspace": {
      "type": "string",
      "description": "Preferred workspace label if ChatGPT shows workspace selection (e.g. PRO, Personal)."
    },
    "conversation_id": {
      "type": "string",
      "description": "Optional conversation id to continue an existing chat."
    },
    "parent_message_id": {
      "type": "string",
      "description": "Optional parent message id for continued conversation state."
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
—— · ——
chatgpt_webui_ask_async_statusGet status for a background ask job.
Input schema
{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "description": "Job id returned by chatgpt_webui_ask_async_start."
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
—— · ——
chatgpt_webui_commandNatural-language command wrapper. Converts phrases like 'with chatgpt webui on gpt 5.2 pro extended thinking: ...' into a chatgpt_webui_prompt call.
Input schema
{
  "type": "object",
  "properties": {
    "command": {
      "type": "string",
      "description": "Natural language command string."
    },
    "mode": {
      "type": "string",
      "enum": [
        "auto",
        "wait",
        "background"
      ],
      "description": "Optional override. If omitted, inferred from command and defaults."
    },
    "wait_for_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Optional wait window for background mode before returning running state."
    },
    "poll_interval_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Polling interval when wait_for_ms is set. Default 2000ms."
    }
  },
  "required": [
    "command"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
—— · ——
chatgpt_webui_modelsList available ChatGPT WebUI models for the current account.
Input schema
{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "type": "object",
  "properties": {}
}
—— · ——
chatgpt_webui_promptUnified prompt entrypoint. mode=auto uses background runs for long tasks (Deep Research, Pro/Thinking, image generation) and direct wait for short tasks.
Input schema
{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Prompt to send."
    },
    "model": {
      "type": "string",
      "description": "Model slug override. Examples: gpt-5-2, gpt-5-2-pro, gpt-5-1-instant, research. Ignored when deep_research=true."
    },
    "model_mode": {
      "type": "string",
      "enum": [
        "auto",
        "instant",
        "thinking",
        "pro"
      ],
      "description": "Quick model mode selector that maps to GPT-5.2 variants."
    },
    "reasoning_effort": {
      "type": "string",
      "enum": [
        "none",
        "standard",
        "extended"
      ],
      "description": "UI reasoning control. Mainly relevant for thinking-capable models."
    },
    "deep_research": {
      "type": "boolean",
      "description": "Enable Deep Research flow. When true, model selection switches to research mode."
    },
    "deep_research_site_mode": {
      "type": "string",
      "enum": [
        "search_web",
        "specific_sites"
      ],
      "description": "Optional Deep Research sites mode override."
    },
    "create_image": {
      "type": "boolean",
      "description": "Enable image-generation mode in ChatGPT UI."
    },
    "wait_timeout_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Max wait for response completion in milliseconds (supports long GPT-5.2 Pro runs)."
    },
    "workspace": {
      "type": "string",
      "description": "Preferred workspace label if ChatGPT shows workspace selection (e.g. PRO, Personal)."
    },
    "conversation_id": {
      "type": "string",
      "description": "Optional conversation id to continue an existing chat."
    },
    "parent_message_id": {
      "type": "string",
      "description": "Optional parent message id for continued conversation state."
    },
    "mode": {
      "type": "string",
      "enum": [
        "auto",
        "wait",
        "background"
      ],
      "description": "Execution mode. auto chooses best mode. wait blocks for result. background returns run_id."
    },
    "wait_for_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Optional extra wait window for background mode before returning running state."
    },
    "poll_interval_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Polling interval when wait_for_ms is set. Default 2000ms."
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
—— · ——
chatgpt_webui_runUnified run checker. Use run_id from chatgpt_webui_prompt background mode (or job_id from legacy async tools).
Input schema
{
  "type": "object",
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run id from chatgpt_webui_prompt."
    },
    "job_id": {
      "type": "string",
      "description": "Legacy alias for run_id."
    },
    "wait_timeout_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Optional max wait for completion before returning running state."
    },
    "poll_interval_ms": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Polling interval while waiting. Default: 2000ms."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
—— · ——
chatgpt_webui_sessionValidate ChatGPT session token and return session details.
Input schema
{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "type": "object",
  "properties": {}
}
—— · ——

Resources 0

Resource templates 0

Prompts 0

Let’s talk about MCP security.

Share your details and our security team will contact you.