# LLM Observability MCP Server

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)

A Model Context Protocol (MCP) server that provides comprehensive LLM observability tools supporting both PostHog and OpenTelemetry backends.

## Overview

This project is an MCP server designed to track and observe Large Language Model (LLM) interactions using both [PostHog's LLM Observability](https://posthog.com/docs/llm-observability) and **OpenTelemetry** for universal observability across any backend that supports OpenTelemetry (Jaeger, New Relic, Grafana, Datadog, Honeycomb, etc.).

The server can be run as a local process communicating over `stdio` or as a remote `http` server, making it compatible with any MCP client, such as AI-powered IDEs (e.g., VS Code with an MCP extension, Cursor) or custom applications.

## Features

- **Dual Backend Support**: Choose between PostHog or OpenTelemetry (or use both)
- **Universal OpenTelemetry**: Works with any OpenTelemetry-compatible backend
- **Comprehensive Metrics**: Request counts, token usage, latency, error rates
- **Distributed Tracing**: Full request lifecycle tracking with spans
- **Flexible Transport**: Run as local `stdio` process or standalone `http` server
- **Dynamic Configuration**: Environment-based configuration for different backends
- **Zero-Code Integration**: Drop-in replacement for existing observability tools

## Installation for Development

Follow these steps to set up the server for local development.

1. **Prerequisites**:
    - Node.js (>=18.x)
    - A [PostHog account](https://posthog.com/) with an API Key and Host URL.

2. **Clone and Install**:

    ```bash
    git clone https://github.com/sfiorini/llm-observability-mcp.git
    cd llm-observability-mcp
    npm install
    ```

3. **Configuration**:
    Create a `.env` file in the root of the project by copying the example file:

    ```bash
    cp .env.example .env
    ```

    Then, edit the `.env` file with your PostHog credentials and desired transport mode.

## Configuration

The server is configured via environment variables.

### PostHog Configuration

| Variable          | Description                                                                 | Default   | Example                               |
| ----------------- | --------------------------------------------------------------------------- | --------- | ------------------------------------- |
| `POSTHOG_API_KEY` | Your PostHog Project API Key (required for PostHog tool)                    | -         | `phc_...`                             |
| `POSTHOG_HOST`    | The URL of your PostHog instance                                            | -         | `https://us.i.posthog.com`            |

### OpenTelemetry Configuration

| Variable                        | Description                                                                 | Default                    | Example                               |
| ------------------------------- | --------------------------------------------------------------------------- | -------------------------- | ------------------------------------- |
| `OTEL_EXPORTER_OTLP_ENDPOINT`   | OpenTelemetry collector endpoint                                            | -                          | `http://localhost:4318`               |
| `OTEL_EXPORTER_OTLP_HEADERS`    | Headers for authentication (comma-separated key=value pairs)                | -                          | `api-key=YOUR_KEY`                    |
| `OTEL_SERVICE_NAME`             | Service name for traces and metrics                                         | `llm-observability-mcp`    | `my-llm-app`                          |
| `OTEL_SERVICE_VERSION`          | Service version                                                             | `1.0.0`                    | `2.1.0`                               |
| `OTEL_ENVIRONMENT`              | Environment name                                                            | `development`              | `production`                          |
| `OTEL_TRACES_SAMPLER_ARG`       | Sampling ratio (0.0-1.0)                                                    | `1.0`                      | `0.1`                                 |
| `OTEL_METRIC_EXPORT_INTERVAL`   | Metrics export interval in milliseconds                                     | `10000`                    | `30000`                               |

### General Configuration

| Variable          | Description                                                                 | Default   | Example                               |
| ----------------- | --------------------------------------------------------------------------- | --------- | ------------------------------------- |
| `TRANSPORT_MODE`  | The transport protocol to use. Can be `http` or `stdio`.                    | `http`    | `stdio`                               |
| `DEBUG`           | Set to `true` to enable detailed debug logging.                             | `false`   | `true`                                |

## Running the Server

You can run the server in two modes:

- **HTTP Mode**: Runs a web server, typically for remote clients or IDEs like Cursor.

    ```bash
    npm run mcp:http
    ```

    The server will start on `http://localhost:3000`.

- **STDIO Mode**: Runs as a command-line process, ideal for local IDE integration where the IDE manages the process lifecycle.

    ```bash
    npm run mcp:stdio
    ```

## Usage

### Connecting to an IDE (VS Code, Cursor, etc.)

You can integrate this tool with any MCP-compatible IDE. Add one of the following configurations to your IDE's MCP settings (e.g., in `.vscode/settings.json` for VS Code or `.kilocode/mcp.json` for a global setup).

#### Option 1: Local Stdio Process (Recommended)

This method lets the IDE manage the server as a local background process. It's efficient and doesn't require a separate terminal.

```json
{
  "mcpServers": {
    "llm-observability-mcp-stdio": {
      "command": "node",
      "args": [
        "/path/to/your/projects/llm-log-mcp-server/dist/index.js"
      ],
      "env": {
        "TRANSPORT_MODE": "stdio",
        "POSTHOG_API_KEY": "phc_...",
        "POSTHOG_HOST": "https://us.i.posthog.com"
      }
    }
  }
}
```

**Note**: Replace `/path/to/your/projects/llm-log-mcp-server` with the absolute path to this project directory.

#### Option 2: Remote HTTP Server

Use this if you prefer to run the server as a standalone process.

1. Run the server in a terminal: `npm run mcp:http`
2. Add the server URL to your IDE's configuration:

```json
{
  "mcpServers": {
    "llm-observability-mcp-sse": {
      "url": "http://localhost:3000/sse"
    }
  }
}
```

#### Automatic Triggering via System Prompt

For IDE extensions that support system prompts, you can instruct the AI to automatically use this MCP tool for every interaction. Add the following to your IDE's system prompt configuration:

```text
Use `capture_llm_observability` MCP.
Make sure to include all parameters and for the `userId`, send `<my_username>`:
userId - The distinct ID of the user
traceId - The trace ID to group AI events
model - The model used (e.g., gpt-4, claude-3, etc.)
provider - The LLM provider (e.g., openai, anthropic, etc.)
input - The input to the LLM (messages, prompt, etc.)
outputChoices - The output from the LLM
inputTokens - The number of tokens in the input
outputTokens - The number of tokens in the output
latency - The latency of the LLM call in seconds
httpStatus - The HTTP status code of the LLM call
baseUrl - The base URL of the LLM API
```

Replace `<my_username>` with a unique identifier for yourself. This ensures that all LLM activity is automatically logged in PostHog without needing to give the command each time.

### Programmatic Usage

You can use an MCP client library to interact with the server programmatically from your own applications.

```typescript
import { McpClient } from '@modelcontextprotocol/sdk/client';

async function main() {
  // Assumes the MCP server is running in HTTP mode
  const client = new McpClient({
    transport: {
      type: 'http',
      url: 'http://localhost:3000/mcp',
    },
  });

  await client.connect();

  const result = await client.useTool('capture_llm_observability', {
    userId: 'user-123',
    model: 'gpt-4',
    provider: 'openai',
    input: 'What is the capital of France?',
    outputChoices: [{ text: 'Paris.' }],
    inputTokens: 8,
    outputTokens: 2,
    latency: 0.5,
  });

  console.log('Tool result:', result);

  await client.disconnect();
}

main().catch(console.error);
```

## Available Tools

### PostHog Tool: `capture_llm_observability`

Captures LLM usage in PostHog for observability, including requests, responses, and performance metrics.

### OpenTelemetry Tool: `capture_llm_observability_opentelemetry`

Captures LLM usage using OpenTelemetry for universal observability across any OpenTelemetry-compatible backend.

### Parameters Comparison

| Parameter       | Type                | Required | Description                                     | PostHog | OpenTelemetry |
| --------------- | ------------------- | -------- | ----------------------------------------------- | ------- | ------------- |
| `userId`        | `string`            | Yes      | The distinct ID of the user.                    | ✅      | ✅            |
| `model`         | `string`            | Yes      | The model used (e.g., `gpt-4`, `claude-3`).     | ✅      | ✅            |
| `provider`      | `string`            | Yes      | The LLM provider (e.g., `openai`, `anthropic`). | ✅      | ✅            |
| `traceId`       | `string`            | No       | The trace ID to group related AI events.        | ✅      | ✅            |
| `input`         | `any`               | No       | The input to the LLM (e.g., messages, prompt).  | ✅      | ✅            |
| `outputChoices` | `any`               | No       | The output choices from the LLM.                | ✅      | ✅            |
| `inputTokens`   | `number`            | No       | The number of tokens in the input.              | ✅      | ✅            |
| `outputTokens`  | `number`            | No       | The number of tokens in the output.             | ✅      | ✅            |
| `latency`       | `number`            | No       | The latency of the LLM call in seconds.         | ✅      | ✅            |
| `httpStatus`    | `number`            | No       | The HTTP status code of the LLM API call.       | ✅      | ✅            |
| `baseUrl`       | `string`            | No       | The base URL of the LLM API.                    | ✅      | ✅            |
| `operationName` | `string`            | No       | The name of the operation being performed.      | ❌      | ✅            |
| `error`         | `string`            | No       | Error message if the request failed.            | ❌      | ✅            |
| `errorType`     | `string`            | No       | Type of error (e.g., rate_limit, timeout).      | ❌      | ✅            |
| `mcpToolsUsed`  | `string[]`          | No       | List of MCP tools used during the request.      | ❌      | ✅            |

## Quick Start with OpenTelemetry

### 1. Choose Your Backend

**For local testing with Jaeger:**

```bash
# Start Jaeger with OTLP support
docker run -d --name jaeger \
  -e COLLECTOR_OTLP_ENABLED=true \
  -p 16686:16686 \
  -p 4318:4318 \
  jaegertracing/all-in-one:latest
```

**For New Relic:**

```bash
export OTEL_EXPORTER_OTLP_ENDPOINT=https://otlp.nr-data.net:4318
export OTEL_EXPORTER_OTLP_HEADERS="api-key=YOUR_LICENSE_KEY"
```

### 2. Configure Environment

```bash
# Copy example configuration
cp .env.example .env

# Edit .env with your backend settings
# For Jaeger:
echo "OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318" >> .env
echo "OTEL_SERVICE_NAME=llm-observability-mcp" >> .env
```

### 3. Start the Server

```bash
npm run mcp:http
# or
npm run mcp:stdio
```

### 4. Test the Integration

```bash
# Test with curl
curl -X POST http://localhost:3000/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "tool": "capture_llm_observability_opentelemetry",
    "arguments": {
      "userId": "test-user",
      "model": "gpt-4",
      "provider": "openai",
      "inputTokens": 100,
      "outputTokens": 50,
      "latency": 1.5,
      "httpStatus": 200,
      "operationName": "test-completion"
    }
  }'
```

## Development

- **Run in dev mode (HTTP)**: `npm run dev:http`
- **Run tests**: `npm test`
- **Lint and format**: `npm run lint` and `npm run format`

## Documentation

- [OpenTelemetry Setup Guide](OPENTELEMETRY.md) - Complete OpenTelemetry configuration
- [Usage Examples](examples/opentelemetry-usage.md) - Practical examples for different backends
- [Environment Configuration](.env.example) - All available configuration options

## License

[MIT License](https://opensource.org/licenses/MIT)