longbridge/longbridge-mcp

Overview

An open-source Rust-based MCP server that provides programmatic access to Longbridge financial services. It enables AI agents to retrieve market data, execute trades, and manage portfolios through the Model Context Protocol.

Best for

Best for
Developers creating MCP-compatible AI agents that need to interact with Longbridge financial services

Use cases

• Fetch real-time stock quotes and historical market data from Longbridge
• Place and manage orders for stocks or ETFs programmatically
• Build AI-driven portfolio monitoring and rebalancing tools

How to use

Install

docker run -p 8443:8443 -v /path/to/certs:/certs:ro ghcr.io/longbridge/longbridge-mcp --bind 0.0.0.0:8443 --base-url https://mcp.example.com --tls-cert /certs/cert.pem --tls-key /certs/key.pem

Tools exposed

• LONGBRIDGE_MCP_CONFIG_DIR
• LONGBRIDGE_HTTP_URL
• LONGBRIDGE_PUBLIC_HOSTS
• LONGBRIDGE_GLOBAL_OAUTH_URL
• LONGBRIDGE_QUOTE_WS_URL
• LONGBRIDGE_TRADE_WS_URL
• LONGBRIDGE_MCP_QUOTE_WS_IDLE_TTL_SECS
• LONGBRIDGE_MCP_QUOTE_WS_MAX_CONTEXTS
• LONGBRIDGE_LOG_PATH
• mcp_tool_calls_total
• mcp_tool_call_duration_seconds
• mcp_tool_call_errors_total

Tested with

Claude Desktop, Claude Code, Cursor, Windsurf, Cline, Zed, ChatGPT, Claude

Example client config

{\n  "mcpServers": {\n    "longbridge": {\n      "url": "https://mcp.longbridge.com"\n    }\n  }\n}

Notes

An open-source Rust-based MCP server that provides programmatic access to Longbridge financial services. It enables AI agents to retrieve market data, execute trades, and manage portfolios through the Model Context Protocol.

7 stars on GitHub. Last updated 2026-05-28. Licensed MIT.

Use cases

• Fetch real-time stock quotes and historical market data from Longbridge
• Place and manage orders for stocks or ETFs programmatically
• Build AI-driven portfolio monitoring and rebalancing tools

Pros

• Written in Rust, offering high performance and low latency
• Leverages standardized MCP protocol for agent integration
• Open source with no vendor lock-in

Cons

• Very early stage with only 7 GitHub stars and limited community adoption
• Relies on Longbridge API; coverage of endpoints may be incomplete
• No official support from Longbridge; maintenance depends on contributors

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.