Sapling Logo

Sapling MCP Server

Grammar checking, AI content detection, paraphrasing, and the rest of Sapling's language tools — available directly inside Claude, Claude Code, and any other MCP-compatible AI assistant.

Add to Claude Code
claude mcp add sapling --env SAPLING_API_KEY=YOUR_API_KEY \
  -- npx -y @saplingai/mcp-server
Adds 7 tools to your assistant
  • sapling_grammar_check
  • sapling_spell_check
  • sapling_ai_detect
  • sapling_rephrase
  • sapling_summarize
  • sapling_sentiment
  • sapling_language_detect
Works in any client that supports local MCP servers
  • Claude Desktop
  • Claude Code
  • Cursor
  • Windsurf
  • Zed
  • Cline
Overview

What is the Sapling MCP Server?

The Model Context Protocol is an open standard that lets AI assistants call external tools and APIs in a structured way. The Sapling MCP Server exposes Sapling's language tools as MCP tools — so you can ask your assistant to grammar-check a document, detect AI-generated content, paraphrase a sentence, or analyze sentiment without leaving the conversation.

You ask in plain English

"Check this email for grammar errors." Your assistant decides a Sapling tool is the right way to answer.

The server runs locally

Your client starts @saplingai/mcp-server on your machine over stdio — no remote endpoint to expose.

Sapling answers

The tool calls the Sapling API and returns structured results — edits, scores, and suggestions — back into the conversation.

Capabilities

Available Tools

Seven tools, one API key. Every tool takes text and returns structured JSON your assistant can reason over.

Grammar & Spell Check Popular

sapling_grammar_check sapling_spell_check

Catch grammar errors, spelling mistakes, punctuation issues, and style problems in any text. Returns edit suggestions with types (preposition, verb tense, etc.) and confidence scores.

AI Content Detection

sapling_ai_detect

Detect whether text was written by a human or generated by GPT-5, Claude 4.5, Gemini 2.5, Qwen3, DeepSeek-V3, or other AI models. Returns an overall score plus per-sentence predictions.

Paraphrase & Rephrase

sapling_rephrase

Rewrite text with different tone, formality level, or style while preserving meaning. Useful for adapting content for different audiences.

Summarization

sapling_summarize

Generate concise summaries of longer documents, emails, or articles.

Sentiment Analysis

sapling_sentiment

Classify text as positive, negative, or neutral. Useful for reviewing customer feedback, tickets, or social media posts within an AI workflow.

Language Detection

sapling_language_detect

Identify the language of a text snippet. Supports 30+ languages including English, Spanish, French, German, Chinese, Japanese, Arabic, and more.

Get started

Quick Setup

Three steps, about two minutes. See the complete setup guide for other MCP clients and troubleshooting.

Install the prerequisites

You need Node.js 18 or newer (including npx) and a Sapling API key. Trial keys are available right after registration. Keep the key in your client's environment configuration — not in prompts or committed files.

Add the server to your client

Claude Code

Run in your terminal, replacing YOUR_API_KEY with your Sapling API key:

Terminal
claude mcp add sapling --env SAPLING_API_KEY=YOUR_API_KEY \
  -- npx -y @saplingai/mcp-server

Then run claude mcp list to confirm sapling is configured.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop:

claude_desktop_config.json
{
  "mcpServers": {
    "sapling": {
      "command": "npx",
      "args": ["-y", "@saplingai/mcp-server"],
      "env": {
        "SAPLING_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Other MCP clients

Any client that accepts a command, arguments, and environment variables can run the server:

Transportstdio
Commandnpx
Arguments-y, @saplingai/mcp-server
EnvironmentSAPLING_API_KEY=YOUR_API_KEY

The package does not expose a remote HTTP MCP endpoint — your client starts the local process, which then calls https://api.sapling.ai.

Approve the tools and start asking

Claude Code asks for approval the first time each Sapling tool runs. To pre-approve them — or if a call is denied instead of prompting — run /permissions and add an allow rule for mcp__sapling (all Sapling tools) or a single tool such as mcp__sapling__sapling_grammar_check. See tool permissions for details.

Check this email for grammar errors.
Is this resume AI-generated?
Paraphrase this paragraph in a more formal tone.
What's the sentiment of these customer reviews?
Why Sapling

Built for production, not just demos

Enterprise Security

The package doesn't log or persist your key or your text. Optional no-data-retention mode, plus on-premises deployment for HIPAA and PCI compliance.

Low Latency

Sapling's API is optimized for real-time use. Grammar checks typically return in under 200 ms, so tool calls don't stall the conversation.

Multilingual

Grammar checking and language detection across 30+ languages including Chinese, German, Spanish, Japanese, and more.

FAQ

Common questions

Which AI assistants work with the Sapling MCP server?

Any MCP client that supports local stdio servers, including Claude Desktop and Claude Code. Clients that accept a command, arguments, and environment variables can run it with command npx, arguments -y @saplingai/mcp-server, and SAPLING_API_KEY in the environment.

What do I need installed?

Node.js 18 or newer, including the npx command, plus a Sapling API key. The server runs locally on your machine and calls the Sapling API over HTTPS.

Do I need a Sapling API key?

Yes. Set your key as the SAPLING_API_KEY environment variable in your MCP client's server configuration. Trial keys are available after registration.

Is my text stored?

The MCP package does not log or persist your API key or submitted text. Tool inputs are sent to the configured Sapling API endpoint for processing. Contact us if you require no-data-retention or an on-premises deployment.

Can I point it at an on-premises Sapling deployment?

Yes. Set SAPLING_API_BASE_URL to your own Sapling endpoint. Only point it at an endpoint you trust — your API key and submitted text are sent there.

Put Sapling in your assistant

Grab an API key, paste one command, and start grammar-checking, detecting, and rephrasing from inside the tools you already use.

Need volume pricing, no-data-retention, or on-premises? Talk to us.