Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready OpenAI MCP server with 110 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across OpenAI — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your OpenAI MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every OpenAI tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every OpenAI call.
Tools Discovery →A OpenAI MCP server lets AI agents read and write OpenAI data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's OpenAI MCP server ships with 110 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
Every action from OpenAI's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
List all currently available models with their permissions and metadata.
Get detailed information about a specific model.
Create a response using the new Responses API (replaces Assistants).
Retrieve a response by its ID.
Delete a response by its ID.
Create a conversation.
Get a conversation.
Update a conversation.
Delete a conversation.
Create items in a conversation.
List all items for a conversation.
Get a single item from a conversation.
Delete an item from a conversation.
Create a new container.
Get a specific container by ID.
List all containers.
Delete a container.
Upload a file to a container.
List files in a container.
Get a specific file from a container.
Delete a file from a container.
Lists all of the users in the organization.
Retrieves a user by their identifier.
Deletes a user from the organization.
Create an invite for a user to the organization.
Returns a list of invites in the organization.
Retrieves an invite.
Delete an invite. If the invite has already been accepted, it cannot be deleted.
Creates a new group in the organization.
Lists all groups in the organization.
Updates a group's information.
Deletes a group from the organization.
Adds a user to a group.
Lists the users assigned to a group.
Removes a user from a group.
Creates a custom role for the organization.
Lists the roles configured for the organization.
Updates an existing organization role.
Deletes a custom role from the organization.
Create a new project in the organization.
Lists all of the projects in the organization.
Retrieves a project.
Adds a user to the project.
Returns a list of users in the project.
Retrieves a user in the project.
Deletes a user from the project.
Creates a new service account in the project.
Returns a list of service accounts in the project.
Retrieves a service account in the project.
Deletes a service account from the project.
Returns a list of API keys in the project.
Retrieves an API key in the project.
Deletes an API key from the project.
Grants a group access to a project.
Lists the groups that have access to a project.
Revokes a group's access to a project.
Create an admin API key for the organization.
Retrieve an admin API key by ID.
List all admin API keys for the organization.
Delete an admin API key.
Create a custom role for a project.
List all custom roles for a project.
Update a custom role for a project.
Delete a custom role from a project.
Create a new skill by uploading a ZIP file.
Get a skill by its ID. Requires Skills API beta access.
List all skills for the current project.
Update the default version pointer for a skill.
Delete a skill by its ID.
Create a new version of an existing skill.
List all versions of a skill.
Get a specific version of a skill.
Delete a specific version of a skill.
Transcribes audio into the input language.
Translates audio into English.
Generates audio from the input text.
Create a Realtime client secret with session configuration.
List input items for a specific response.
Download the actual content of a file from a container.
Lists the organization roles assigned to a group within the organization.
Returns the rate limits per model for a project.
Get usage statistics for audio speech generation.
Get usage statistics for audio transcription.
Get usage statistics for code interpreter sessions.
Get usage statistics for completions.
Get usage statistics for embeddings.
Get usage statistics for image generation.
Get usage statistics for content moderation.
Get usage statistics for vector stores.
Get organization costs for audit logging.
List audit log events for the organization.
List all roles assigned to a group in a project.
List all roles assigned to a user in a project.
Download a skill zip bundle by its ID.
Download a specific version of a skill as a ZIP bundle.
Delete a fine-tuned model. You must have the Owner role.
Get input token counts for a request.
Cancel a model response with the given ID.
Compact a conversation.
Modifies a user's role in the organization.
Assigns an organization role to a group within the organization.
Unassigns an organization role from a group within the organization.
Modifies a project in the organization.
Archives a project in the organization.
Modifies a user's role in the project.
Updates a project rate limit.
Assign a role to a group in a project.
Remove a role from a group in a project.
Assign a role to a user in a project.
Remove a role from a user in a project.
One endpoint. Any framework. Your agent is talking to OpenAI in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.