Ritekit for AI agents
RiteKit provides social media tools for hashtag suggestions, link shortening, email validation, and turning text into shareable images. 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 Ritekit.
Suggest hashtags for a post
Get hashtag suggestions for a caption before it goes out on social media.
Check an email before adding it
Detect whether an email address is disposable or has a typo before adding it to a list.
Confirm before removing a link ad
List existing link ads first, then delete one only after confirming it's no longer running.
14 Ritekit actions, graded by risk.
Every Ritekit 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.
- ritekit.get_client_idRiteKit Get Client ID
- ritekit.list_link_adsList Link Ads
- ritekit.get_access_tokenGet Access Token
- ritekit.get_client_secretRiteKit Get Client Secret
- ritekit.get_full_email_insightsGet Full Email Insights
- ritekit.detect_email_typoDetect Email Typo
- ritekit.detect_disposable_emailDetect Disposable Email
write
6Create and change things. Allow, or ask the user first.
- ritekit.auto_hashtagAuto Hashtag
- ritekit.shorten_linkShorten Link
- ritekit.text_to_imageConvert Text to Image
- ritekit.freemail_detectionFree Email Detection
- ritekit.hashtag_suggestionsRiteKit Hashtag Suggestions
- ritekit.banned_instagram_hashtagsCheck Banned Instagram Hashtags
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- ritekit.link_ad_deleteDelete Link Ad
Ritekit in three steps.
- 01Your users connect RitekitThey add their Ritekit api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “auto Hashtag” can wait for the user, and “delete Link Ad” can be denied outright.
- 03Any agent can actYour agent calls Ritekit through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('ritekit', { read: 'allow', write: 'ask', // auto_hashtag destructive: 'deny', // link_ad_delete }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Ritekit connects.
Users add their Ritekit 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 Ritekit 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 Ritekit from any agent.
Ritekit and Arc0, answered.
Can I use Ritekit with Claude, ChatGPT or Cursor?
Yes. Connect Ritekit 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 Ritekit actions you allow.
How do users connect Ritekit?
Users add their Ritekit 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 Ritekit actions can my agent take?
14 in total: 7 read, 6 write and 1 destructive, such as “auto Hashtag”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Ritekit?
Yes. Actions like “delete Link Ad” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Ritekit too?
Yes. The same Ritekit connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Ritekit into your agent.
Your users connect Ritekit once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan