Ocrolus MCP connector
The Ocrolus connector for Elaichi lets Claude, ChatGPT, Cursor, or any MCP client read and work with your Ocrolus books, documents, transactions, fraud signals, and cash flow analysis, with each person signed in as themselves and every action logged.
-
How it connects. App credentials. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
67 tools
How to connect
How to connect Ocrolus to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Ocrolus once
-
Open Connections, choose Add connection, and pick Ocrolus.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste your Ocrolus app credentials. Ocrolus authenticates the app rather than a person. One person supplies the credentials once, and everyone else works through Share with.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Ocrolus MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Ocrolus MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Ocrolus MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Ocrolus to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Ocrolus through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Underwriting
Read a borrower's book summary before the call
Ask for the summary and form data on an applicant's Ocrolus book and get income, balances, and the key figures from their bank statements and pay stubs in plain language, without opening the dashboard.
-
Fraud and risk
Check fraud signals before approving a file
Pull the fraud signals on a book or on a single uploaded document and ask what was flagged, so tampered statements or altered pay stubs are caught before a decision is made.
-
Loan operations
Open a book and upload the applicant's PDFs
Create a new Ocrolus book for a borrower, upload the bank statements and mixed PDFs they sent over, and check status until processing is done.
-
Credit analysis
Review enriched transactions and cash flow features
List the enriched transactions on a book, ask for the cash flow features, and have the agent explain recurring deposits, overdrafts, and monthly revenue trends for a small business applicant.
-
Quality control
Confirm every document was classified correctly
Ask for the classification summary on a book to see which pages were recognized as bank statements, tax forms, or pay stubs, and spot documents that still need attention.
-
Onboarding
Import a Plaid asset report into a book
Bring an applicant's Plaid asset report into their Ocrolus book alongside the documents they uploaded, so the underwriter works from one complete file.
Try asking
- “Summarize the books created in Ocrolus this week.”
- “List documents still processing in the Lending Ops book.”
- “Show fraud signals flagged on last month's Ocrolus books.”
Compare
Elaichi vs Zapier MCP vs Composio for Ocrolus
All three can connect Ocrolus to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Ocrolus tools | Allow or restrict single Ocrolus tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Ocrolus call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
AI tools
Ocrolus tools for your AI agents
67 tools are ready to call through Elaichi's MCP endpoint the moment you connect Ocrolus, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Ocrolus gets you
6 screens from the product, each doing one job for your Ocrolus account.
The agent
Ask about books, get answers from Ocrolus.
Type a question in plain language and read live Ocrolus book and document records.
- books
- documents
- fraud signals
- bank statements
Ask Elaichi to work across your apps.
Summarize the books created in Ocrolus this week.
List documents still processing in the Lending Ops book.
Show fraud signals flagged on last month's Ocrolus books.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach Ocrolus here.
One org MCP endpoint over OAuth, no SDK to write and no shared API key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
All 67 Ocrolus tools are already wired.
Books, documents, form data and fraud signals, with methods listed and no custom code.
- List all Ocrolus books
- Create a Ocrolus book
- Get single Ocrolus book by ID
- Ocrolus books get status
ElaichiToolsToolboxes
Every team gets its own Ocrolus toolbox.
Curate one toolbox per team so lending sees books and ops sees uploads.
- Lending Ops
- Underwriting
- Fraud Review
- Accounting
ElaichiToolboxesShared connections
Share an Ocrolus account, never the key.
See who connected each account and which teams and members work through it.
- Lending Ops
- Underwriting
- Fraud Review
- Accounting
ElaichiConnectionsAudit log
Every Ocrolus call is written down.
When, who, what happened, type and resource, in an append only log.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule fires and Ocrolus work finishes.
Fetch books, group them, draft a digest, get approval, post back to Ocrolus.
Ocrolus digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch books
Ocrolus
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Ocrolus
Queued
Collections and dashboards
Ocrolus book numbers arrive without being asked.
Four metrics, 14 days of books created and a team breakdown, computed on schedule.
Ocrolus health
Refreshed 4 minutes ago · every 15 minutes · from the books collection
Books
1,284 ↓ 12%
Documents
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Books created
Last 14 days
By team
Share of activity
Lending Ops 34%
Underwriting 27%
Fraud Review 21%
Accounting 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Ocrolus to Claude?
Connect Ocrolus in Elaichi first: pick Ocrolus from the catalog and enter the app credentials from your Ocrolus account, which takes a couple of minutes. There is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Sign in with your Elaichi account and Ocrolus is available in your chat.
Does Ocrolus work with ChatGPT and Cursor as well as Claude?
Yes. Once Ocrolus is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Ocrolus once and every client you use picks it up.
What can an AI agent actually do with my Ocrolus data?
With Ocrolus connected, an agent can create a book for a borrower, upload their bank statements and pay stubs, check processing status, and read back the summary, form data, and classification results. It can list transactions and enriched transactions, pull cash flow features, and report fraud signals on a book or a single document. Because Ocrolus has a large set of actions, short concrete asks like "fraud signals on the Acme book" work better than long sentences.
Does connecting Ocrolus give the AI access to every book in our account?
No. Every call to Ocrolus runs inside the access of the person who signed in to Elaichi, so an agent sees the books and documents that person can already see in Ocrolus and nothing more. Elaichi can narrow that further, for example to read-only actions for a team, but it can never widen access beyond what Ocrolus itself allows.
Can I stop an agent from deleting or changing things in Ocrolus?
Yes. Restrictions in Elaichi apply per action, so you can block deleting Ocrolus books or documents, or block uploads, while leaving summaries, transactions, and fraud signals available. A blocked action is never advertised to Claude, ChatGPT, or Cursor at all, so no prompt, however worded, can reach it.
What happens to an Ocrolus connection when someone leaves?
Offboarding a person in Elaichi ends their access to Ocrolus at once, across Claude, ChatGPT, Cursor, and every other client they used. A shared Ocrolus connection keeps working for everyone else on the team. If you want to remove Ocrolus entirely, disconnecting it once in Elaichi removes it from every client for everyone.
Does the Ocrolus MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Ocrolus is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Ocrolus?
Yes. Both let Claude, ChatGPT or Cursor use Ocrolus. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Ocrolus call.
How is Elaichi different from Composio for Ocrolus?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Ocrolus: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Ocrolus in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.