README.md•10.1 kB
# ✅ Official Alpha Vantage MCP Server
[](https://smithery.ai/server/@calvernaz/alphavantage)
[](https://mseep.ai/app/b76d0966-edd1-46fd-9cfb-b29a6d8cb563)
A MCP server for the stock market data API, Alphavantage API.
**MCP Server URL**: https://mcp.alphavantage.co
**PyPi**: https://pypi.org/project/alphavantage-mcp/
## Configuration
### Getting an API Key
1. Sign up for a [Free Alphavantage API key](https://www.alphavantage.co/support/#api-key)
2. Add the API key to your environment variables as `ALPHAVANTAGE_API_KEY`
## Installation
### Option 1: Using uvx (Recommended)
The easiest way to use the AlphaVantage MCP server is with `uvx`:
```bash
# Run directly without installation
uvx alphavantage-mcp
# Or with specific arguments
uvx alphavantage-mcp --server http --port 8080
```
### Option 2: Using pip
```bash
pip install alphavantage-mcp
alphavantage-mcp
```
### Option 3: From source
```bash
git clone https://github.com/calvernaz/alphavantage.git
cd alphavantage
uv run alphavantage
```
## Server Modes
The AlphaVantage server can run in two different modes:
### Stdio Server (Default)
This is the standard MCP server mode used for tools like Claude Desktop.
```bash
alphavantage
# or explicitly:
alphavantage --server stdio
```
### Streamable HTTP Server
This mode provides real-time updates via HTTP streaming.
```bash
alphavantage --server http --port 8080
```
### Streamable HTTP Server with OAuth 2.1 Authentication
This mode adds OAuth 2.1 authentication to the HTTP server, following the MCP specification for secure access.
```bash
alphavantage --server http --port 8080 --oauth
```
#### OAuth Configuration
When using the `--oauth` flag, the server requires OAuth 2.1 configuration via environment variables:
**Required Environment Variables:**
```bash
export OAUTH_AUTHORIZATION_SERVER_URL="https://your-auth-server.com/realms/your-realm"
export OAUTH_RESOURCE_SERVER_URI="https://your-mcp-server.com"
```
**Optional Environment Variables:**
```bash
# Token validation method (default: jwt)
export OAUTH_TOKEN_VALIDATION_METHOD="jwt" # or "introspection"
# For JWT validation
export OAUTH_JWT_PUBLIC_KEY="-----BEGIN PUBLIC KEY-----\n...\n-----END PUBLIC KEY-----"
export OAUTH_JWT_ALGORITHM="RS256" # default
# For token introspection validation
export OAUTH_INTROSPECTION_ENDPOINT="https://your-auth-server.com/realms/your-realm/protocol/openid-connect/token/introspect"
export OAUTH_INTROSPECTION_CLIENT_ID="your-client-id"
export OAUTH_INTROSPECTION_CLIENT_SECRET="your-client-secret"
# Optional: Required scopes (space-separated)
export OAUTH_REQUIRED_SCOPES="mcp:access mcp:read"
# Optional: Enable session binding for additional security (default: true)
export OAUTH_SESSION_BINDING_ENABLED="true"
```
#### OAuth Features
The OAuth implementation provides:
- **OAuth 2.0 Protected Resource Metadata** endpoint (`/.well-known/oauth-protected-resource`)
- **Bearer token authentication** for all MCP requests
- **JWT and Token Introspection** validation methods
- **MCP Security Best Practices** compliance:
- Token audience validation (prevents token passthrough attacks)
- Session hijacking prevention with secure session IDs
- User-bound sessions for additional security
- Proper WWW-Authenticate headers for 401 responses
#### Example: Keycloak Configuration
For testing with Keycloak:
```bash
# Keycloak OAuth configuration
export OAUTH_AUTHORIZATION_SERVER_URL="https://keycloak.example.com/realms/mcp-realm"
export OAUTH_RESOURCE_SERVER_URI="https://mcp.example.com"
export OAUTH_TOKEN_VALIDATION_METHOD="introspection"
export OAUTH_INTROSPECTION_ENDPOINT="https://keycloak.example.com/realms/mcp-realm/protocol/openid-connect/token/introspect"
export OAUTH_INTROSPECTION_CLIENT_ID="mcp-server"
export OAUTH_INTROSPECTION_CLIENT_SECRET="your-keycloak-client-secret"
export OAUTH_REQUIRED_SCOPES="mcp:access"
# Start server with OAuth
alphavantage --server http --port 8080 --oauth
```
#### OAuth Client Flow
When OAuth is enabled, MCP clients must:
1. **Discover** the authorization server via `GET /.well-known/oauth-protected-resource`
2. **Register** with the authorization server (if using Dynamic Client Registration)
3. **Obtain access tokens** from the authorization server
4. **Include tokens** in requests: `Authorization: Bearer <access-token>`
5. **Handle 401/403 responses** and refresh tokens as needed
Options:
- `--server`: Choose between `stdio` (default) or `http` server mode
- `--port`: Specify the port for the Streamable HTTP server (default: 8080)
- `--oauth`: Enable OAuth 2.1 authentication (requires `--server http`)
## 📊 Telemetry
The AlphaVantage MCP server includes optional Prometheus metrics for monitoring and observability.
### Enabling Telemetry
Set the following environment variables to enable telemetry:
```bash
# Enable telemetry (default: true)
export MCP_TELEMETRY_ENABLED=true
# Server identification (optional)
export MCP_SERVER_NAME=alphavantage
export MCP_SERVER_VERSION=1.0.0
# Metrics server port (default: 9464)
export MCP_METRICS_PORT=9464
```
### Metrics Endpoint
When telemetry is enabled, Prometheus metrics are available at:
```
http://localhost:9464/metrics
```
### Available Metrics
The server collects the following metrics for each tool call:
- **`mcp_tool_calls_total`** - Total number of tool calls (labeled by tool and outcome)
- **`mcp_tool_latency_seconds`** - Tool execution latency histogram
- **`mcp_tool_request_bytes`** - Request payload size histogram
- **`mcp_tool_response_bytes`** - Response payload size histogram
- **`mcp_tool_active_concurrency`** - Active concurrent tool calls gauge
- **`mcp_tool_errors_total`** - Total errors by type (timeout, bad_input, connection, unknown)
### Example Usage with Telemetry
```bash
# Start server with telemetry enabled
export MCP_TELEMETRY_ENABLED=true
export MCP_SERVER_NAME=alphavantage-prod
export ALPHAVANTAGE_API_KEY=your_api_key
alphavantage --server http --port 8080
# View metrics
curl http://localhost:9464/metrics
```
## 🚀 AWS Serverless Deployment
Deploy the AlphaVantage MCP Server on AWS Lambda using the stateless MCP pattern for production-ready, scalable deployment.
### Quick AWS Deployment
```bash
cd deploy/aws-stateless-mcp-lambda
export ALPHAVANTAGE_API_KEY=your_api_key_here
./deploy.sh
```
**Features:**
- ✅ **Stateless MCP pattern** - Perfect for Lambda's execution model
- ✅ **Auto-scaling** - Handles any load with AWS Lambda + API Gateway
- ✅ **Cost-effective** - Pay only for requests (~$1-5/month for typical usage)
- ✅ **Production-ready** - Based on AWS official sample patterns
- ✅ **OAuth 2.1 support** - Optional authentication for secure access
**📖 Full Documentation:** See [AWS Deployment Guide](deploy/aws-stateless-mcp-lambda/README.md) for complete setup instructions, testing, monitoring, and troubleshooting.
### Usage with Claude Desktop
#### Option 1: Using uvx (Recommended)
Add this to your `claude_desktop_config.json`:
```json
{
"mcpServers": {
"alphavantage": {
"command": "uvx",
"args": ["alphavantage-mcp"],
"env": {
"ALPHAVANTAGE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
```
#### Option 2: From source
If you cloned the repository, use this configuration:
```json
{
"mcpServers": {
"alphavantage": {
"command": "uv",
"args": [
"--directory",
"<DIRECTORY-OF-CLONED-PROJECT>/alphavantage",
"run",
"alphavantage"
],
"env": {
"ALPHAVANTAGE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
```
#### Running the Server in Streamable HTTP Mode
**Using uvx:**
```json
{
"mcpServers": {
"alphavantage": {
"command": "uvx",
"args": ["alphavantage-mcp", "--server", "http", "--port", "8080"],
"env": {
"ALPHAVANTAGE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
```
**From source:**
```json
{
"mcpServers": {
"alphavantage": {
"command": "uv",
"args": [
"--directory",
"<DIRECTORY-OF-CLONED-PROJECT>/alphavantage",
"run",
"alphavantage",
"--server",
"http",
"--port",
"8080"
],
"env": {
"ALPHAVANTAGE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
```
## 📺 Demo Video
Watch a quick demonstration of the Alpha Vantage MCP Server in action:
[](https://github.com/user-attachments/assets/bc9ecffb-eab6-4a4d-bbf6-9fc8178f15c3)
## 🔧 Development & Publishing
### Publishing to PyPI
This project includes scripts for publishing to PyPI and TestPyPI:
```bash
# Publish to TestPyPI (for testing)
python scripts/publish.py --test
# Publish to PyPI (production)
python scripts/publish.py
# Use uv publish instead of twine
python scripts/publish.py --test --use-uv
```
The script uses `twine` by default (recommended) but can also use `uv publish` with the `--use-uv` flag.
### GitHub Actions
The repository includes a GitHub Actions workflow for automated publishing:
- **Trusted Publishing**: Uses PyPA's official publish action with OpenID Connect
- **Manual Trigger**: Can be triggered manually with options for TestPyPI vs PyPI
- **Twine Fallback**: Supports both trusted publishing and twine-based publishing
To set up publishing:
1. **For Trusted Publishing** (recommended):
- Configure trusted publishing on PyPI/TestPyPI with your GitHub repository
- No secrets needed - uses OpenID Connect
2. **For Token-based Publishing**:
- Add `PYPI_API_TOKEN` and `TEST_PYPI_API_TOKEN` secrets to your repository
- Use the "Use twine" option in the workflow dispatch
## 🤝 Contributing
We welcome contributions from the community! To get started, check out our [contribution](CONTRIBUTING.md) guide for setup instructions,
development tips, and guidelines.