OpenAI MCP server for AI agents
Generate text, embeddings and images, and moderate content with the OpenAI API.
- Auth
- Access token
- Tools
- 6
- Triggers
- 0
- Category
- AI
Tools and triggers
Generate a response
OPENAI_CREATE_RESPONSE
Runs a model on a prompt and returns its answer text in `output_text`, plus the full response object. Costs tokens.
Create a chat completion
OPENAI_CREATE_CHAT_COMPLETION
Sends a list of chat messages to a model and returns its reply in choices[0].message.content. Costs tokens.
List models
OPENAI_LIST_MODELS
Lists the models the API key can use, with their ids.read-only
Create embeddings
OPENAI_CREATE_EMBEDDING
Turns text into embedding vectors for search and similarity. Input is one string or an array of strings.
Generate an image
OPENAI_CREATE_IMAGE
Generates an image from a text prompt. The result is base64-encoded image data in data[0].b64_json, which is large.
Check text for policy violations
OPENAI_CREATE_MODERATION
Classifies text for harassment, hate, self-harm, sexual content, violence and similar categories. Free to use.read-only
Connect via MCP
Create an MCP server for OpenAI in the dashboard, then add its URL to your client. This is the Claude Code command; the client guide has the others.
claude mcp add --transport http openai \
"https://www.prompt-tm.com/mcp/<server id>?user_id=<your user>" \
--header "x-api-key: ptm_…"Connect via REST
Run a tool with one request. The response is { data, error, successful, log_id } for every tool.
curl -X POST https://www.prompt-tm.com/api/v3/tools/execute/OPENAI_CREATE_RESPONSE \
-H "x-api-key: $PROMPT_TM_KEY" -H "content-type: application/json" \
-d '{ "user_id": "alice", "arguments": {} }'
