KlavisAIKlavisAI
Sign Up

Connectto Doc2markdown, Supabase, Slack MCP Servers

Create powerful AI workflows by connecting multiple MCP servers including Doc2markdown, Supabase, Slack with Claude's advanced reasoning capabilities in Klavis AI.

Get Started FreeView All MCP Servers
Doc2markdown icon

Doc2markdown

featured

Convert any file to markdown using markitdown

Available Tools:

  • convert_document_to_markdown
Supabase icon

Supabase

featured

Supabase official MCP Server

Available Tools:

  • supabase_list_projects
  • supabase_get_project
  • supabase_get_cost
  • +21 more tools
Slack icon

Slack

featured

Slack is a messaging app for business that connects people to the information they need

Available Tools:

  • slack_list_channels
  • slack_post_message
  • slack_reply_to_thread
  • +6 more tools

Quick Setup Guide

Follow these steps to connect Claude to these MCP servers

1

Create Your Account

Sign up for KlavisAI to access our MCP server management platform and get your API keys.

2

Configure Connections

Add your desired MCP servers to Claude and configure authentication settings with your Anthropic API key.

3

Test & Deploy

Verify your connections work correctly with Claude's function calling and start using your enhanced AI capabilities.

Claude + KlavisAI Integration Snippets

View Documentation
import os
import json
from anthropic import Anthropic
from klavis import Klavis
from klavis.types import McpServerName, ConnectionType, ToolFormat

# Initialize clients
anthropic_client = Anthropic(api_key=os.getenv("ANTHROPIC_API_KEY"))
klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))

# Constants
CLAUDE_MODEL = "claude-3-5-sonnet-20241022"
user_message = "Your message here"

doc2markdown_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.DOC2MARKDOWN,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

supabase_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.SUPABASE,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

slack_mcp_instance = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.SLACK,
    user_id="1234",
    platform_name="Klavis",
    connection_type=ConnectionType.STREAMABLE_HTTP,
)

# Get tools from all MCP servers
doc2markdown_tools = klavis_client.mcp_server.list_tools(
    server_url=doc2markdown_mcp_instance.server_url,
    connection_type=ConnectionType.STREAMABLE_HTTP,
    format=ToolFormat.ANTHROPIC,
)
supabase_tools = klavis_client.mcp_server.list_tools(
    server_url=supabase_mcp_instance.server_url,
    connection_type=ConnectionType.STREAMABLE_HTTP,
    format=ToolFormat.ANTHROPIC,
)
slack_tools = klavis_client.mcp_server.list_tools(
    server_url=slack_mcp_instance.server_url,
    connection_type=ConnectionType.STREAMABLE_HTTP,
    format=ToolFormat.ANTHROPIC,
)

# Combine all tools
all_tools = []
all_tools.extend(doc2markdown_tools.tools)
all_tools.extend(supabase_tools.tools)
all_tools.extend(slack_tools.tools)

messages = [
    {"role": "user", "content": user_message}
]
        
response = anthropic_client.messages.create(
    model=CLAUDE_MODEL,
    max_tokens=4000,
    messages=messages,
    tools=all_tools
)

Frequently Asked Questions

Everything you need to know about connecting Claude to these MCP servers

Ready to Get Started?

Join developers who are already using KlavisAI to power their Claude applications with these MCP servers.

Start For Free