0CodeKit for AI agents
0CodeKit is a collection of small utility APIs for everyday backend chores: validation, hashing, unit conversion and simple lookups. Developers use it to skip writing boilerplate helper functions. 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 0CodeKit.
Validate an email address
Check whether an address is properly formatted and deliverable before it goes into a signup list or CRM field.
Parse UTM parameters from a link
Pull source, medium and campaign values out of a marketing URL to tag where a lead actually came from.
Check remaining API credits
Look up how many credits are left on the account before kicking off a large batch of lookups.
8 0CodeKit actions, graded by risk.
Every 0CodeKit action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- 0codekit.find_keywordsFind Keywords
- 0codekit.get_remaining_creditsGet Remaining Credits
- 0codekit.calculate_bmiCalculate BMI
- 0codekit.check_weekendCheck Weekend
- 0codekit.validate_emailValidate Email
- 0codekit.convert_nation_isoConvert Nation and ISO Code
- 0codekit.parse_utm_parametersParse UTM Parameters
write
1Create and change things. Allow, or ask the user first.
- 0codekit.hash_messageHash Message
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
0CodeKit in three steps.
- 01Your users connect 0CodeKitThey add their 0CodeKit api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “hash Message” can wait for the user to approve.
- 03Any agent can actYour agent calls 0CodeKit through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('0codekit', { read: 'allow', write: 'ask', // hash_message destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How 0CodeKit connects.
Users add their 0CodeKit 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 0CodeKit 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 0CodeKit from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
0CodeKit and Arc0, answered.
Can I use 0CodeKit with Claude, ChatGPT or Cursor?
Yes. Connect 0CodeKit 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 0CodeKit actions you allow.
How do users connect 0CodeKit?
Users add their 0CodeKit 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 0CodeKit actions can my agent take?
8 in total: 7 read, 1 write and 0 destructive, such as “hash Message”. Your policies decide which of them each agent may call.
Can I make my agent read-only in 0CodeKit?
Yes. Allow read actions and deny writes in the 0CodeKit policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call 0CodeKit too?
Yes. The same 0CodeKit connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug 0CodeKit into your agent.
Your users connect 0CodeKit 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