Talonic

What is Talonic?

Talonic is the official Model Context Protocol (MCP) server for extracting structured, schema-validated data from messy documents—PDFs, scans, images, DOCX, spreadsheets, and forms. It provides AI agents with a reliable alternative to raw OCR plus LLM calls, returning JSON with per-field confidence scores and a detected document type.

How to use Talonic?

Install locally in any stdio-compatible MCP client (Claude Desktop, Cursor, Cline, Continue, Cowork) by adding a JSON config with "command": "npx", "args": ["-y", "@talonic/mcp@latest"], and the TALONIC_API_KEY environment variable. For the hosted path (Claude.ai), connect via OAuth at https://mcp.talonic.com/mcp or fall back to an API key in the URL. Get a free API key at https://app.talonic.com (50 extractions/day, no credit card required).

Key features of Talonic

• talonic_extract tool: schema-validated JSON with per-field confidence scores and cost tracking
• talonic_search: conceptual search across documents, fields, sources, and schemas
• talonic_filter: filter documents by extracted field values with smart operator warnings
• talonic_get_document and talonic_to_markdown: fetch full metadata or OCR markdown
• talonic_list_schemas, talonic_save_schema: manage reusable extraction schemas
• talonic_get_balance: read credit balance, burn rate, runway, and tier info
• Two resources: talonic://schemas and talonic://webhooks/reference

Use cases of Talonic

• Extract structured data from invoices, receipts, or contracts into a known schema
• Search across a workspace of documents by conceptual content, not just keywords
• Filter documents by extracted field values (e.g., amount > $500) with schema-aware feedback
• Monitor extraction costs and credit balance before processing large batches

FAQ from Talonic

What makes Talonic different from raw OCR plus an LLM call?

Raw OCR combined with an LLM call produces unreliable results. Talonic returns schema-validated JSON with per-field confidence scores and a detected document type, giving agents structured, validated data.

What runtime does Talonic require?

The local installation uses npx, which requires Node.js. The hosted endpoint works through any MCP-capable client without local dependencies.

Where does my data live?

Documents are processed and stored in your Talonic workspace. The server interacts with the Talonic API and returns data to the client; no data is stored on the client machine.

Which transports and authentication methods are supported?

Local installations use stdio transport; the hosted endpoint uses HTTP with Server-Sent Events (SSE). Authentication can be an API key (for stdio or URL-based hosted) or OAuth via PKCE (for the Claude.ai connector).

Are there any usage limits?

Yes. The free tier allows 50 extractions per day. The talonic_get_balance tool provides credit balance, 30-day burn rate, projected runway, tier, and next-tier-reset timestamp for budget-aware behaviour.