LlamaParse MCP

The LlamaParse MCP is a Model Context Protocol server that exposes the LlamaParse Platform’s document-processing capabilities (Parse, Classify, Extract, Split, and Index v2) as tools that any MCP-compatible agent can call. Instead of wiring up the REST API or SDK yourself, you connect your agent to the MCP server once and let it parse documents, extract structured data, classify and split files, and retrieve from your indexes directly.

The server is open source and hosted at https://mcp.llamaindex.ai.

Authentication

The MCP server uses OAuth, aligned with the rest of the LlamaParse Platform. You authenticate once, in your MCP client, and the same credentials gate access to all LlamaParse services, no API key needed. Authentication happens automatically on first use, and tokens refresh without manual intervention.

Connecting an MCP client

Connect to the unified endpoint https://mcp.llamaindex.ai/mcp to get the full platform surface area (Parse, Classify, Extract, Split, and Index v2) in one server.

Cursor

Click the button to add the server in one click:

Open in Cursor

Or add the server manually to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "llamaparse": {
      "type": "http",
      "url": "https://mcp.llamaindex.ai/mcp"
    }
  }
}

VS Code

Click the button to add the server in one click:

Open in VS Code

Or add the server manually to your settings.json:

{
  "mcp": {
    "servers": {
      "llamaparse": {
        "type": "http",
        "url": "https://mcp.llamaindex.ai/mcp"
      }
    }
  }
}

Claude Code

claude mcp add --transport http llamaparse https://mcp.llamaindex.ai/mcp

Claude Desktop

Open the connectors settings to add the server:

Open in Claude Desktop

Or add the server manually to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "llamaparse": {
      "type": "http",
      "url": "https://mcp.llamaindex.ai/mcp"
    }
  }
}

Codex

Open Codex settings to add the server:

Open in Codex

Or add through the CLI:

codex mcp add llamaparse --url https://mcp.llamaindex.ai/mcp

The first time your agent uses a tool, you’ll be prompted to authenticate through your browser.

Available tools

The MCP server groups its tools by product.

Upload helpers

Most processing tools operate on files already on the LlamaParse Platform, so the server provides two ways to get a file there:

• uploadFileByUrl — accepts a public file URL, fetches the file, and uploads it to the platform.
• getUploadUrl — returns a temporary, authenticated upload endpoint your client can POST a local file to via multipart form data.

Parse

• parseFile — parses a document into clean, structured text/markdown using Parse.

Classify

• classifyFile — assigns a document to one of your defined categories using Classify.

Split

• splitFile — segments a document into logical sections using Split.

Extract

Structured extraction is more reliable through dedicated tools than asking an agent to read a parsed document and pull fields out of the text: agents may only receive a truncated version of large documents, and prompt-only extraction leaves the output schema underspecified.

• generateExtractionConfig — generates a JSON schema and extraction rules from a description.
• extractFile — runs extraction against a file using an extraction configuration.

Index v2

Index v2 is the managed knowledge base offered by the LlamaParse Platform, built for agentic workflows. Beyond semantic search, it gives agents file-system-like access to the underlying documents:

• getUserProjects — lists your available projects.
• listIndexes — discovers the indexes you can query.
• findFilesInIndex — locates relevant files within an index.
• readFileFromIndex — reads the contents of a file in an index.
• grepFileFromIndex — searches for pattern matches within indexed files.
• retrieveFromIndex — performs hybrid (sparse + dense) retrieval over an index.

Product-specific servers

The unified /mcp endpoint exposes every capability, which is ideal for exploratory work and broader document-processing tasks. When you want a more focused tool list, you can connect directly to a product-specific server instead. Narrowing the scope helps agents make tool-selection decisions more reliably and run independent tasks in parallel.

The server tree looks like this:

https://mcp.llamaindex.ai/
├── mcp                       # full platform: Parse, Classify, Extract, Split, Index v2
├── parse
│   └── /mcp
├── classify
│   ├── /mcp
│   └── /{configId}/mcp
├── extract
│   ├── /mcp
│   └── /{configId}/mcp
├── split
│   ├── /mcp
│   └── /{configId}/mcp
└── index
    └── /{indexId}/mcp

The classify, extract, and split servers can optionally inherit a configuration ID, and index inherits an index ID, directly from the route. When you connect to a /{configId}/mcp endpoint, the agent operates with that configuration already in context.

For example, to connect an agent directly to a specific classification configuration:

{
  "mcpServers": {
    "classify-folder-1": {
      "type": "http",
      "url": "https://mcp.llamaindex.ai/classify/cfg-abc/mcp"
    }
  }
}

And, in parallel, to a specific extraction configuration:

{
  "mcpServers": {
    "extract-folder-1": {
      "type": "http",
      "url": "https://mcp.llamaindex.ai/extract/cfg-abc/mcp"
    }
  }
}

This modular model lets you compose workflows from multiple specialized servers, each responsible for a well-defined task, improving isolation, enabling greater parallelism, and giving you fine-grained control over throughput.

Example workflows

• Classify, then extract — an agent classifies the files in a folder using a classification server, organizes them into category-specific subfolders, then runs the matching extraction configuration against each category in parallel and saves the results as JSON for downstream analysis.
• Agentic retrieval — an agent discovers indexes with listIndexes, locates relevant files with findFilesInIndex, inspects them with readFileFromIndex, searches with grepFileFromIndex, and retrieves passages with retrieveFromIndex — navigating PDFs, Office documents, images, and other unstructured files the way it would a file system.

Tip

The unified /mcp server is the best starting point for prototyping. Reach for the product-specific servers once you know which capabilities a workflow needs and want tighter scoping or more parallelism.