Network Call Analyzer MCP Server
A Model Context Protocol server that analyzes network traffic for a given URL using Playwright. This server enables LLMs to understand the resources loaded by a webpage.
Available Tools
analyze_network- Analyzes network traffic for a URL using Playwright.url(string, required): URL to analyze.filters(string, optional): Comma-separated list of file extensions or content types to filter out (e.g., css,png,woff).
Prompts
- analyze_network
- Analyze network traffic for a URL.
- Arguments:
url(string, required): URL to analyze.
Installation
Requires Node.js and Playwright to be installed.
- Install Playwright browsers:
playwright install --with-deps chromium # Or: python -m playwright install --with-deps chromium
Using uv (recommended)
When using uv no specific installation is needed. We will
use uvx to directly run network-call-analyzer.
Using PIP
Alternatively you can install network-call-analyzer via pip:
uv pip install .
After installation, you can run it as a script using:
python -m network_call_analyzer_mcp
Configuration
Configure for Claude.app
Add to your Claude settings:
Using uvx
"mcpServers": {
"network_analyzer": {
"command": "uvx",
"args": ["network-call-analyzer"]
}
}
Using docker
"mcpServers": {
"network_analyzer": {
"command": "docker",
"args": ["run", "-i", "--rm", "your-docker-image-name"] # TODO: Update docker image name
}
}
Using pip installation
"mcpServers": {
"network_analyzer": {
"command": "python",
"args": ["-m", "network_call_analyzer_mcp"]
}
}
Debugging
You can use the MCP inspector to debug the server. For uvx installations:
npx @modelcontextprotocol/inspector uvx network-call-analyzer
Or if you've installed the package in a specific directory or are developing on it:
cd path/to/servers/src/network_call_analyzer # Adjust path if needed
npx @modelcontextprotocol/inspector uv run network-call-analyzer
Contributing
We encourage contributions to help expand and improve network-call-analyzer. Whether you want to add new tools, enhance existing functionality, or improve documentation, your input is valuable.
For examples of other MCP servers and implementation patterns, see: https://github.com/modelcontextprotocol/servers
Pull requests are not welcome! This is meant to be a throw away package that it shall work as such
License
network-call-analyzer is licensed under the Better than MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the Better than MIT License. For more details, please see the LICENSE file in the project repository.
Metadata
Release files for network-call-analyzer 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| network_call_analyzer-0.1.0.tar.gz | 6.4 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| network_call_analyzer-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 13.4 kB
Release files / network_call_analyzer-0.1.0.tar.gz
| Download URL | network_call_analyzer-0.1.0.tar.gz |
|---|---|
| Size | 6.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d6ecc87fb01b9fb7ea63270554a6744476bff89b161c6094c18d5272b41f43de
|
|
BLAKE2b-256 checksum How to use checksums |
0a9f526067122f6b04ada75320994168904b9d49b421fb608fbbfefafe1615a0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.5.16
|
Release files / network_call_analyzer-0.1.0-py3-none-any.whl
| Download URL | network_call_analyzer-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c9e2a6f3ebfe036b02b0c1d210d627b2585ffe553190f09d029af2ea3992c9ec
|
|
BLAKE2b-256 checksum How to use checksums |
4fccb51f724581b6eaab180385f8d9f067daaa2895cba6d894278e5988380f75
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.5.16
|
Security for network-call-analyzer 0.1.0
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.