About Defeatbeta Api
Defeat Beta API MCP is an MCP server that exposes defeatbeta-api financial data to large language models through standardized contextual interfaces. It targets users who want agents to run structured, controlled market data analysis, and can be installed through natural language in supported clients.
Key features
- 01Exposes defeatbeta-api data to MCP clients
- 02Connects to clients over stdio transport
- 03Runs via uvx without manual deployment
- 04Supports HTTP proxy through DEFEATBETA_GATEWAY
Use cases
- 01Querying current stock prices and price history
- 02Comparing key financial metrics across companies
- 03Asking an agent to summarize recent market performance
MCP support
This project is an MCP server that connects to MCP clients such as Claude Desktop over stdio and exposes financial data queries to them.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEDefeat Beta API MCP
Defeat Beta API MCP is an MCP server that exposes data from defeatbeta-api to large language models via standardized contextual interfaces, enabling structured and controlled financial data analysis.
Click here to discover more ways to use MCP and explore additional use cases and best practices.
Overall Architecture
┌──────────────────────┐
│ MCP Client │
│ (Claude Desktop / │
│ Manus AI / │
│ Cherry Studio / │
│ Other MCP Clients) │
└──────────┬───────────┘
│ MCP (stdio)
│ JSON-RPC
▼
┌──────────────────────────────┐
│ Defeat Beta API MCP Server │
│ │
│ - MCP Tool Definitions │
│ - Context Construction │
│ - Windowing / Summarization │
│ - Output Shaping for LLM │
│ │
│ (runs in isolated .venv) │
└──────────┬───────────────────┘
│
│ Python API Calls
▼
┌──────────────────────────────┐
│ defeatbeta-api │
│ (Published PyPI Package) │
│ │
│ - Market Data Access │
│ - Price / History / Metrics │
│ │
└──────────┬───────────────────┘
│
▼
┌──────────────────────────────┐
│ Financial Data Sources │
│ (via defeatbeta-api) │
└──────────────────────────────┘
Installation
Defeat Beta API MCP can be installed through natural language in MCP-capable agents and clients, including Claude Desktop, Manus, Codex, Hermes Agent, OpenClaw Agent, and others.
Send the following message to your agent:
Install the Defeat Beta API MCP from https://github.com/defeat-beta/defeatbeta-api/tree/main/mcp. Use uvx to run it, configure it for this agent, and verify that the MCP server connects successfully.
The agent will handle the installation and MCP configuration for you.
Troubleshooting: Installation Timeout
The first startup may take longer while uvx downloads the package. If the installation or MCP connection times out, ask your agent to run the following command and then retry:
uvx --refresh "git+https://github.com/defeat-beta/defeatbeta-api.git#subdirectory=mcp"
Optional: HTTP Proxy
If your environment cannot access the Defeat Beta Yahoo Finance Dataset, ask your agent to configure the DEFEATBETA_GATEWAY environment variable for the MCP server:
Configure the Defeat Beta API MCP to use my HTTP proxy by setting DEFEATBETA_GATEWAY to http://127.0.0.1:8118, then restart the MCP server and verify the connection.
Replace http://127.0.0.1:8118 with your proxy address.
Usage
After installation, ask your agent financial data questions directly. The agent will use Defeat Beta API MCP when appropriate.
Examples:
- What is Apple's latest stock price?
- Show NVIDIA's price history for the last month.
- Compare the key financial metrics of Microsoft and Google.
- Summarize Tesla's recent market performance.
📷 View a Claude Desktop example
📷 View a Manus example
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.