Skip to main content

MCP Test Server

This project is a test server implementation for the Model Context Protocol (MCP). It uses the FastMCP framework to provide basic MCP server functionality.

Available Tools

greet

A function that receives a name and returns a greeting message.

  • name (string, required): The name to greet
    • Returns: A string containing the greeting message

Installation

Using uv (Recommended)

No special installation is required when using uv. You can run mcp-server-testing directly using uvx.

Using PIP

Alternatively, you can install mcp-server-testing using pip:

pip install mcp-server-testing

After installation, you can run the script as follows:

mcp-server-testing

Configuration

Configure for Claude.app

Add to your Claude settings:

Using uvx
{
  "mcpServers": {
    "testing": {
      "command": "uvx",
      "args": ["mcp-server-testing"]
    }
  }
}

Configure for VS Code

For quick installation, use one of the one-click install buttons below...

Install with UV in VS Code

Command Line Options

You can specify the following options when running the server:

  • --sse: Enable SSE transport

    • Choices: on, off
    • Default: off
    • Description: Enables SSE transport when set to "on"
  • --host: Host to bind the server

    • Default: localhost
    • Description: Specifies the host address the server should bind to
  • --port: Port to bind the server

    • Type: Integer
    • Default: 8000
    • Description: Specifies the port number for the server to bind to
  • --log-level: Set the logging level

    • Choices: debug, info, warning, error

    • Default: info

    • Description:

      • debug: Detailed debugging information
      • info: General runtime information (default)
      • warning: Potential issues that do not affect execution
      • error: Errors that occur during execution

Development

This project serves as a basic implementation example of an MCP server. To add new features, implement them in server.py.

During development, you can test your scripts with the following commands:

uv pip install -e .
mcp-server-testing

Metadata

Release files for mcp-server-testing 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp-server-testing 0.2.0
File Size Uploaded Provenance
mcp_server_testing-0.2.0.tar.gz 26.3 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for mcp-server-testing 0.2.0
File Interpreter ABI Platform
mcp_server_testing-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 30.4 kB

Release files / mcp_server_testing-0.2.0.tar.gz

Download URL mcp_server_testing-0.2.0.tar.gz
Size 26.3 kB
Tags Source
SHA-256 checksum
How to use checksums
f7814cf5e4555840c7e099dc291cee8887e7d72535f834a37d45f0e8ea4410f4
BLAKE2b-256 checksum
How to use checksums
0c96b19c6edb122e6f58ceac3c4919a6e3e953380f0183ef4fd453b92f61a3cb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via python-httpx/0.28.1

Release files / mcp_server_testing-0.2.0-py3-none-any.whl

Download URL mcp_server_testing-0.2.0-py3-none-any.whl
Size 4.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c841bf2c2b7336068d06fa8a963ba82bc42f34798f23ede3d0a57e2eccff7b72
BLAKE2b-256 checksum
How to use checksums
c3d636c77bb95e2476b0c27b1a9cbfaa58598b923e8aa795df647bb7d60b377a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via python-httpx/0.28.1

Security for mcp-server-testing 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page