OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Klavis

Klavis is an open-source Python framework and platform that connects AI agents to external tools through MCP integrations, OAuth-enabled connectors, SDKs, a REST API and scalable MCP sandbox environments.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Klavis — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Klavis when an AI agent needs a documented MCP-based tool layer, prebuilt service connectors or sandbox infrastructure for tool-use development and training.

Who it is for

  • Developers building AI agents that need external tool access
  • Teams integrating SaaS services through MCP
  • Researchers and engineers working on LLM tool-use training or reinforcement learning

Documented uses

  • Connect agents to prebuilt external-tool integrations
  • Create individual MCP server instances or grouped Strata servers
  • Add OAuth-supported service connections
  • Provide MCP environments for LLM training and reinforcement learning
  • Expose integrations through Python, TypeScript or REST interfaces
Before you choose

Requirements & limits

The repository documents cloud-hosted, self-hosted and server options, plus Python, TypeScript and REST interfaces. It shows API-key use for SDK examples.

  • Choose between cloud-hosted, self-hosted and server deployment paths based on the integration architecture being built.
  • Use Strata when several MCP servers need to be grouped for an agent; individual MCP server instances are also documented.
  • The repository states that more than 100 prebuilt integrations and OAuth support are available, but the complete connector catalogue is not provided.
  • The project is public and licensed under Apache-2.0.
  • The supplied examples use Gmail and Slack, while connector-specific configuration and authorization details are not established.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Create a Strata MCP server with the Python SDK

Set up a Strata instance containing the Gmail and Slack MCP servers.

Before you start

  • Python environment with the Klavis SDK installed
  • Klavis API key
  • A user identifier
  • Access to the Gmail and Slack MCP server names

Steps

  1. Import Klavis and the MCP server name type.

  2. Initialize the client with an API key.

  3. Call the Strata server creation method with a user ID and Gmail and Slack server names.

Expected outcome

A Strata server instance is requested with Gmail and Slack integrations.

Guide limitations

  • The supplied quick start does not document the resulting server response, subsequent connection steps or connector-specific authorization flow.
  • The example does not establish that every listed integration is available in the same deployment.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
Klavis-AI/klavis · Official homepage title · retained in its source language
How we review sourcesSuggest a correction