# JobTread MCP connector

The JobTread connector brings customer and vendor accounts, comments, files, budget tasks, and events into Claude, ChatGPT, Cursor, and Microsoft Copilot, where each person works inside their own JobTread access with every action logged.

Source: https://elaichi.ai/connectors/jobtread/

## Facts

| | |
| --- | --- |
| Application | JobTread |
| Category | CRM |
| AI tools | 281 |
| Authentication | OAuth or API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once JobTread is connected

- Create a vendor account for Ridgeline Plumbing with their contact details
- Summarize the comments on the Harper kitchen remodel this week
- Add budget tasks for framing, roofing, and drywall to the Miller job

## Connect JobTread in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick JobTread.
2. Optionally set Share with, then press Connect.
3. Approve it in JobTread. JobTread's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which JobTread tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## JobTread MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## JobTread MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## JobTread MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## JobTread MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## JobTread MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect JobTread to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a JobTread tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with JobTread through Elaichi

### Catch the customer account up after a call

Sales. Tell the agent what changed on the call and it updates the JobTread customer account and leaves a comment so the estimator sees it before pricing starts.

### Add budget tasks without opening the estimate

Estimating. Describe the scope line by line and the agent creates each budget task in JobTread, ready for you to price.

### Find the comment with the change order

Project management. Ask what the client said about the kitchen tile and the agent searches JobTread comments and attached files to pull up the exact thread.

### Set up new vendors in one go

Office. Paste a list of new subcontractors and the agent creates each vendor account in JobTread with the custom field values your office relies on.

### Check statement descriptors before invoices go out

Accounting. Ask for every JobTread account whose statement descriptor is missing or out of date and fix them from one conversation.

### See who can touch which account

Leadership. Ask which accounts a given person can access across JobTread, including child organizations, and tidy up access that no longer makes sense.

## Elaichi vs Zapier MCP vs Composio for JobTread

All three can connect JobTread 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. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over JobTread tools | Allow or restrict single JobTread 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 JobTread 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 | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect JobTread to Claude?

Open JobTread in Elaichi and connect it with your JobTread sign-in or an API key from your JobTread settings. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Most people are done in a few minutes.

### Does JobTread work with ChatGPT and Cursor as well as Claude?

Yes. Once JobTread is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client, and the Elaichi Agent. You connect JobTread once and every client picks it up.

### What can an AI agent actually do with my JobTread data?

It can look up customer and vendor accounts, create or update them, read and post comments, open attached files, add budget tasks, and check who has access to what in JobTread. Ask in plain words, such as the name of a customer and what changed. Short, concrete asks work better than long paragraphs.

### Does connecting JobTread give the AI access to everything in my organization?

No. Every call runs as the person who signed in, so the agent sees only the JobTread accounts, comments, and child organizations that person can already open. Elaichi can narrow that access further with roles and restrictions, and it can never widen it beyond what JobTread grants.

### Can my team share one JobTread connection?

Yes. One person connects JobTread in Elaichi and shares it with a team, and nobody else ever handles the API key. Each teammate still signs in to Elaichi as themselves, so the audit log names the actual person behind every comment or account change in JobTread.

### Can I stop an agent from deleting or changing things in JobTread?

Yes. Restrictions in Elaichi apply per action, for example deleting a JobTread account or comment, and are set on a role or on one person. A restricted action still appears in Elaichi's tool search flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to a JobTread connection when someone leaves?

Offboarding that person in Elaichi ends their JobTread access through every client at once. A JobTread connection they shared keeps working for everyone else on the team. If you later want JobTread gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client.

### Does the JobTread MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. JobTread 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, Microsoft Copilot, 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 JobTread?

Yes. Both let Claude, ChatGPT or Cursor use JobTread. 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 JobTread call.

### How is Elaichi different from Composio for JobTread?

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 JobTread: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 281 JobTread tools

Every tool below is callable through https://api.elaichi.ai/mcp once JobTread is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List all JobTread account aces** (List). List the access entries (ACEs) of a account (Pave `account.aces`). Required: `account_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **List all JobTread account custom field values** (List). List the custom field values of a account (Pave `account.customFieldValues`). Required: `account_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **List all JobTread account statement descriptors** (List). List the account statement descriptors of a account (Pave `account.accountStatementDescriptors`). Required: `account_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Create a JobTread account** (Create). Create an account (Pave `createAccount`). Required: name, type. `organizationId` defaults to the connected organization. Returns the new record (`createdAccount`).
- **Delete a JobTread account by ID** (Delete). Delete an account (Pave `deleteAccount`). Required: id.
- **Get single JobTread account by ID** (Get). An account is a customer or vendor. Get one account by its JobTread id (Pave `account`). A record that doesn't exist or that this grant can't see returns 404. Required: id.
- **List all JobTread accounts** (List). List the accounts in the connected JobTread organization (Pave `organization.accounts`). Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Update a JobTread account by ID** (Update). Update an account (Pave `updateAccount`); send only the fields to change. Returns the record after the change. Required: id.
- **Create a JobTread ace** (Create). Create an access entry (ACE) (Pave `createAce`). Required: assignee, targetId, targetType. Returns the new record (`createdAce`).
- **Delete a JobTread ace by ID** (Delete). Delete an ace (Pave `deleteAce`). Required: id.
- **JobTread aces send** (Send). Send the access notification (invitation) for an access entry (ACE) (Pave `sendAceNotification`). Required: ace_id.
- **List all JobTread API versions** (List). The current API version. Get the current JobTread API version (a commit hash); needs no key (Pave `version`).
- **Create a JobTread budget task** (Create). Create a tasks from budget (Pave `createTasksFromBudget`). Required: jobId. JobTread returns no record for this mutation.
- **List all JobTread child organization connections** (List). List the child organization connections in the connected JobTread organization (Pave `organization.childOrganizationConnections`). Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **List all JobTread comment aces** (List). List the access entries (ACEs) of a comment (Pave `comment.aces`). Required: `comment_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Get single JobTread comment file by ID** (Get). Get one comment file by its JobTread id (Pave `commentFile`). A record that doesn't exist or that this grant can't see returns 404. Required: id.
- **List all JobTread comment files** (List). List the comment files of a comment (Pave `comment.files`). Required: `comment_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Update a JobTread comment file by ID** (Update). Update a comment file (Pave `updateCommentFile`); send only the fields to change. Returns the record after the change. Required: id.
- **Create a JobTread comment** (Create). Create a comment (Pave `createComment`). Required: message. Returns the new record (`createdComment`).
- **Delete a JobTread comment by ID** (Delete). Delete a comment (Pave `deleteComment`). Required: id.
- **Get single JobTread comment by ID** (Get). Get one comment by its JobTread id (Pave `comment`). A record that doesn't exist or that this grant can't see returns 404. Required: id.
- **List all JobTread comments** (List). List the comments in the connected JobTread organization (Pave `organization.comments`). Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Update a JobTread comment by ID** (Update). Update a comment (Pave `updateComment`); send only the fields to change. Returns the record after the change. Required: id.
- **Delete a JobTread conference event attendee by ID** (Delete). Delete a conference event attendee (Pave `deleteConferenceEventAttendee`). Required: id.
- **List all JobTread conference event attendees** (List). List the conference event attendees of a user (Pave `user.conferenceEventAttendees`). Required: `user_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **List all JobTread contact custom field values** (List). List the custom field values of a contact (Pave `contact.customFieldValues`). Required: `contact_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Create a JobTread contact** (Create). Create a contact (Pave `createContact`). Required: accountId, name. Returns the new record (`createdContact`).
- **Delete a JobTread contact by ID** (Delete). Delete a contact (Pave `deleteContact`). Required: id.
- **Get single JobTread contact by ID** (Get). Get one contact by its JobTread id (Pave `contact`). A record that doesn't exist or that this grant can't see returns 404. Required: id.
- **List all JobTread contacts** (List). List the contacts in the connected JobTread organization (Pave `organization.contacts`). Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Update a JobTread contact by ID** (Update). Update a contact (Pave `updateContact`); send only the fields to change. Returns the record after the change. Required: id.
- **Create a JobTread cost code mapping** (Create). Create a cost code mapping (Pave `createCostCodeMapping`). Required: name, costCodeId. JobTread returns no record for this mutation.
- **Delete a JobTread cost code mapping by ID** (Delete). Delete a cost code mapping (Pave `deleteCostCodeMapping`). The id is the `costCodeId` input. Required: id, name.
- **List all JobTread cost code mappings** (List). List the cost code mappings in the connected JobTread organization (Pave `organization.costCodeMappings`). Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **List all JobTread cost code qbo integration items** (List). List the qbo integration items of a cost code (Pave `costCode.qboIntegrationItems`). Required: `cost_code_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Create a JobTread cost code** (Create). Create a cost code (Pave `createCostCode`). Required: name. `organizationId` defaults to the connected organization. Returns the new record (`createdCostCode`).
- **Delete a JobTread cost code by ID** (Delete). Delete a cost code (Pave `deleteCostCode`). Required: id.
- **Get single JobTread cost code by ID** (Get). Get one cost code by its JobTread id (Pave `costCode`). A record that doesn't exist or that this grant can't see returns 404. Required: id.
- **List all JobTread cost codes** (List). List the cost codes in the connected JobTread organization (Pave `organization.costCodes`). Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Update a JobTread cost code by ID** (Update). Update a cost code (Pave `updateCostCode`); send only the fields to change. Returns the record after the change. Required: id.
- **List all JobTread cost group files** (List). List the line item files of a cost group (Pave `costGroup.files`). Required: `cost_group_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Create a JobTread cost group** (Create). Create a cost group (Pave `createCostGroup`). Required: name. `organizationId` defaults to the connected organization. Returns the new record (`createdCostGroup`).
- **Delete a JobTread cost group by ID** (Delete). Delete a cost group (Pave `deleteCostGroup`). Required: id.
- **Get single JobTread cost group by ID** (Get). Get one cost group by its JobTread id (Pave `costGroup`). A record that doesn't exist or that this grant can't see returns 404. Required: id.
- **List all JobTread cost groups** (List). List the cost groups in the connected JobTread organization (Pave `organization.costGroups`). Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Update a JobTread cost group by ID** (Update). Update a cost group (Pave `updateCostGroup`); send only the fields to change. Returns the record after the change. Required: id.
- **List all JobTread cost item custom field values** (List). List the custom field values of a cost item (Pave `costItem.customFieldValues`). Required: `cost_item_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **List all JobTread cost item files** (List). List the line item files of a cost item (Pave `costItem.files`). Required: `cost_item_id`. Filter with `where` and sort with `sort_by` (Pave JSON); `fields` picks the returned fields. The connector pages through all results with JobTread's `nextPage` cursor (25 per page, or your `limit` up to 100).
- **Create a JobTread cost item** (Create). Create a catalog cost item with an organizationId, a job budget cost item with a jobId, a document costItem with a documentId or an item in a group in any of those contexts with a costGroupId. Create a cost item (Pave `createCostItem`). Required: name. `organizationId` defaults to the connected organization. Returns the new record (`createdCostItem`).
- **Delete a JobTread cost item by ID** (Delete). Delete a cost item (Pave `deleteCostItem`). Required: id.
- ...and 231 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
