djinsight
Track page views. Query with AI.
Your Django app's analytics, exposed to Claude and AI agents via MCP.
The Problem
You want page view analytics. But you also want Claude to answer questions like:
"What are my top 5 articles this week?"
Most analytics packages don't talk to AI. djinsight does.
Installation
pip install djinsight
Add to settings.py:
INSTALLED_APPS += ['djinsight']
DJINSIGHT = {
'ENABLE_TRACKING': True,
'USE_REDIS': False,
'USE_CELERY': False,
}
Run migrations:
python manage.py migrate
Add URLs to urls.py:
urlpatterns = [
path('djinsight/', include('djinsight.urls')),
]
Done.
Usage
Track a page
Add to any template:
{% load djinsight_tags %}
{% track %}
That's it. Views are now tracked.
Display stats
{% stats metric="views" period="week" %}
{% stats metric="views" period="week" output="chart" %}
Connect to Claude
- Install with MCP support:
pip install djinsight[mcp]
- Add to Claude Desktop config (
~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"djinsight": {
"command": "python",
"args": ["-m", "djinsight.mcp"],
"env": {
"DJANGO_SETTINGS_MODULE": "your_project.settings"
}
}
}
}
- Restart Claude Desktop.
13 tools available:
- Basic:
get_page_stats,get_top_pages,list_tracked_models - Periods:
get_period_stats,compare_periods - Trends:
get_trending_pages - Referrers:
get_referrer_stats,get_traffic_sources - Behavior:
get_device_breakdown,get_hourly_pattern - Cross-model:
get_site_overview,compare_content_types - Search:
search_pages
Now Claude can answer:
- "What are my top 10 pages this week?"
- "Where does my traffic come from?"
- "Which pages are trending up?"
- "Compare mobile vs desktop traffic"
High Traffic?
Use Redis + Celery for async processing:
DJINSIGHT = {
'ENABLE_TRACKING': True,
'USE_REDIS': True,
'USE_CELERY': True,
'REDIS_HOST': 'localhost',
}
Start Celery:
celery -A your_project worker -l info
celery -A your_project beat -l info
Stats Tag Options
{% stats metric="views" period="week" output="chart" chart_type="line" %}
| Parameter | Options |
|---|---|
metric |
views, unique_views |
period |
today, week, month, year, total |
output |
text, chart, json, badge |
chart_type |
line, bar |
Custom Backends
Swap any component:
DJINSIGHT = {
'PROVIDER_CLASS': 'myapp.providers.CustomProvider',
'WIDGET_RENDERER': 'myapp.renderers.CustomRenderer',
}
License
MIT
Links
Sponsors
Metadata
Release files for djinsight 0.4.2
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 | Actions |
|---|---|---|---|---|
| djinsight-0.4.2.tar.gz | 172.7 kB | Without provenance | Details for djinsight-0.4.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| djinsight-0.4.2-py3-none-any.whl | Python 3 | none | any | Details for djinsight-0.4.2-py3-none-any.whl |
Total release size: 338.6 kB
Release files / djinsight-0.4.2.tar.gz
| Download URL | djinsight-0.4.2.tar.gz |
|---|---|
| Size | 172.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0d0db094071ac4f78ad051976f4382f8a1135b44bfedc2022d446e66c3a65967
|
|
BLAKE2b-256 checksum How to use checksums |
2dc3e2079be997ae87fb5ade0cd4276c56c8f1984b73ad75517609abb472f14d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
Release files / djinsight-0.4.2-py3-none-any.whl
| Download URL | djinsight-0.4.2-py3-none-any.whl |
|---|---|
| Size | 165.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
68cf4b8a92aaaee63cf15653112a0531949c992753a2c1eba1fa2df7784e91ad
|
|
BLAKE2b-256 checksum How to use checksums |
fd0b0041127800d2beeb70b53faa93433d4b1c58e116738db7ba969d4fb73482
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
Security for djinsight 0.4.2
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.