---
name: iblai-connect-temenos
description: "Read and write Temenos Transact data through the Temenos Core Banking (Transact) APIs and expose it to an ibl.ai agent as an MCP tool. Use when the user asks an agent to work with Temenos Transact data, or to set up a Temenos Transact MCP connection on ibl.ai."
metadata:
  kind: guide
---

# Temenos Transact connector for AI agents

> A starting point maintained on ibl.ai at https://ibl.ai/developer/connectors/temenos — not part of the iblai/vibe repository. Checked against Temenos' documentation on October 20, 2026; test it against your own Temenos Transact setup before you rely on it.

Temenos Transact, presented on the developer portal as Temenos Core Banking, is a core banking system used by over 1,000 banks across retail, corporate, treasury, wealth and payments. Holds customers, accounts, deposits, loans and orders.

## Auth & conventions

- **API:** Temenos Core Banking (Transact) APIs (REST). REST/JSON APIs grouped into Holdings, Order, Party, Product, Reference, Enterprise, Meta, Settings and System domains, with paths such as api/v1.0.0/holdings/... A Postman collection is published.
- **Access:** Issued by your administrator. Free sandbox after registering with the Temenos Basecamp community; customers and partners use Temenos credentials. Production APIs run on the bank's own Transact deployment (SaaS, cloud or on-premise).
- **Auth:** API key (sandbox). Sandbox calls use a key from the portal's My API Key page, valid 30 days and regenerable at any time. Production authentication is set by the bank's deployment and is not described on public pages.
- Keep Temenos Transact credentials in environment variables or the ibl.ai credential store. Never print a token in chat and never commit one to a file.
- Destructive or outward-facing calls are marked **Confirm with the user first** — do.

## Reads

- **Customers** — Party domain: customers, beneficiaries, contact details and KYC data.
- **Accounts and arrangements** — Holdings domain: accounts, deposits, loans and other arrangements.
- **Orders** — Order domain: payments, transfers, standing instructions and other order instructions.
- **Products and pricing** — Product domain: product catalog, pricing and interest conditions.
- **Reference data** — Reference domain: currencies, countries, bank codes and transaction codes.

## Writes

- **Create customer** — Party APIs create a customer record (shown in the sandbox guide).
- **Open account or loan** — Holdings APIs create current, deposit and loan accounts. **Confirm with the user first.**
- **Payment orders** — Order APIs submit payments and fund transfers. **Confirm with the user first.**

## Expose it to an ibl.ai agent (MCP)

Temenos did not publish an MCP server of its own when this skill was checked. Host a small MCP server that wraps the calls above, then register it below.

First install the ibl.ai platform skills and connect your organization (writes `IBLAI_ORG`, `IBLAI_USERNAME` and `IBLAI_API_KEY` to `.env`):

```bash
npx skills add iblai/vibe --all
# then, in your coding agent:
/iblai-api-login
```

Every call below sends `Authorization: Api-Token $IBLAI_API_KEY`.

1. **Register the server** — `POST https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/mcp-servers/` with `name`, `url`, `transport` (`sse` | `websocket` | `streamable_http`) and `auth_type` (`none` | `token` | `oauth2`). Capture the returned `id`.
   - For an API key or service credential use `auth_type=token` with `auth_scope=platform` for one key across the organization, or scope it to a single agent for one key per agent.
2. **Create the connection** — `POST https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/mcp-server-connections/` with `server`, `scope` (`platform` | `mentor` | `user`), `auth_type`, and either `credentials` + `authorization_scheme` or a `connected_service` id for OAuth. Credentials are masked on read; never send a masked value back.
3. **Enable it on the agent** — `GET https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/mentors/{agent_id}/settings/`, add `mcp-tool` to `tool_slugs` and the server id to `mcp_servers`, then `PATCH` the full lists back. They are replaced, not merged.

Full reference: https://ibl.ai/developer/platform/mcp/mcp-connections and the `/iblai-api-agent-mcp` skill.

## Example prompts

- "Fetch the customer record and KYC status for customer 100345"
- "List all loan arrangements for this customer with outstanding balances"
- "Show the interest conditions on our standard savings product"
- "Create a current account for this new customer in the sandbox"

## Guardrails

- Customer, KYC and account data are GLBA nonpublic personal information for U.S. banks (personal data under local law elsewhere). Card APIs, where used, carry PCI cardholder data.
- Request the narrowest Temenos Transact scopes or role the task needs, and prefer a read-only credential for agents that only answer questions.
- Return the fields the user asked for, not whole records; do not paste personal data into chat that the user did not request.
- Before any write, show the user exactly what will change and wait for a yes.
- Page through large result sets and back off on rate-limit responses instead of retrying in a loop.

## References

- Temenos Developer Portal: https://developer.temenos.com/
- Temenos Core Banking (Transact) APIs: https://developer.temenos.com/transact-apis
- API Sandbox quick guide: https://developer.temenos.com/article/sandbox-quick-guide
- This connector on ibl.ai: https://ibl.ai/developer/connectors/temenos
- ibl.ai MCP server connections: https://ibl.ai/developer/platform/mcp/mcp-connections