Mistral Adds 20+ MCP Connectors and Memory Features to Le Chat, All Free
Mistral released 20+ MCP-powered connectors for Le Chat, integrating tools like Databricks, Snowflake, GitHub, Stripe, and Asana. The update includes a memory feature that saves user preferences across conversations, with one-click import from ChatGPT. All features are available on the free plan.
Mistral launched 20+ enterprise integrations and a memory system for Le Chat today, with all features available on the free plan.
MCP Connectors Go Live
Le Chat now supports Model Context Protocol (MCP) connectors across six categories:
- Data: Databricks (coming soon), Snowflake (coming soon), Pinecone, Prisma Postgres, DeepWiki
- Productivity: Box, Notion, Asana, Monday.com, Jira, Confluence, Outlook
- Development: GitHub, Linear, Sentry, Cloudflare Development Platform
- Automation: Zapier, Brevo
- Commerce: PayPal, Plaid, Square, Stripe
- Custom: Users can add any remote MCP server
The connectors enable search, summarization, and actions within integrated tools. According to Mistral, enterprise admins control which connectors are available to users, with on-behalf authentication ensuring users only access permitted data.
Deployment options include self-hosted, private/public cloud, or Mistral Cloud.
Memory System Launched
Le Chat's new memory feature stores user preferences and facts across conversations. Mistral claims the system "saves what's important, avoiding forbidden or sensitive inferences" and "ignoring ephemeral content."
Users can add, edit, or delete memory entries at any time. The feature includes one-click import of memories from ChatGPT.
According to Mistral's internal evaluations, the memory system demonstrates "accuracy and reliability" in saving relevant information while avoiding hallucinations. No specific benchmark scores were disclosed.
Mobile and Enterprise Access
All features are available through chat.mistral.ai and mobile apps on iOS and Android. Enterprise deployment details are available through Mistral's sales team.
Mistral is hosting a webinar on MCP capabilities on September 9 and a two-day hackathon in Paris on September 13-14.
What This Means
Mistral is positioning Le Chat as an enterprise-ready ChatGPT alternative by matching OpenAI's memory features while adding broader tool integrations through MCP. The free tier strategy—offering all features without credit card requirements—is a direct challenge to ChatGPT Plus's $20/month pricing. The MCP connector approach gives developers flexibility to integrate proprietary tools, though the "coming soon" tags on Databricks and Snowflake suggest the enterprise data story is still incomplete.
Related Articles
AWS launches AgentCore platform for building voice AI agents with Amazon Nova 2 Sonic
AWS has released AgentCore, a new platform for hosting and running voice-based AI agents, integrated with Amazon Nova 2 Sonic for real-time speech capabilities. The platform uses the open Model Context Protocol (MCP) to connect agents to backend systems and deploys each conversation in isolated microVMs.
xAI's Grok 4.3 now available on AWS Bedrock with 1M token context and configurable reasoning
xAI has made Grok 4.3 generally available on Amazon Bedrock, marking xAI's debut as a Bedrock model provider. The multimodal model offers a 1 million token context window, configurable reasoning effort (none/low/medium/high), and runs on Bedrock's Mantle inference engine using OpenAI-compatible APIs.
Apple Intelligence cleared for China launch using Alibaba's Qwen AI model
China's Cyberspace Administration approved Apple Intelligence for launch in the country, backed by integration of Alibaba's Qwen AI model across Apple's operating systems. The deal ends a two-year delay that began when Apple Intelligence debuted in 2024.
GitHub Copilot for Visual Studio adds MCP server trust layer and C++ support
GitHub released its June 2026 update for Copilot in Visual Studio, adding a trust layer for Model Context Protocol (MCP) servers, improved usage analytics visibility, and the first C++ language scenarios for the AI coding assistant.
Comments
Loading...