@sifter-ai
基本情報
Sifter extracts structured, typed records from your documents (PDFs, scans, contracts, invoices) using a natural-language field spec, then lets an agent query and aggregate them — exact counts, sums, filters, with citations back to the source page. Unlike RAG, it answers collecti
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"sifter": {
"command": "uvx",
"args": [
"sifter-mcp",
"--base-url",
"https://api.sifter.run/api"
],
"env": {
"SIFTER_API_KEY": "sk-..."
}
}
}
}List sifts with their name, instructions, and document/record counts. Args: limit: Maximum number of sifts to return (default 50, max 200) offset: Number of sifts to skip for pagination
Get sift metadata and inferred extraction schema for a specific sift.
Get extracted records from a sift. Args: sift_id: The sift identifier limit: Maximum number of records to return (default 20, max 100) offset: Number of records to skip (ignored when cursor is provided) cursor: Opaque pagination cursor from a previous call's next_cursor field
Run a natural language query over a sift's extracted records. Args: sift_id: The sift identifier natural_language: The question to answer (e.g. "What is the total by client?")
List folders with their name and document count. Args: limit: Maximum number of folders to return (default 100, max 200) offset: Number of folders to skip for pagination
Get folder metadata, linked sifts, and document list for a specific folder. Args: folder_path: Folder path (e.g. '/invoices/2025')
Get per-field citation map for a record (page, bbox, source text for each field). Args: sift_id: The sift identifier record_id: The record identifier
Create a new sift with the given extraction instructions. Args: name: Human-readable sift name instructions: Natural language extraction instructions (e.g. "client, date, total") folder_path: Optional folder path to link (e.g. '/invoices/2025'); created if it doesn't exist
Update an existing sift's name or instructions. Args: sift_id: The sift identifier name: New name (leave empty to keep current) instructions: New instructions (leave empty to keep current)
Delete a sift and all its records. Args: sift_id: The sift identifier
Upload a document to a folder. The folder is created if it doesn't exist. The document will be processed by all sifts linked to the folder. Args: folder_path: Target folder path (e.g. '/invoices/2025'). Created if it doesn't exist. filename: Original filename (used for display) content_base64: Base64-encoded file bytes
Enqueue extraction for a document on a specific sift. Args: document_id: The document identifier sift_id: The sift to extract with
Check extraction status for a document on a sift. Args: document_id: The document identifier sift_id: The sift identifier Returns: {"status": "queued|running|completed|failed", "error": "..." (on failure)}
Filter records with structured criteria (no LLM roundtrip). Args: sift_id: The sift identifier filter: Mongo-subset filter dict e.g. {"total": {"$gt": 1000}} sort: Optional sort spec e.g. [["date", -1]] limit: Max records to return (default 50) cursor: Opaque pagination cursor from a previous call Returns: {"records": [...], "next_cursor": "..." | null}
Run a MongoDB aggregation pipeline against a sift's records. Args: sift_id: The sift identifier pipeline: MongoDB aggregation pipeline stages e.g. [{"$group": {"_id": "$client", "total": {"$sum": "$total"}}}] Returns: Array of aggregated rows
Sifter is an MCP server that converts a folder of documents into a queryable database of typed records. It extracts structured data (e.g., from invoices, contracts, receipts) using natural language schema definitions, then enables agents to query and aggregate over the entire collection with every value cited back to its source document, page, and bounding box.
Connect via an MCP client configuration: remote (hosted endpoint with Bearer API key) or local (self-hosted using uvx sifter-mcp and docker compose up -d). Once connected, use the server’s tools to create a sift (define extraction fields in plain language), upload documents (PDFs, scans, images, etc.), and then list, filter, or aggregate records with full citations.
RAG excels at finding passages but cannot answer aggregations like counts, sums, or group-bys across a document collection. Sifter extracts every document into typed records so you can query the whole set and get exact, traceable answers.
You need Docker (to run
MCP server for working with PDF files
A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.
Blazing-fast, asynchronous MCP server for seamless filesystem operations.
Storacha MCP storage server - self-sovereign data for your AI applications.
A Box model context protocol server to search, read and access files
コメント