How to Use CB Insights MCP Server with Bifrost
Use the CB Insights MCP Server to connect to ChatCBI
[ MCP SERVER SUMMARY ]
CB Insights MCP server summary
Use the CB Insights MCP Server to connect to ChatCBI Connect CB Insights through Bifrost MCP Gateway to centralize access control, virtual keys, and tool-call observability for your AI assistants.
| Property | Details |
|---|---|
| Company | Upstream maintainer |
| Connection type | Confirm upstream transport |
| Authentication | Varies by upstream server |
| Package or endpoint | See upstream documentation |
| Capabilities | CB Insights tools over MCP, AI assistant connectivity, Governed tool access through Bifrost |
| Official documentation | CB Insights MCP documentation |
Before you start
- Review the CB Insights upstream documentation for its installation requirements
- Obtain any credentials required by the upstream service
- A running Bifrost MCP Gateway instance
What you can do with CB Insights
- Use the CB Insights MCP Server to connect to ChatCBI
- Expose CB Insights tools to Claude, Cursor, and other MCP clients through one endpoint
- Apply virtual keys, tool allowlists, and audit logging at the gateway
[ HOW TO CONNECT ]
Connect CB Insights to Bifrost in three steps
Install Bifrost
Start the gateway locally or deploy in your VPC.
npx -y @maximhq/bifrost
Add CB Insights in MCP Gateway
Open MCP Gateway in the Bifrost dashboard, click New MCP Server, and select the transport documented by the upstream server. Or register via the API below.
• Confirm the transport, command or endpoint, and authentication requirements in the CB Insights upstream documentation.
• Replace every placeholder in the example before sending the request.
Point clients at Bifrost /mcp
Configure Claude Desktop, Cursor, or Claude Code to use your Bifrost endpoint with a virtual key instead of connecting directly to CB Insights.
{
"mcpServers": {
"bifrost": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer vk_your_virtual_key"
}
}
}
}[ EXAMPLE CONFIG ]
Register CB Insights via API
Add this MCP client with a POST to /api/mcp/client. See Connecting to MCP Servers for full options.
# For a remote HTTP or SSE server:
curl -X POST http://localhost:8080/api/mcp/client \
-H "Content-Type: application/json" \
-d '{
"name": "cb-insights",
"connection_type": "<http|sse>",
"connection_string": "<upstream MCP endpoint>",
"tools_to_execute": ["*"]
}'
# For a local STDIO server:
curl -X POST http://localhost:8080/api/mcp/client \
-H "Content-Type: application/json" \
-d '{
"name": "cb-insights",
"connection_type": "stdio",
"stdio_config": {
"command": "<upstream command>",
"args": ["<arg>"]
},
"tools_to_execute": ["*"]
}'[ WHY BIFROST ]
Run CB Insights through one governed gateway
Access control
Virtual keys, RBAC, and tool allowlists per team or agent.
Cost governance
Attribute MCP tool spend alongside LLM usage in one view.
Observability
Log every tool call with latency, server, and virtual key metadata.
Credential isolation
Upstream secrets stay in the gateway — not on every laptop.
[ FAQ ]
Common questions
What does the CB Insights MCP server do?
Use the CB Insights MCP Server to connect to ChatCBI The exact tools available depend on the upstream server version and configuration.
How do I connect CB Insights to Bifrost?
Check the upstream documentation to determine whether CB Insights uses STDIO, Streamable HTTP, or SSE. Then add it as an MCP client in Bifrost using the corresponding command or endpoint.
Does Bifrost replace the CB Insights MCP server?
No. Bifrost connects to CB Insights as an upstream MCP client and adds a governed gateway between that server and your AI assistants.
[ RELATED SERVERS ]
More MCP integrations
Carbon Voice
MCP Server that connects AI Agents to Carbon Voice. Create, manage, and interact with voice messages, conversations, direct messages, folders, voice memos, AI actions and more in Carbon Voice.
Cartesia
Connect to the Cartesia voice platform to perform text-to-speech, voice cloning etc.
Cashfree
Cashfree Payments official MCP server.