Connect
Optimize
Secure
Mintlify MCP Server
for AI Agents
Production-ready Mintlify MCP server with extensible actions — plus built-in authentication, security, and optimized execution.
Mintlify MCP Server
Built by 
StackOne
StackOne 
Coverage
14 Agent Actions
Create, read, update, and delete across Mintlify — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Mintlify MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Mintlify tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Mintlify call.
Tools Discovery →What is the Mintlify MCP Server?
A Mintlify MCP server lets AI agents read and write Mintlify data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Mintlify MCP server ships with 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.
All Mintlify MCP Tools and Actions
Every action from Mintlify's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Trigger Deployments
- Trigger Deployment
Trigger a documentation deployment to publish updates from your configured branch
Deployment Status
- Get Deployment Status
Get the status of a deployment update by its status ID
Agent Jobs
- Create Agent Job
Initiates an AI-powered background job to automatically generate documentation updates and create pull requests with the changes
- Get Agent Job
Retrieves the current status, progress, and details of a specific agent job by its unique identifier for monitoring documentation generation
Agent Follow-up Messages
- Send Agent Follow-up Message
Sends additional instructions or refinements to an active agent job to iteratively improve documentation output without creating a new job
Documentations
- Search Documentation
Search through documentation using semantic and keyword search
Page Contents
- Get Page Content
Retrieve the full text content of a documentation page by its path
Assistant Messages
- Create Assistant Message
Generate a streaming response from the AI assistant trained on your documentation
User Feedbacks
- Get User Feedback
Retrieve user feedback from your documentation including page ratings and code snippet feedback
Feedback By Pages
- Get Feedback By Page
Retrieve user feedback counts aggregated by documentation page
Assistant Conversations
- Get Assistant Conversations
Retrieve AI assistant conversation history including queries, responses, and cited sources
Queries
- Get Search Queries
Retrieve documentation search terms with hit counts, click-through rates, and top clicked pages
Page Views
- Get Page Views
Retrieve per-page and site-wide content view counts split by human and AI traffic
Unique Visitors
- Get Unique Visitors
Retrieve per-page and site-wide approximate unique visitor counts split by human and AI traffic
Set Up Your Mintlify MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Mintlify in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"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>"
]
}
}
}Mintlify MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
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
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
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
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
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
Mintlify MCP Server FAQ
Mintlify MCP server vs direct API integration — what's the difference?
A Mintlify MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Mintlify. A Mintlify MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Mintlify at runtime. StackOne provides both.
How does Mintlify authentication work for AI agents?
Mintlify authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Mintlify account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Mintlify MCP tools vulnerable to prompt injection?
Yes — Mintlify MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Mintlify agent and how do I avoid it?
Context bloat happens when Mintlify tool schemas and API responses eat your Mintlify agent's memory, preventing it from reasoning effectively. A single Mintlify query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Mintlify agent can access?
Yes — you can limit which actions your Mintlify agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Mintlify MCP server?
Yes — you can create custom agent actions for your Mintlify MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Mintlify's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Mintlify MCP server?
Skip a Mintlify MCP server if your integration is purely software-to-software — direct Mintlify API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Mintlify actions at runtime.
What AI frameworks and AI clients does the StackOne Mintlify MCP server support?
The StackOne Mintlify MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.