Create powerful AI workflows by connecting multiple MCP servers including Salesforce, Gong, GitHub with Claude's advanced reasoning capabilities in Klavis AI.
Salesforce is the world's leading customer relationship management (CRM) platform that helps businesses connect with customers, partners, and potential customers
Gong is a revenue intelligence platform that captures and analyzes all revenue-related interactions to help sales teams close more deals. It provides conversation analytics, deal insights, and sales performance tracking through call recordings and transcripts
Enhanced GitHub MCP Server
Follow these steps to connect Claude to these MCP servers
Sign up for KlavisAI to access our MCP server management platform and get your API keys.
Add your desired MCP servers to Claude and configure authentication settings with your Anthropic API key.
Verify your connections work correctly with Claude's function calling and start using your enhanced AI capabilities.
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"
salesforce_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.SALESFORCE,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
gong_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.GONG,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
github_mcp_instance = klavis_client.mcp_server.create_server_instance(
server_name=McpServerName.GITHUB,
user_id="1234",
platform_name="Klavis",
connection_type=ConnectionType.STREAMABLE_HTTP,
)
# Get tools from all MCP servers
salesforce_tools = klavis_client.mcp_server.list_tools(
server_url=salesforce_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.ANTHROPIC,
)
gong_tools = klavis_client.mcp_server.list_tools(
server_url=gong_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.ANTHROPIC,
)
github_tools = klavis_client.mcp_server.list_tools(
server_url=github_mcp_instance.server_url,
connection_type=ConnectionType.STREAMABLE_HTTP,
format=ToolFormat.ANTHROPIC,
)
# Combine all tools
all_tools = []
all_tools.extend(salesforce_tools.tools)
all_tools.extend(gong_tools.tools)
all_tools.extend(github_tools.tools)
messages = [
{"role": "user", "content": user_message}
]
response = anthropic_client.messages.create(
model=CLAUDE_MODEL,
max_tokens=4000,
messages=messages,
tools=all_tools
)
Everything you need to know about connecting Claude to these MCP servers
Join developers who are already using KlavisAI to power their Claude applications with these MCP servers.
Start For Free