TextRazor for AI agents
TextRazor is a natural language processing API that extracts entities, topics, and sentiment from text, used by teams building content analysis into their own tools. 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 TextRazor.
Extract entities from a document
Pull named people, places, and organizations mentioned in a piece of text.
Classify a piece of content
Run text through a classifier to tag its topic or category.
Check account usage
Look up remaining account capacity as a read-only check before a large batch analysis.
6 TextRazor actions, graded by risk.
Every TextRazor action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- textrazor.extract_entitiesExtract Named Entities from Text
write
5Create and change things. Allow, or ask the user first.
- textrazor.account_infoGet Account Information
- textrazor.classify_textClassify Text
- textrazor.dictionary_managerDictionary Manager
- textrazor.custom_classifier_managerManage Custom Classifiers
- textrazor.text_razor_analyze_contentAnalyze Content with TextRazor
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
TextRazor in three steps.
- 01Your users connect TextRazorThey add their TextRazor api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “get Account Information” can wait for the user to approve.
- 03Any agent can actYour agent calls TextRazor through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('textrazor', { read: 'allow', write: 'ask', // account_info destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How TextRazor connects.
Users add their TextRazor 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 TextRazor 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 TextRazor from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
TextRazor and Arc0, answered.
Can I use TextRazor with Claude, ChatGPT or Cursor?
Yes. Connect TextRazor 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 TextRazor actions you allow.
How do users connect TextRazor?
Users add their TextRazor 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 TextRazor actions can my agent take?
6 in total: 1 read, 5 write and 0 destructive, such as “get Account Information”. Your policies decide which of them each agent may call.
Can I make my agent read-only in TextRazor?
Yes. Allow read actions and deny writes in the TextRazor policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call TextRazor too?
Yes. The same TextRazor connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug TextRazor into your agent.
Your users connect TextRazor once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan