Customgpt for AI agents
CustomGPT.ai builds AI chatbots trained on a business's own content, letting a company deploy an assistant that answers from its own documents. 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 Customgpt.
Send a message to a project's agent
Send a message to a project's chatbot and get back an answer grounded in its sources.
Check a message's trust score
Check a response's trust score before relying on it for a customer-facing answer.
Confirm before deleting a source
Confirm before deleting a source document, since the agent's answers relying on it would change.
40 Customgpt actions, graded by risk.
Every Customgpt action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
23Look things up. Allowed by default.
- customgpt.get_statsGet Agent Statistics
- customgpt.list_pagesList Agent Documents
- customgpt.get_messageGet Message
- customgpt.get_pluginsGet Agent Plugins
- customgpt.get_projectGet CustomGPT Project
- customgpt.list_sourcesList Agent Sources
- customgpt.list_personasList Persona Versions
- customgpt.list_projectsList CustomGPT Projects
- customgpt.get_usage_limitsGet Usage Limits
- customgpt.get_user_profileGet Current User Profile
- customgpt.get_page_metadataGet Page Metadata
- customgpt.get_report_trafficGet Traffic Analytics Report
- customgpt.get_project_licenseGet Project License
- customgpt.get_report_analysisGet Analytics Chart Data
- customgpt.search_team_membersSearch Team Members
- customgpt.get_project_settingsGet Project Settings
write
13Create and change things. Allow, or ask the user first.
- customgpt.add_sourceAdd Source to Project
- customgpt.update_sourceUpdate Source Settings
- customgpt.create_projectCreate CustomGPT Project
- customgpt.update_projectUpdate Project
- customgpt.create_conversationCreate Conversation
- customgpt.update_user_profileUpdate User Profile
- customgpt.update_page_metadataUpdate Page Metadata
- customgpt.update_project_licenseUpdate Project License
- customgpt.update_project_settingsUpdate Project Settings
- customgpt.reindex_pageReindex Page
- customgpt.clone_projectClone CustomGPT Project
- customgpt.submit_message_feedbackSubmit Message Feedback
- customgpt.activate_persona_versionActivate Persona Version
destructive
4Delete, cancel or archive. Ask first, or deny outright.
- customgpt.delete_pageDelete Page from Agent
- customgpt.delete_sourceDelete CustomGPT Source
- customgpt.delete_projectDelete CustomGPT Project
- customgpt.delete_project_licenseDelete CustomGPT Project License
Customgpt in three steps.
- 01Your users connect CustomgptThey add their Customgpt api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create CustomGPT Project” can wait for the user, and “delete Page from Agent” can be denied outright.
- 03Any agent can actYour agent calls Customgpt through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('customgpt', { read: 'allow', write: 'ask', // create_project destructive: 'deny', // delete_page }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Customgpt connects.
Users add their Customgpt 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 Customgpt 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 Customgpt from any agent.
Customgpt and Arc0, answered.
Can I use Customgpt with Claude, ChatGPT or Cursor?
Yes. Connect Customgpt 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 Customgpt actions you allow.
How do users connect Customgpt?
Users add their Customgpt 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 Customgpt actions can my agent take?
40 in total: 23 read, 13 write and 4 destructive, such as “create CustomGPT Project”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Customgpt?
Yes. Actions like “delete Page from Agent” 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 Customgpt too?
Yes. The same Customgpt connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Customgpt into your agent.
Your users connect Customgpt once, under your brand. Your agent gets 40 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan