product updateMistral AI

Mistral launches 20+ MCP connectors and memory system for Le Chat, all features free

TL;DR

Mistral has released 20+ Model Context Protocol (MCP) connectors for Le Chat, enabling integration with enterprise tools including Databricks, Snowflake, GitHub, Atlassian, Asana, Stripe, and Zapier. The company also introduced Memories, a cross-conversation context system that retains user preferences and facts. Both features are available on Le Chat's free plan.

2 min read
0

Mistral launches 20+ MCP connectors and memory system for Le Chat, all features free

Mistral has released 20+ Model Context Protocol (MCP) connectors for Le Chat, enabling direct integration with enterprise tools across data, productivity, development, automation, and commerce categories. The company also introduced Memories, a cross-conversation context retention system. Both features are available on Le Chat's free plan with no credit card required.

MCP Connector Directory

The connector library spans five core categories:

Data platforms: Databricks (coming soon), Snowflake (coming soon), Pinecone, Prisma Postgres, DeepWiki

Productivity tools: Box, Notion, Asana, Monday.com, Atlassian (Jira, Confluence), Outlook

Development platforms: GitHub (issues, PRs, repositories), Linear, Sentry, Cloudflare Development Platform

Automation: Zapier, Brevo

Commerce: PayPal, Plaid, Square, Stripe

Users can also connect to any remote MCP server not listed in the directory, extending functionality beyond the pre-built connectors. Admin users control which connectors are available to team members through on-behalf authentication.

Memories System

The Memories feature retains context across conversations, storing user preferences, decisions, and work-specific details. According to Mistral, the system "saves what's important, avoiding forbidden or sensitive inferences, ignoring ephemeral content, and retrieving the right information without hallucinations."

Users maintain full control over stored memories with the ability to add, edit, or delete entries. The system includes an import tool for migrating memories from ChatGPT.

Mistral states the feature "scores high in our evaluations for accuracy and reliability," though specific benchmark numbers were not disclosed.

Deployment Options

Le Chat with MCP connectors supports three deployment models:

  • Self-hosted on-premises
  • Private or public cloud deployment
  • Fully managed service on Mistral Cloud

The company is positioning these capabilities for enterprise adoption, with admin controls and flexible deployment addressing common enterprise security requirements.

What this means

Mistral is making a direct play for enterprise AI assistant adoption by offering sophisticated tooling—MCP integration and persistent memory—on a free tier. This contrasts with competitors who typically gate advanced features behind paid plans. The MCP connector approach leverages Anthropic's open protocol, which could accelerate Le Chat's integration ecosystem if developers build custom connectors. The free availability may pressure other AI assistant providers to expand their free tiers or accelerate their own connector ecosystems. Mistral's focus on deployment flexibility (on-prem, cloud, self-hosted) addresses a key enterprise requirement that consumer-focused AI assistants often overlook.

Related Articles

product update

Mistral AI Releases MCP Connectors in Studio with Direct Tool Calling and Human-in-the-Loop Workflows

Mistral AI has released Connectors in Studio, allowing developers to integrate custom MCP (Model Context Protocol) servers alongside built-in connectors for enterprise AI applications. The release includes direct tool calling, human-in-the-loop approval flows, and programmatic connector management via API and SDK.

model release

Mistral Releases Medium 3.5: 128B Model with Cloud Coding Agents and 77.6% SWE-Bench Verified

Mistral AI released Medium 3.5, a 128B dense model with a 256k context window that scores 77.6% on SWE-Bench Verified. The model powers new remote coding agents in Mistral Vibe that run asynchronously in the cloud, plus a new Work mode in Le Chat for multi-step agentic tasks.

model release

Mistral releases Devstral Medium and Small 1.1 with 61.6% SWE-Bench Verified score

Mistral AI has released two specialized coding models: Devstral Medium, achieving 61.6% on SWE-Bench Verified, and Devstral Small 1.1, scoring 53.6% and released under Apache 2.0 license. The company claims Devstral Medium surpasses Gemini 2.5 Pro and GPT-4.1 at a quarter of the price.

product update

Mistral AI Launches Compute Infrastructure Service with Tens of Thousands of NVIDIA GPUs

Mistral AI has launched Mistral Compute, an AI infrastructure service offering private, integrated stacks including GPUs, orchestration, and APIs. The service will provide access to tens of thousands of NVIDIA GPUs, targeting European, Middle Eastern, and Asian customers seeking alternatives to US or China-based cloud providers.

Comments

Loading...