Mintlify Index
OfficialProvides real-time documentation retrieval from Mintlify's indexed developer documentation, returning cited answers to implementation questions.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Mintlify IndexHow do I set up authentication in Next.js with NextAuth?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Mintlify Index
Real-time documentation retrieval for coding agents.
Mintlify Index answers implementation questions (syntax, configuration, migration, setup) with compact, cited context assembled from primary-source developer documentation and live web search. It ships as a hosted MCP server exposing a single context tool.
Quickstart
npx mint indexThe interactive installer detects your coding agents and adds the hosted MCP server (https://index.mintlify.com/mcp) plus a usage rule so the agent reaches for it automatically. Supported clients:
Claude Code
Cursor
VS Code (Copilot)
Codex
OpenCode
Windsurf
Zed
Non-interactive setup:
npx mint index --claude --cursor --yes # specific clients, skip prompts
npx mint index --project # write project-level config instead of globalAny other MCP client can be pointed at the server manually:
{
"mcpServers": {
"mintlify-index": {
"type": "http",
"url": "https://index.mintlify.com/mcp"
}
}
}The context tool takes a query (plus optional product, includeDomains, excludeDomains, and a tokenBudget up to 6000) and returns a cited answer in one call.
Related MCP server: docctx
How it works
query
│
▼
router ────────────── LLM route decision against a catalog of indexed sites
│
├───────────────┬─────────────────┐
▼ ▼ │
mintlify leg web leg │ run concurrently or routed
(Chroma hybrid (Exa search + │
search over live contents) │
indexed docs) │
└───────┬───────┘ │
▼ │
combine + rerank ── deterministic scoring, hosted reranker, LLM fallback
│
▼
context assembly ── token-budget packing with query-centered snippets
│
▼
MCP `context` toolDirectory | Pipeline stage |
| LLM query router deciding which leg(s) to serve |
| The engine: legs, blending, ranking, relevance cutoff, hydration |
| Web leg over Exa |
| Hosted + LLM rerankers, query-centered snippeting |
| Token-budget context packing |
|
|
| Tunable retrieval configuration |
| MCP server: the |
| The |
| Interfaces for Mintlify-platform components backing the hosted service |
About this repo
This is a source release of the hosted service. It is not runnable standalone: docs ingestion, the Chroma corpus, auth, and infrastructure live in the Mintlify platform and are represented here by small interfaces in src/internal/. src/server.ts shows how the pieces wire together in production.
License
This server cannot be deployed
Maintenance
Related MCP Connectors
Search GitHub, npm, PyPI, StackOverflow, ArXiv from one MCP — built for coding agents.
Retrieve citation-ready technical context and coordinate evidence-backed work between AI agents.
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Token-efficient search for coding agents over public and private documentation.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI coding agents to retrieve and manage code context with hybrid search, project memory, and observability via MCP tools.29MIT
- AlicenseAqualityDmaintenanceLocal-first context retrieval engine that serves precise documentation chunks to coding agents via MCP, ensuring high-confidence context for code generation.3MIT
- AlicenseNot gradedqualityBmaintenanceAgent-native developer Q&A service providing MCP tooling and A2A runtime endpoints for deep research and citations.2MIT
- AlicenseNot gradedqualityAmaintenanceEnables coding agents to retrieve human-validated, version-pinned web3 integration recipes and evidence over MCP, with tools for search, exact lookup, dependency inspection, and full-text retrieval. Every result carries re-fetchable citations and honest abstention when no matching evidence exists.MIT