coonet-mcp
MCP server for querying the CooNet Croatian news database. Exposes 8 tools over the Model Context Protocol, allowing any MCP-compatible LLM to search articles, entities, and trends using natural language.
Install
pip install coonet-mcp
Setup
All you need is a PostgreSQL connection string to a CooNet database.
Claude Code
Place .mcp.json at your project root:
{
"mcpServers": {
"coonet": {
"command": "coonet-mcp",
"env": {
"DATABASE_URL": "postgresql+asyncpg://coonet:coonet_dev@localhost:5432/coonet"
}
}
}
}
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"coonet": {
"command": "coonet-mcp",
"env": {
"DATABASE_URL": "postgresql+asyncpg://coonet:coonet_dev@localhost:5432/coonet"
}
}
}
}
With uvx (no install needed)
{
"mcpServers": {
"coonet": {
"command": "uvx",
"args": ["coonet-mcp"],
"env": {
"DATABASE_URL": "postgresql+asyncpg://coonet:coonet_dev@localhost:5432/coonet"
}
}
}
}
Available tools
| Tool | Description |
|---|---|
get_stats() |
Database statistics: total articles, portals, entity count, date range |
list_portals() |
All news portals with IDs and status |
list_categories() |
All distinct article categories |
search_articles(...) |
Keyword search with portal, category, date filters |
get_article(id) |
Full article content by ID with optional NER entities |
get_entity_mentions(...) |
Most frequently mentioned entities (PER/ORG/LOC) |
get_entity_co_occurrences(...) |
Entities that co-occur with a given entity |
get_articles_by_entity(...) |
Articles mentioning a specific entity via NER tags |
Requirements
- Python 3.11+
- A reachable PostgreSQL database with the CooNet schema
Metadata
Release files for coonet-mcp 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 | Actions |
|---|---|---|---|---|
| coonet_mcp-0.1.0.tar.gz | 7.0 kB | Without provenance | Details for coonet_mcp-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| coonet_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for coonet_mcp-0.1.0-py3-none-any.whl |
Total release size: 15.8 kB
Release files / coonet_mcp-0.1.0.tar.gz
| Download URL | coonet_mcp-0.1.0.tar.gz |
|---|---|
| Size | 7.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a52ec40a388db5059374d28fe3e287bde5eac087d0bbff7f25bb9bac65b82db7
|
|
BLAKE2b-256 checksum How to use checksums |
20f2a877b27a89fcdbdf8ac921d6fd06959df565af8b5b09d77d1afed92b6f79
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.7
|
Release files / coonet_mcp-0.1.0-py3-none-any.whl
| Download URL | coonet_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 8.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
95b74117fb6a5f153ec7d0c9436d785698a6bc811f5822ab0d9b0e5a0ee80668
|
|
BLAKE2b-256 checksum How to use checksums |
18503c0de60b282b59275420684e697717aa3c3b3573737a53272db9453acce8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.7
|
Security for coonet-mcp 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.