Klazify for AI agents
Klazify is a content classification API that categorizes websites, extracts logos and social links, and identifies a site's technology stack. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Klazify.
Categorize a website by topic
Classify a prospect's domain into a topic category to enrich a lead record.
Pull a company's tech stack
Look up the technologies detected on a domain before a sales call, as a read-only lookup.
Find a domain's social profiles
Extract social media links and logo for a company domain to fill out a CRM record.
8 Klazify actions, graded by risk.
Every Klazify action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- klazify.get_tech_stackGet Tech Stack
- klazify.get_domain_logoGet Domain Logo
- klazify.get_company_dataGet Company Data
- klazify.get_domain_expirationGet Domain Expiration
- klazify.get_similar_companiesGet Similar Companies
- klazify.get_social_media_linksGet Social Media Links
write
2Create and change things. Allow, or ask the user first.
- klazify.categorize_urlCategorize URL
- klazify.real_time_categorizationReal Time Categorization
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Klazify in three steps.
- 01Your users connect KlazifyThey add their Klazify api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “categorize URL” can wait for the user to approve.
- 03Any agent can actYour agent calls Klazify through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('klazify', { read: 'allow', write: 'ask', // categorize_url destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Klazify connects.
Users add their Klazify api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Klazify connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Klazify from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Klazify and Arc0, answered.
Can I use Klazify with Claude, ChatGPT or Cursor?
Yes. Connect Klazify to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Klazify actions you allow.
How do users connect Klazify?
Users add their Klazify api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Klazify actions can my agent take?
8 in total: 6 read, 2 write and 0 destructive, such as “categorize URL”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Klazify?
Yes. Allow read actions and deny writes in the Klazify policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Klazify too?
Yes. The same Klazify connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Klazify into your agent.
Your users connect Klazify once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan