31 lines
566 B
Markdown
31 lines
566 B
Markdown
# Content Extract MCP
|
|
|
|
Python MCP scaffold for article content extraction.
|
|
|
|
## Run
|
|
|
|
```bash
|
|
pip install -e .
|
|
summary-mcp
|
|
```
|
|
|
|
The server exposes two tools:
|
|
|
|
- `extract_url_content`
|
|
- `extract_item_content`
|
|
|
|
Validate an LLM summary result:
|
|
|
|
```bash
|
|
validate-llm-result outputs/result.json --extracted outputs/read-flow-2026.extracted.json
|
|
```
|
|
|
|
Run the minimal extraction-to-summary loop:
|
|
|
|
```bash
|
|
python scripts/run_summary_loop.py ^
|
|
--extracted outputs/read-flow-2026.extracted.json ^
|
|
--prompt outputs/llm-summary-prompt.txt ^
|
|
--output outputs/result.json
|
|
```
|