---
name: iblai-connect-ncino
description: "Read and write nCino data through the Salesforce Platform APIs on the nCino org; nCino Mortgage API, Consumer Banking APIs and eVault API and expose it to an ibl.ai agent as an MCP tool. Use when the user asks an agent to work with nCino data, or to set up an nCino MCP connection on ibl.ai."
metadata:
  kind: guide
---

# nCino connector for AI agents

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

nCino runs commercial, small business, consumer and mortgage lending and deposit account opening for banks and credit unions. Its core platform lives in the bank's Salesforce org; loan, borrower and collateral records sit there.

## Auth & conventions

- **API:** Salesforce Platform APIs on the nCino org; nCino Mortgage API, Consumer Banking APIs and eVault API (Mixed). Loan and relationship records are objects in the bank's Salesforce org, reachable with SOQL and sObject APIs. Separate nCino APIs cover the U.S. Mortgage platform, consumer loan and deposit origination, and eVault.
- **Access:** Issued by your administrator. The bank's Salesforce admin grants org API access. nCino product API credentials are issued per institution, and each credential only reaches the endpoints and methods toggled on for it in the portal.
- **Auth:** OAuth 2.0 (Salesforce org); API key and secret exchanged for a token (nCino product APIs). Org data uses Salesforce OAuth. For the Mortgage API, endpoint authorization changes apply on the next token request made with the credential's API key and secret.
- Keep nCino 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

- **Loans and relationships** — SOQL over nCino objects in the Salesforce org; object API names depend on the installed package.
- **Org configuration** — Via nCino MCP: validation rules, flows, approval processes, Apex, page layouts, permission sets, picklist values.
- **Data model** — nCino MCP resolve_schema and query_soql tools against a registered sandbox org.
- **Release notes and help** — nCino MCP search_releases and search_help_documentation; no org connection needed.

## Writes

- **Records (sandbox)** — nCino MCP record_upsert creates or updates records in a registered sandbox org.
- **Feature flags and properties** — nCino MCP manage_feature_flags and manage_system_properties (sandbox only).
- **Metadata (sandbox)** — nCino MCP metadata_deploy pushes configuration to a sandbox org; batches are not atomic.

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

nCino publishes an official MCP server, nCino MCP (https://developer.ncino.com/ncino-mcp/docs/ncino-mcp). Register it below as-is, or host your own server that wraps the calls in this skill.

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

- "Which validation rules fire when a commercial loan moves to underwriting?"
- "List loans in the sandbox stuck in approval for more than 10 days"
- "Explain what changed in the latest nCino release for deposit account opening"
- "Turn on the feature flag for the new credit memo layout in our UAT sandbox"

## Guardrails

- Loan files hold GLBA nonpublic personal information: borrower income, tax IDs, credit and collateral details. Sandbox copies of production data carry the same obligations.
- Request the narrowest nCino 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

- nCino Developer Portal: https://developer.ncino.com/
- nCino MCP overview: https://developer.ncino.com/ncino-mcp/docs/ncino-mcp
- nCino Mortgage API: Getting Started: https://developer.ncinomortgage.com/mortgage/docs/getting-started
- nCino MCP: https://developer.ncino.com/ncino-mcp/docs/ncino-mcp
- This connector on ibl.ai: https://ibl.ai/developer/connectors/ncino
- ibl.ai MCP server connections: https://ibl.ai/developer/platform/mcp/mcp-connections