# Le Chat AI MCP Server > Le Chat AI: Independent guide to Mistral's Le Chat [](https://nodejs.org) [](https://nodejs.org) [](https://modelcontextprotocol.io/specification) [](https://nodejs.org)
[](https://modelcontextprotocol.io/specification)
[](#installation)
[](https://smithery.ai)
[](./LICENSE)
[](https://modelcontextprotocol.io)
A Model Context Protocol server that exposes the canonical Le Chat AI knowledge surface — models, prompts, and chat workflows, pricing, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.
Official website: https://lechatai.online
## 💬 About Le Chat AI
LeChat AI (lechatai.online) is an independent guide and resource hub for Mistral's Le Chat conversational AI platform. The site covers the platform's capabilities in depth — from its speed benchmarks and pricing tiers to its European data compliance stance and open-weight model philosophy. Visitors can read structured comparisons, tutorials, and feature breakdowns, and follow direct links to test Le Chat themselves. The content is oriented toward helping individuals and organizations evaluate whether Le Chat fits their needs, particularly those comparing it against ChatGPT, Claude, Gemini, or other mainstream AI assistants.
## Key Features
- **Flash Answers**: Near-instantaneous response generation powered by Cerebras WSE-3 hardware, reaching approximately 1,000 tokens per second — one of the fastest inference speeds available in a consumer-facing AI product.
- **Deep Research**: An automated research mode that synthesizes information from multiple sources and returns structured, cited reports — suited for market analysis, academic literature reviews, and competitive comparisons.
- **Document analysis**: Native support for large PDF imports (50+ pages) with summarization and in-line citation, allowing users to interrogate long documents without manual reading.
- **MCP connectors**: Over 20 integrations with third-party platforms including GitHub, Snowflake, and Atlassian, enabling Le Chat to pull live data from internal systems during conversations.
- **Memories**: Persistent cross-session context so the assistant retains relevant preferences and prior conversation details over time.
- **Canvas workspace**: A collaborative, document-style workspace for drafting and iterating on longer-form outputs alongside the assistant.
- **No Telemetry mode**: Available on the Pro tier, this option disables usage data collection — a meaningful option for privacy-conscious teams.
## Use Cases
- **Enterprise research workflows**: Teams use Deep Research to produce sourced briefings on competitors, technologies, or regulatory landscapes without manual aggregation.
- **Document review**: Legal, compliance, and finance professionals import large PDFs and ask targeted questions, receiving cited answers rather than raw text.
- **Developer tooling**: Engineering teams connect Le Chat to GitHub or internal databases via MCP connectors to query codebases, pull request histories, or data pipelines in natural language.
- **Privacy-first AI adoption**: European organizations subject to GDPR constraints evaluate Le Chat as a compliant alternative to US-hosted AI services, with EU data residency and telemetry controls.
- **AI platform comparison**: Individuals and procurement teams use the site's structured breakdowns to compare Le Chat's pricing (approximately $14.99/month for Pro) and capabilities against competing platforms before committing.
## Who Is It For
The primary audience is professionals and organizations already using or evaluating AI assistants who want a clear, detailed picture of what Le Chat offers. This includes enterprise IT and procurement teams assessing compliance requirements, developers looking for open-weight model deployability, and European companies that need GDPR-aligned tools with EU data hosting. It also serves individual power users who care about response speed, document handling depth, or third-party integrations — and who want a straightforward comparison rather than marketing material. The site assumes some familiarity with conversational AI but does not require technical expertise.
## Tools
### `list_models`
Return the canonical list of chat models exposed on the site, with capability notes. (Le Chat AI)
_Input:_ no parameters. _Returns:_ text/markdown.
### `get_pricing`
Return the canonical pricing entry point for Le Chat AI.
_Input:_ no parameters. _Returns:_ text/markdown.
### `get_official_links`
Return the canonical list of official links for Le Chat AI (website, support, docs when available).
_Input:_ no parameters. _Returns:_ text/markdown.
## Resources
- `site://lechatai/models` — Supported chat models and capability notes.
- `site://lechatai/pricing` — Canonical pricing entry point.
- `site://lechatai/faq` — Short FAQ generated from public site metadata.
- `site://lechatai/links` — Canonical URLs to share with users.
## Prompts
### `tell_me_about_lechatai`
Summarize what the site is, who it's for, and how it works. — Le Chat AI
### `start_chat_session_lechatai`
Open a chat-evaluation session against the site's models, with sensible defaults. — Le Chat AI
## Installation
### Install via Smithery
```bash
npx -y @smithery/cli install lechatai-mcp --client claude
```
(Replace `claude` with `cursor`, `windsurf`, or `continue` for those clients.)
### Install from source
```bash
git clone https://github.com/rocnubie/lechatai-mcp.git
cd lechatai-mcp
pnpm install
```
Then add to your MCP client config (`claude_desktop_config.json` for Claude Desktop, `mcp.json` for Cursor / Windsurf / Continue):
```json
{
"mcpServers": {
"lechatai-mcp": {
"command": "node",
"args": [
"/absolute/path/to/lechatai-mcp/src/index.mjs"
]
}
}
}
```
### Debug with MCP Inspector
```bash
npx @modelcontextprotocol/inspector node src/index.mjs
```
## Official Links
- Website: https://lechatai.online
- Pricing: https://lechatai.online/pricing
- GitHub: https://github.com/Rocniubi/MSA
- Support: support@lechatai.online
## Development
```bash
pnpm install
pnpm start # run the server over stdio
```
## License
MIT
No reviews yet — be the first
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
Social sign-in isn’t configured yet. You can still create an account with email below, or ask an admin to add Google/GitHub/Discord OAuth credentials.
A collection of reference implementations for the Model Context Protocol (MCP), demonstrating secure and controlled access to tools and data sources for Large…
🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your…