Labradoc MCP Server
Check Gmail connection status and initiate OAuth flow to connect.
Check Google Drive connection status and initiate OAuth flow to connect.
Create a Stripe checkout session to purchase AI credits for the user.
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., "@Labradoc MCP Server list my recent documents"
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.
Labradoc MCP Server
A Model Context Protocol (MCP) server that exposes Labradoc API capabilities as MCP tools. This enables AI assistants like Claude Desktop, OpenAI Agents, and other MCP-compatible clients to interact with Labradoc's document management, email ingestion, task extraction, and integration features.
Features
Files: List, search, get, and archive documents
Email: Manage inbound email addresses and view ingested emails
Tasks: List and close tasks extracted from documents
User: View usage statistics and purchase AI credits
Integrations: Connect Google Drive, Gmail, and Microsoft Outlook
Related MCP server: Document Tools
Requirements
Node.js 20+
A Labradoc API key
Quick Start
npx @labradoc/mcpOr install globally:
npm install -g @labradoc/mcp
LABRADOC_API_KEY=your-key labradoc-mcpConfiguration
Variable | Required | Default | Description |
| Yes | - | Your Labradoc API key |
| No |
| Labradoc API base URL |
| No |
| Log level: debug, info, warn, error |
Available MCP Tools
Files
Tool | Description |
| List user's files with optional status filter, pagination, and search |
| Search files by query string |
| Get a single file by ID |
| Archive files by their IDs |
Tool | Description |
| List user's inbound email addresses |
| Request a new inbound email address |
| List ingested emails |
Tasks
Tool | Description |
| List tasks extracted from documents |
| Close/complete tasks by their IDs |
User & Billing
Tool | Description |
| Get user statistics (completed pages, unlimited pages status) |
| Create a Stripe checkout session for AI credits |
Integrations
Tool | Description |
| Check if Google Drive is connected |
| Start Google Drive OAuth flow |
| Check if Gmail is connected |
| Start Gmail OAuth flow |
| Check if Microsoft Outlook is connected |
| Start Microsoft Outlook OAuth flow |
Usage
Claude Desktop (macOS/Windows)
Edit your Claude Desktop configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"labradoc": {
"command": "npx",
"args": ["@labradoc/mcp"]
}
}
}Or with a global install:
{
"mcpServers": {
"labradoc": {
"command": "labradoc-mcp"
}
}
}Set the API key in your environment or .env file:
LABRADOC_API_KEY=your-api-keyClaude CLI
claude mcp add labradoc -- npx @labradoc/mcpDirect stdio Usage
LABRADOC_API_KEY=your-key npx @labradoc/mcpDevelopment
npm install
npm run build
LABRADOC_API_KEY=your-key node dist/index.jsLicense
MIT
Available Tools
17 toolsbilling_checkoutB
Create a Stripe checkout session for AI credits
Inputs: no named parameters.
email_addresses_createB
Request a new inbound email address
Inputs: description.
email_addresses_listB
List user's inbound email addresses
Inputs: no named parameters.
emails_listB
List ingested emails
Inputs: no named parameters.
files_deleteC
Archive files by their IDs
Inputs: ids (required).
files_getA
Get a single file by ID
Inputs: file_id (required).
files_listC
List user's files with optional status filter, pagination, and search
Inputs: status, page_size, page_number, query.
files_searchB
Search files by query string
Inputs: query (required).
google_drive_connectA
Start Google Drive OAuth flow to connect your account
Inputs: no named parameters.
google_drive_statusA
Check if Google Drive is connected
Inputs: no named parameters.
google_gmail_connectA
Start Gmail OAuth flow to connect your account
Inputs: no named parameters.
google_gmail_statusC
Check if Gmail is connected
Inputs: no named parameters.
microsoft_outlook_connectB
Start Microsoft Outlook OAuth flow to connect your account
Inputs: no named parameters.
microsoft_outlook_statusA
Check if Microsoft Outlook is connected
Inputs: no named parameters.
tasks_closeB
Close/complete tasks by their IDs
Inputs: ids (required).
tasks_listB
List tasks extracted from documents
Inputs: no named parameters.
user_statsA
Get user statistics including completed pages and unlimited pages status
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Each tool targets a distinct resource or action: billing, email addresses, ingested emails, files, cloud service connections (Drive, Gmail, Outlook), tasks, and user stats. Descriptions clearly differentiate overlapping areas like email addresses vs ingested emails vs Gmail status.
Most tools follow a consistent verb_noun pattern in snake_case (e.g., files_list, google_drive_connect). Minor deviations exist: 'billing_checkout' uses a non-standard verb, and 'user_stats' abbreviates. Overall pattern is clear and predictable.
17 tools cover a broad domain including files, email, cloud integrations, tasks, and billing. The count is slightly above the typical 3-15 range but each tool serves a distinct purpose, making the set well-scoped without bloat.
Notable gaps exist: no file create/update, no task creation, no billing history or status, no ability to disconnect cloud services. While core retrieval and listing are covered, essential lifecycle operations are missing, which will hinder agent workflows.
Maintenance
Related MCP Connectors
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Connect AI assistants to your Tedix organization’s tasks, knowledge, apps, and results through MCP.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI assistants to search, read, and manage documents in a Laserfiche repository via the MCP protocol, with optional write operations and safety controls.2373 PyPI2MIT
- FlicenseNot gradedqualityDmaintenanceEnables document conversion and processing through an MCP server interface for AI assistants.-
- AlicenseNot gradedqualityDmaintenanceProvides AI assistants with access to ProductLane support threads, contacts, changelogs, and documentation through a set of MCP tools.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to interact with ExecuFunction's project management, knowledge base, code indexing, and calendar tools via MCP, allowing natural language management of tasks, notes, and code.MIT