# Textrawl MCP server

> Turn documents into agent memory with hybrid semantic and keyword search over emails, PDFs, notes, and past conversations.

- Repository: https://github.com/jeffgreendesign/textrawl
- Page: https://hostedmcp.org/servers/jeffgreendesign/textrawl
- Transport: —
- Stars: 6
- License: MIT

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `EMBEDDING_PROVIDER` | no | no |  |
| `GCP_PROJECT_ID` | no | no |  |
| `OLLAMA_BASE_URL` | no | no |  |
| `OLLAMA_MODEL` | no | no |  |

## Tools (28)

- `full`
- `legacy`
- `capture`
- `remember`
- `search`
- `get_document`
- `list_documents`
- `update_document`
- `add_note`
- `remember_fact`
- `build_knowledge`
- `query_memory`
- `relate_entities`
- `forget_entity`
- `extract_memories`
- `save_conversation_context`
- `query_conversations`
- `delete_conversation`
- `get_insights`
- `discover_connections`
- `dismiss_insight`
- `ask`
- `daily_briefing`
- `save_url`
- `timeline`
- `pg_analyze`
- `pg_recommendations`
- `pg_report_history`

## FAQ

### Can I run Textrawl locally for better privacy?

Yes, you can run it locally using Ollama and a local PostgreSQL database to keep your document text and embeddings on your machine.

### How does the search functionality work?

Textrawl uses hybrid search, combining vector similarity with traditional keyword matching using Reciprocal Rank Fusion to ensure relevant results.
