Weave MCP Server + Client Linked Traces:
About
# Weave MCP Server + Client Linked Traces: This repo is taken from the example in Arize-ai/phoenix and adapted to export to wandb/weave. Note: There is a race condition which sometimes causes the tool to fail to run at the OpenAI call step. This bug was also present in the original and was not introduced by weave. ##…
Explore
- End-to-end tracing across MCP client and server
- Automatic OpenTelemetry context propagation via openinference-instrumentation-mcp
- Exports traces to wandb/Weave
- Supports multi-language MCP components
- Connects AI models to external data sources
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Weave MCP Server + Client Linked Traces:Command (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
When properly instrumented, trace context is automatically propagated across the MCP client-server boundary, allowing you to:
- Track requests from client to server in a single trace
- Observe latency at different stages of the request lifecycle
- Debug issues that span across service boundaries
First run cp .env.example .env
Follow the instructions and set the relevant keys in your new env file.
- uv: uv sync
- pip: pip install -r requirements.txt
1. Navigate to this directory:
cd tutorials/mcp/tracing_between_mcp_client_and_server
2. Install the required dependencies:
pip install -r requirements.txt
1. Run Phoenix locally, or connect to an instance online
2. Update your .env file with OPENAI_API_KEY, and your PHOENIX_COLLECTOR_ENDPOINT. If you're using an online Phoenix instance or have auth enabled, also set your PHOENIX_API_KEY.
3. Run the MCP client. The client code will spin up the server at run time in a separate process.
python client.py
4. Ask questions of the agent.
5. View the traces in Phoenix:
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"weave mcp server + client linked traces:": {
"weave-mcp-server-client-trace": {
"command": "python",
"args": [
"client.py"
]
}
}
}
}McpServers
{
"weave-mcp-server-client-trace": {
"command": "python",
"args": [
"client.py"
]
}
}Set up your environment:
First run cp .env.example .env
Follow the instructions and set the relevant keys in your new env file.
Install Dependencies:
- uv: uv sync
- pip: pip install -r requirements.txt
Run the client and export traces
- uv: uv run client.py
- python: python client.py
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
