Payhere for AI agents
PayHere provides simple payment links for accepting online payments without building custom checkout pages. Small businesses use it to collect one-off and recurring payments quickly. 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 Payhere.
Check recent payments read-only
List recent payments to confirm a customer's transaction went through.
Look up active subscriptions
List subscriptions read-only to see which customers are on a recurring plan.
Update a plan with approval
Change a subscription plan's price only after a manager confirms the update.
13 Payhere actions, graded by risk.
Every Payhere action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- payhere.get_userGet User
- payhere.list_hooksList REST Hooks
- payhere.list_plansList Plans
- payhere.list_paymentsList Payments
- payhere.list_customersList Customers
- payhere.list_subscriptionsList subscriptions
- payhere.get_current_companyGet Current Company
- payhere.get_current_company_statsGet Current Company Stats
write
4Create and change things. Allow, or ask the user first.
- payhere.create_hookCreate Hook
- payhere.create_planCreate Plan
- payhere.update_planUpdate Plan
- payhere.update_current_companyUpdate Current Company
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- payhere.delete_hookDelete Hook
Payhere in three steps.
- 01Your users connect PayhereThey add their Payhere api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Hook” can wait for the user, and “delete Hook” can be denied outright.
- 03Any agent can actYour agent calls Payhere through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('payhere', { read: 'allow', write: 'ask', // create_hook destructive: 'deny', // delete_hook }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Payhere connects.
Users add their Payhere 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 Payhere 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 Payhere from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Payhere and Arc0, answered.
Can I use Payhere with Claude, ChatGPT or Cursor?
Yes. Connect Payhere 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 Payhere actions you allow.
How do users connect Payhere?
Users add their Payhere 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 Payhere actions can my agent take?
13 in total: 8 read, 4 write and 1 destructive, such as “create Hook”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Payhere?
Yes. Actions like “delete Hook” 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 Payhere too?
Yes. The same Payhere connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Payhere into your agent.
Your users connect Payhere once, under your brand. Your agent gets 13 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan