TechPrufer
Sign inGet started

Blogs›Mistral AI›Connectors and Tool Orchestration

Connectors and Tool Orchestration

Connectors and Tool Orchestration

2
posts
2026

Mistral AI introduces enhanced controls for Connectors, including enriched admin controls for workspace/org-level access and tool-level permissions, API keys with connector scopes for secure automated workloads, multi-account connectors for authenticating with multiple accounts, a Connectors Debugger for root cause analysis of MCP connectors, and integration of Connectors into Vibe Code and Workflows for seamless and governed access to enterprise tools. This expands on the initial release of Connectors and tool orchestration by adding granular security and debugging capabilities.

2026

Bringing more control over your connectors | Mistral AI

6/24/2026

This post introduces several new capabilities for Mistral AI Connectors: Enriched admin controls (GA) for setting connector access per workspace/org and individual tool permissions, API keys with connector scopes (GA) for securing automated AI workloads, Multi-account connectors (GA) allowing a single connector to authenticate with multiple accounts, Connectors Debugger (Public Preview) for end-to-end root cause analysis of MCP connectors, Connectors in Vibe Code (GA) for reusing connectors in developer interfaces, and Connectors in Workflows (Public Preview) for long-running tasks. These features enhance security, manageability, and debugging for enterprise integrations.

Connect the dots: Build with built-in and custom MCPs in Studio | Mistral AI

5/22/2026

This post introduces Connectors in Studio, a new capability for building customized AI applications. It details programmatic access for managing connectors (create, modify, list, delete) and their tools, enabling their use across Mistral apps (Le Chat, AI Studio, Vibe). The post demonstrates integration with enterprise systems via Conversation API, Completions API, and Agent SDK. It highlights the abstraction of integration complexities like API docs, auth, and debugging. New features include direct tool calling for deterministic execution and human-in-the-loop approval flows for controlled tool execution. Code examples illustrate creating custom MCP connectors, configuring agents with connectors, and direct tool invocation.