About Carbon Arc
Carbon Arc MCP is a remote MCP server from Carbon Arc, reached over Streamable HTTP and authenticated with OAuth 2.0 and dynamic client registration. The README is brief and does not describe specific tools or data offerings beyond access setup and Cursor installation.
Key features
- 01Remote endpoint over Streamable HTTP
- 02OAuth 2.0 with dynamic client registration
- 03Installation through the Cursor plugin marketplace
Use cases
- 01Connecting Cursor to the Carbon Arc service
MCP support
Carbon Arc MCP is a remote MCP server. Clients connect to its Streamable HTTP endpoint and authenticate with OAuth 2.0 and dynamic client registration.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.carbonarc.aiclaude mcp add --transport http carbon-arc https://mcp.carbonarc.ai{"mcpServers":{"carbon-arc":{"type":"http","url":"https://mcp.carbonarc.ai"}}}Open in Cursor{"servers":{"carbon-arc":{"type":"http","url":"https://mcp.carbonarc.ai"}}}Open in VS Code{"mcpServers":{"carbon-arc":{"type":"http","url":"https://mcp.carbonarc.ai"}}}{"mcpServers":{"carbon-arc":{"serverUrl":"https://mcp.carbonarc.ai"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMECarbon Arc MCP
- Endpoint:
https://mcp.carbonarc.ai(Streamable HTTP) - Auth: OAuth 2.0 + Dynamic Client Registration
- Docs: https://docs.carbonarc.ai/platform/mcp/carbonarc-mcp
Getting access
To get an API Token:
- Sign up for Carbon Arc at https://app.carbonarc.co/pricing
- Log into your account
- Get your API Token from your user profile
Questions or need help?
- Support: [email protected]
- Sales: [email protected]
Install via Cursor
- Open Cursor → Plugins → Browse Marketplace
- Search "Carbon Arc" → Install
License: Apache 2.0
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.