Claix 推出文档处理安全层：AI Agent 读取文件前先拦截恶意内容

• Invisible to end users

  Your customer sees your brand, logo, and product. Claix never appears in the UI. Behind the scenes, our intelligent AI mapping engine does the heavy lifting.

• API-first by design

  REST for backends and microservices, A2A (Agent-to-Agent) when you orchestrate autonomous agents, and MCP for IDEs. No mandatory SDKs—integrate into your product stack, CRM, ERP, automation, or agents via HTTP, JSON-RPC, or MCP tools.

• MCP server for IDEs and agents

  Connect Claix to Cursor, Claude Desktop, or Windsurf in one click. Process PDFs and spreadsheets from your IDE—or from the agents and tools you already run—via our MCP protocol.

  View MCP documentation →MCP article →

• A2A agent (Agent-to-Agent)

  Claix is also a native A2A agent: peers discover it via Agent Card and invoke 20+ extraction and document-query skills over JSON-RPC. Prefer REST for your backend? It stays available unchanged.

  View A2A documentation →A2A article →

• Secure infrastructure in Stockholm

  Data hosted in the EU, with encryption in transit and at rest, API Key authentication and multi-tenant isolation.

• Zero maintenance for you

  We manage the AI engine, semantic mapping, and scaling. You focus on selling your product—not maintaining data pipelines.

• Full privacy control. Zero AI training.

  You decide how much we remember. Neither Claix nor our providers use your confidential documents to train models. Keep absolute control over your data by choosing instant deletion (total destruction after processing), temporary mode (memory retained per session), or persistent mode (encrypted context exclusive to your organization).

• Clean ID-based architecture

  Drop spaghetti code and unstable prompts. Create and manage extraction structures via API, all centralized under a unique identifier (schema_id). Your database and business logic stay clean.

  See schema management →

• Before processing

  Claix Trust

  Claix Trust verifies files before ingestion, helping block malicious content and unsafe instructions before they reach document processing, RAG memory or AI agents.

• Field citations

  Source Tracing

  Grounded extraction: each field can return { value, source } pointing to a page, cell, or fragment—not a generic badge. That is explainable AI extraction your backend, audit trail, or agent can actually check.

• Typed contract

  Guaranteed schema

  The payload still conforms to your schema. Typed JSON is the contract; Source Tracing is the evidence layer on top. Grounded AI output does not mean a looser structure.

• Human-in-the-loop

  requires_human_revision

  When anchoring fails, Claix does not invent a citation. source is requires_human_revision so human-in-the-loop AI validation can take over. That reduces AI hallucination risk instead of hiding a weak AI confidence score.

1. Step 01 · Onboarding and instant API Key

   Frictionless onboarding

   Free signup with 100 successful processing calls included. Generate your server API key in seconds and start integrating—no credit card and no OCR or embeddings infrastructure to deploy.

2. Step 02 · REST connection or A2A protocol

   REST integration and A2A protocol

   Inject HTTP endpoints into your microservices, n8n, or Make with standard headers (x-api-key). In multi-agent architectures, you can also interact natively through the Agent-to-Agent (A2A) protocol with Agent Card discovery and task delegation.

3. Step 03 · Deterministic extraction against schema

   Typed extraction against schema

   Claix processes scanned PDFs, Excel workbooks, Word files, or images with multimodal vision. Data is transformed deterministically into the requested JSON Schema. Fields without evidence stay null—reducing AI hallucination risk instead of inventing a number.

4. Step 04 · Document memory and Knowledge Spaces

   Persistence and Knowledge Spaces

   Associate processed documents with a shared space_id. Your backend, automation, or agent can query individual files by document_id or run cross-document queries across the whole space to compare, sum, and reconcile data across multiple files in a single call.

5. Step 05 · Scale without tech debt

   Scaling and multi-tenant isolation

   Strict logical isolation by space and account to guarantee privacy and GDPR compliance. Cut prompt token consumption by more than 80%, drop fragile RAG pipeline maintenance, and ship to production faster—with or without agents.

200 OK → charged401 / 403 → free400 / 422 → free5xx → free

PAY PER USE

Per successful call. Scale when you need to.

100 successful calls free — plenty of room to integrate Claix into your stack without spending a cent.

Excel → JSON

Start Now

ENTERPRISE

For teams that need a tailored rollout.

• Self Hosted
• MSA and SLA
• Dedicated On-Call Support
• Custom Pricing