get_document
Search & retrievalFetches the full cleaned text of one passage by id — the lazy read path.
Search gives the agent metadata; this gives it the text, for exactly the passage it chose. The content is cleaned extraction rather than raw HTML, so there is no navigation, no cookie banner and no footer eating the budget.
Arguments
| Name | Type | Description |
|---|---|---|
idrequired | string | A passage id from a search hit. |
Returns:The cleaned passage text plus its metadata.
Example
Prompt: “Read the tokio documentation page you just found.”
{ "id": "p:8f2c9a" }Over HTTP
The same operation is available as GET /doc/:id for anything that does not speak MCP.
curl -H "x-api-key: $UNLOB_API_KEY" \
"https://api.unlob.com/doc/p:8f2c9a"Setup
One config block gives your client all 11 tools, including this one.
{
"mcpServers": {
"unlob": {
"command": "npx",
"args": ["-y", "@unlob/mcp"],
"env": { "UNLOB_API_KEY": "ulb_your_key_here" }
}
}
}Get a key and connect
10,000 free requests a month. MCP calls bill exactly like HTTP calls — one request each.