Shinzo

v1.0.0Monitoring & Observabilitystable

Python SDK for MCP server observability, built on OpenTelemetry. Gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. Integrate with any OpenTelemetry ingest service including the Shinzo p

aiai-agentsanalyticsframeworkinfrastructure
Share:
13
Stars
0
Downloads
0
Weekly
0/5

What is Shinzo?

Shinzo is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to python sdk for mcp server observability, built on opentelemetry. gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. integrate with any o...

Python SDK for MCP server observability, built on OpenTelemetry. Gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. Integrate with any OpenTelemetry ingest service including the Shinzo p

This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Python SDK for MCP server observability, built on OpenTeleme

Use Cases

OpenTelemetry-based MCP observability
Analyze agent usage and tool performance
shinzo-labs

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedApr 27, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx shinzo-py

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Shinzo

Shinzo is a Python SDK that adds OpenTelemetry-based observability to MCP servers, giving developers deep insight into how AI agents interact with their tools. By wrapping any FastMCP or standard MCP server with a single function call, it automatically tracks request durations, error rates, tool call arguments, and session correlations. Telemetry can be streamed to the hosted Shinzo platform or any OTLP-compatible backend such as Grafana, Jaeger, or Honeycomb.

Prerequisites

  • Python 3.9 or later
  • An existing MCP server built with FastMCP or the standard MCP Python SDK
  • pip or uv package manager
  • An OTLP-compatible observability backend (optional — defaults to Shinzo's hosted service)
  • An MCP-compatible client such as Claude Desktop or Cursor for testing
1

Install the Shinzo SDK

Install the shinzo package from PyPI using pip or uv. This adds the instrumentation library to your Python environment.

pip install shinzo
2

Instrument your FastMCP server

Import instrument_server from shinzo and call it with your FastMCP instance before defining any tools. The SDK wraps the server transparently and begins collecting telemetry.

from mcp.server.fastmcp import FastMCP
from shinzo import instrument_server

mcp = FastMCP(name="my-mcp-server")
observability = instrument_server(mcp, config={
    "server_name": "my-mcp-server",
    "server_version": "1.0.0",
    "sampling_rate": 1.0,
    "enable_metrics": True,
    "enable_tracing": True,
    "enable_pii_sanitization": True
})

@mcp.tool()
def get_data(query: str) -> str:
    return f"Result for: {query}"
3

Configure a custom OTLP exporter (optional)

If you want to send telemetry to your own backend instead of the Shinzo hosted service, set the exporter_endpoint and authentication in the config dictionary.

observability = instrument_server(mcp, config={
    "server_name": "my-mcp-server",
    "server_version": "1.0.0",
    "exporter_endpoint": "https://your-otlp-endpoint:4318",
    "exporter_auth": {"type": "bearer", "token": "YOUR_TOKEN"},
    "exporter_type": "otlp-http"
})
4

Run your instrumented MCP server

Start your server normally. Shinzo will begin emitting traces and metrics for every tool invocation automatically.

python your_server.py
5

Register with your MCP client

Add the instrumented server to your Claude Desktop or other MCP client configuration as you normally would. Observability is transparent to the client.

{
  "mcpServers": {
    "my-mcp-server": {
      "command": "python",
      "args": ["/path/to/your_server.py"]
    }
  }
}

Shinzo Examples

Client configuration

Example Claude Desktop configuration for an MCP server instrumented with Shinzo.

{
  "mcpServers": {
    "my-mcp-server": {
      "command": "python",
      "args": ["/path/to/your_server.py"],
      "env": {}
    }
  }
}

Prompts to try

After instrumenting your server with Shinzo, use your AI client normally — observability is automatic. These prompts test that your tools are being tracked.

- "Use the get_data tool to fetch results for 'test query' and tell me what you got"
- "Call my tool three times with different inputs so I can see traces in Shinzo"
- "What tools does this MCP server expose?"

Troubleshooting Shinzo

No telemetry appearing in the Shinzo dashboard after instrumentation

Check that instrument_server is called before the MCP server starts handling requests. Also verify the exporter_endpoint is reachable and that enable_tracing is set to True in the config.

PII data appearing in traces despite enable_pii_sanitization being True

The built-in sanitizer covers common patterns (emails, phone numbers, SSNs). For domain-specific sensitive fields, provide a custom pii_sanitizer function in the config that redacts your specific data patterns.

High memory usage when tracing servers with many concurrent requests

Reduce the sampling_rate (e.g., 0.1 for 10% sampling) and increase batch_timeout_ms to batch telemetry more aggressively. Also consider setting enable_argument_collection to False if tool arguments are large.

Frequently Asked Questions about Shinzo

What is Shinzo?

Shinzo is a Model Context Protocol (MCP) server that python sdk for mcp server observability, built on opentelemetry. gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. integrate with any opentelemetry ingest service including the shinzo p It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Shinzo?

Follow the installation instructions on the Shinzo GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Shinzo?

Shinzo works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Shinzo free to use?

Yes, Shinzo is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Monitoring & Observability MCP Servers

Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "shinzo-py": { "command": "npx", "args": ["-y", "shinzo-py"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Shinzo?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides