Standard Metrics MCP Server

Standard Metrics MCP Server

Connects AI clients to the Standard Metrics API for automated analysis of venture capital portfolio data. It enables users to query financial metrics, track company performance, and generate comprehensive reports using natural language.

Category
访问服务器

README

Standard Metrics MCP Server

A Model Context Protocol (MCP) server that connects Claude Desktop and other MCP-compatible clients to the Standard Metrics API, enabling AI-powered analysis of your venture capital portfolio data.

What This Does

This MCP server allows Claude to directly access your Standard Metrics data to:

  • Analyze Portfolio Performance: Get comprehensive overviews of all your portfolio companies
  • Query Financial Metrics: Access revenue, growth, burn rate, and other key metrics
  • Search and Filter: Find companies by sector, performance, or custom criteria
  • Generate Reports: Create detailed financial summaries and performance analyses
  • Track Trends: Monitor metrics over time with historical data analysis

Installation

1. Get Your Standard Metrics OAuth2 Credentials

  1. Log into your Standard Metrics account
  2. On the left hand menu, click on Settings
  3. Click on Developer Settings
  4. Click "Add Application" in the top right
  5. Fill in the application name and description
  6. Click "Create Application"
  7. Copy your Client ID and Client Secret and store them securely (you won't be able to see the secret again!)

2. Install via Claude Desktop

Add the following to your Claude Desktop MCP configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

First, find your uvx path by running which uvx in your terminal, then use that path in the config:

{
  "mcpServers": {
    "standard-metrics": {
      "command": "/path/to/uvx",
      "args": ["smx-mcp"],
      "env": {
        "SMX_CLIENT_ID": "your_client_id_here",
        "SMX_CLIENT_SECRET": "your_client_secret_here"
      }
    }
  }
}

Replace /path/to/uvx with the result from which uvx and replace your_client_id_here and your_client_secret_here with your actual OAuth2 credentials.

Prerequisites

If you don't have it installed already, you'll need to install the uv Python package manager first:

macOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

3. Restart Claude Desktop

Close and reopen Claude Desktop. You should see "Standard Metrics" appear in your MCP connections.

Usage Examples

Once installed, you can ask Claude to analyze your portfolio data:

Portfolio Overview

Show me a summary of my entire portfolio performance

Company Analysis

What are the key metrics for Acme Corp over the last 12 months?

Sector Comparison

Compare the revenue growth of all my SaaS companies

Financial Deep Dive

Create a financial summary for company ID abc123 including burn rate and runway

Custom Queries

Find all companies with revenue growth above 50% and show their latest metrics

Available Data

The MCP server provides access to:

Data Type Description
Companies Portfolio company information and details
Financial Metrics Revenue, expenses, growth rates, burn rate
Budgets & Forecasts Budget data and financial projections
Custom Columns Your firm's custom data columns
Documents Uploaded reports and financial documents
Notes Internal notes and commentary
Fund Data Fund-level information
Information Requests Data collection requests sent to companies
Information Reports Responses to information requests
Users Team members in your firm

Alternative Installation Methods

Using Docker

{
  "mcpServers": {
    "standard-metrics": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "-e", "SMX_CLIENT_ID=your_client_id_here",
        "-e", "SMX_CLIENT_SECRET=your_client_secret_here",
        "-p", "8000:8000",
        "quaestorapp/smx-mcp:latest"
      ]
    }
  }
}

Local Development

git clone https://github.com/Quaestor-Technologies/smx-mcp
cd smx-mcp
uv sync

Then use the local path in your Claude Desktop config:

{
  "mcpServers": {
    "standard-metrics": {
      "command": "uv",
      "args": ["run", "python", "-m", "src.server"],
      "env": {
        "SMX_CLIENT_ID": "your_client_id_here",
        "SMX_CLIENT_SECRET": "your_client_secret_here"
      }
    }
  }
}

Running with Docker

1. Run with the Hosted Image (Recommended)

You can use the prebuilt image from Docker Hub for the fastest setup:

docker run --rm -it \
  -e SMX_CLIENT_ID=your_client_id_here \
  -e SMX_CLIENT_SECRET=your_client_secret_here \
  -p 8000:8000 \
  quaestorapp/smx-mcp:latest
  • Replace your_client_id_here and your_client_secret_here with your actual Standard Metrics OAuth2 credentials.
  • The server will be available at http://localhost:8000.

2. Build and Run Locally

If you want to build the image yourself (for development or customization):

# Build the Docker image
docker build -t smx-mcp .

# Run the container
docker run --rm -it \
  -e SMX_CLIENT_ID=your_client_id_here \
  -e SMX_CLIENT_SECRET=your_client_secret_here \
  -p 8000:8000 \
  smx-mcp
  • Again, replace the environment variables with your credentials.

3. Using Docker in Claude Desktop

Add this to your Claude Desktop MCP config to use the Docker image:

{
  "mcpServers": {
    "standard-metrics": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "-e", "SMX_CLIENT_ID=your_client_id_here",
        "-e", "SMX_CLIENT_SECRET=your_client_secret_here",
        "-p", "8000:8000",
        "quaestorapp/smx-mcp:latest"
      ]
    }
  }
}

Tip:

  • The hosted image is updated automatically with every release.
  • For local development, you can mount your code into the container with -v $(pwd)/src:/app/src if you want live code reloads.

Troubleshooting

"Connection Failed" Error

  • Verify your Client ID and Client Secret are correct
  • Ensure your OAuth2 application is active in Standard Metrics
  • Check that Claude Desktop has been restarted after configuration

"No Data Found" Error

  • Confirm your Standard Metrics account has portfolio data
  • Verify your OAuth2 application has the necessary permissions
  • Try a simpler query first: "List my companies"

Authentication Issues

  • Double-check your credentials haven't expired
  • Ensure there are no extra spaces in your configuration
  • Try regenerating your OAuth2 credentials if needed

Available Tools

Companies

list_companies - List all companies associated with your firm

  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

get_company - Get a specific company by ID

  • company_id: The unique identifier for the company (string, required)

search_companies - Search companies by various criteria

  • name_contains: Filter companies containing this text in their name (string, optional)
  • sector: Filter companies by sector (string, optional)
  • city: Filter companies by city (string, optional)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

Financial Metrics

get_company_metrics - Get metrics for a specific company

  • company_id: The unique identifier for the company (string, required)
  • from_date: Start date for metrics (YYYY-MM-DD format) (date, optional)
  • to_date: End date for metrics (YYYY-MM-DD format) (date, optional)
  • category: Filter by metric category (string, optional)
  • cadence: Filter by metric cadence (daily, monthly, etc.) (string, optional)
  • include_budgets: Include budget metrics in results (boolean, optional, default: false)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

get_metrics_options - Get available metric categories and options

  • category_name: Filter by specific category name (string, optional)
  • is_standard: Filter by standard vs custom metrics (boolean, optional)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

get_company_recent_metrics - Get the most recent metrics for a company

  • company_id: The unique identifier for the company (string, required)
  • category: Filter by specific metric category (string, optional)
  • limit: Maximum number of recent metrics to return (number, optional, default: 10)

Portfolio Analysis

get_portfolio_summary - Get a comprehensive portfolio summary including companies, funds, and key metrics

  • company_ids: Specific company IDs to include (array of strings, optional, if None includes all companies)
  • max_companies: Maximum number of companies to include metrics for (number, optional, if None includes all)
  • include_metrics: Whether to fetch metrics for each company (boolean, optional, default: true)
  • metrics_per_company: Number of recent metrics to fetch per company (number, optional, default: 50)

get_company_performance - Get comprehensive performance data for a specific company

  • company_id: The unique identifier for the company (string, required)
  • months: Number of months of historical data to include (number, optional, default: 12)

get_company_financial_summary - Get a financial summary for a company including key metrics over time

  • company_id: The unique identifier for the company (string, required)
  • months: Number of months of historical data to include (number, optional, default: 12)

Budgets & Forecasts

list_budgets - List all budgets associated with your firm

  • company_slug: Filter by company slug (string, optional)
  • company_id: Filter by company ID (string, optional)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

Custom Data

get_custom_columns - Get custom column data for companies

  • company_slug: Filter by company slug (string, optional)
  • company_id: Filter by company ID (string, optional)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

get_custom_column_options - Get all custom columns and their available options

  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

Documents

list_documents - List all documents associated with your firm

  • company_id: Filter by company ID (string, optional)
  • parse_state: Filter by document parse state (string, optional)
  • from_date: Filter documents from this date (YYYY-MM-DD format) (date, optional)
  • to_date: Filter documents to this date (YYYY-MM-DD format) (date, optional)
  • source: Filter by document source (string, optional)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

Funds

list_funds - List all funds associated with the firm

  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

Information Requests & Reports

list_information_requests - List all information requests associated with the firm

  • name: Filter by request name (string, optional)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

list_information_reports - List all information reports associated with the firm

  • company_id: Filter by company ID (string, optional)
  • information_request_id: Filter by information request ID (string, optional)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

Notes

list_notes - List all notes associated with a specific company

  • company_slug: Filter by company slug (string, optional)
  • company_id: Filter by company ID (string, optional)
  • sort_by: Sort notes by specific field (string, optional)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

get_company_notes_summary - Get a summary of notes for a company

  • company_id: The unique identifier for the company (string, required)
  • recent_notes_limit: The number of recent notes to return (number, optional, default: 5, max: 100)

Users

list_users - List all users associated with your firm

  • email: Filter by user email (string, optional)
  • page: Page number for pagination (number, optional, default: 1)
  • per_page: Results per page (number, optional, default: 100, max: 100)

Support

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选