# Agworld MCP connector

The Agworld connector brings fields, activities, product applications, seeding records and reported problems into Claude, ChatGPT, Cursor, Microsoft Copilot or any MCP client, with each person signed in as themselves and every call logged.

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

## Facts

| | |
| --- | --- |
| Application | Agworld |
| Category | CRM |
| AI tools | 155 |
| Authentication | OAuth or API key |
| Bring your own OAuth app | Yes |
| 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 Agworld is connected

- Which fields had a seeding activity recorded this week?
- List product applications on the north block since March.
- Show problems reported across all fields this month.

## Connect Agworld in Elaichi

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

1. Open Connections, choose Add connection, and pick Agworld.
2. Optionally set Share with, then press Connect.
3. Supply your own Agworld app, then approve. Agworld needs an OAuth app you register yourself, so bring its client ID and secret. One person does this once for the organization.

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

## Agworld 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.

## Agworld 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`.

## Agworld 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.

## Agworld 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.

## Agworld 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 Agworld 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 Agworld 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 Agworld through Elaichi

### Check what went on a field

Agronomy. Before a visit, ask for every product application on a field this season, with the active ingredient amounts, and read it back in one place.

### See which operations ran this week

Operations. Pull the activity operations, the operators who did them and the assets they used, so the week's work is clear without opening each record.

### Answer a spray record question fast

Compliance. When an auditor asks what was applied where and by whom, look up the product applications and compound products for that field and date range.

### Reconcile inputs against recorded applications

Finance. List the compound products and application activities for a block of fields to compare against supplier invoices.

### Summarize seeding progress across properties

Management. Ask how many fields have a seeding activity recorded this month and which ones do not, then share the summary with growers.

### Review problems reported in the field

Grower services. Bring up the activity problems logged across a client's fields so an agronomist can plan the next visit around them.

## Elaichi vs Zapier MCP vs Composio for Agworld

All three can connect Agworld 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 Agworld tools | Allow or restrict single Agworld 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 Agworld 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 Agworld to Claude?

Connect Agworld in Elaichi first, then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Agworld's own sign-in uses an OAuth application you register inside Agworld yourself, so somebody brings a client ID and secret once, or an API key if your organization prefers that. Nothing further has to be generated on the Claude side, and nobody else on the team handles that step again.

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

Yes. Agworld is connected once in Elaichi, and the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. Each person signs in as themselves whichever client they use.

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

With Agworld connected, an agent can look up fields, activities, operations, seeding records, product applications, compound products, active ingredient amounts, operators, assets and reported problems, and answer questions about them. It can tell you what was applied on a field, which operations ran last week, or where problems were logged. Short, concrete asks such as a field name and a date range work better than long sentences.

### Does connecting Agworld give the AI access to every farm and field?

No. Agworld access follows the person who signed in, so an agent only sees the properties, fields and activities that person can already see in Agworld. Elaichi can narrow that further with roles and restrictions, and it never widens it.

### Can my team share one Agworld connection?

Yes. One person connects Agworld in Elaichi and shares the connection with a team, so nobody else handles the client ID, secret or API key. Each person still signs in as themselves, so the audit log names who looked up which Agworld field or activity.

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

The Agworld connector only reads records, so an agent cannot delete or change fields, activities or applications through it. Restrictions still apply per action, on a role or on one person, if you want to limit what can be looked up. A restricted tool still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to an Agworld connection when someone leaves?

Offboarding that person in Elaichi ends their Agworld access at once, in every client they used. A shared Agworld connection keeps working for everyone else on the team. Disconnecting Agworld once in Elaichi removes it from every client.

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

Yes. Agworld 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 Agworld?

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

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

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

## All 155 Agworld tools

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

- **List all Agworld active ingredient amounts** (List). Fetch applied active ingredients. OAuth scope: access:api_v2. Agworld API v2. Required: grower_id.
- **List all Agworld activity asset IDS** (List). List Activity Assets IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld activity asset by ID** (Get). Get an Activity Asset. Retrieves a single activity asset by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld activity assets** (List). List Activity Assets. Retrieves a paginated list of activity assets for a specific grower company. Activity assets represent the assignment of a farm asset (e.g. a tractor or sprayer) to a parent activity (actual, observation, planned, recommendation, or work order). Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld activity compound product IDS** (List). List Activity Compound Products IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld activity compound product by ID** (Get). Get an Activity Compound Product. Retrieves a single activity compound product by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld activity compound products** (List). List Activity Compound Products. Retrieves a paginated list of activity compound products (custom blends) for a specific grower company. This endpoint follows the JSON:API specification and supports: - Pagination - Sorting - Filtering - Sparse fieldsets. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld activity field IDS** (List). List Activity Fields IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld activity field by ID** (Get). Get an Activity Field. Retrieves a single activity field by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld activity fields** (List). List Activity Fields. Retrieves a paginated list of activity fields for a specific grower company. This endpoint follows the JSON:API specification and supports: - Pagination - Sorting - Filtering - Sparse fieldsets. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld activity operation IDS** (List). List Activity Operations IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld activity operation by ID** (Get). Get an Activity Operation. Retrieves a single activity operation by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld activity operations** (List). List Activity Operations. Retrieves a paginated list of activity operations for a specific grower company. Activity operations examples include "boomspray application", "agronomy fees", "fuel", etc. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld activity operator user IDS** (List). List Activity Operator Users IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld activity operator user by ID** (Get). Get an Activity Operator User. Retrieves a single activity operator user by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld activity operator users** (List). List Activity Operator Users. Retrieves a paginated list of activity operator users for a specific grower company. This endpoint follows the JSON:API specification and supports: - Pagination - Sorting - Filtering - Sparse fieldsets. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld activity problem IDS** (List). List Activity Problems IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld activity problem by ID** (Get). Get an Activity Problem. Retrieves a single activity problem by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld activity problems** (List). List Activity Problems. Retrieves a paginated list of activity problems for a specific grower company. Activity problems represent pests or issues observed during a parent activity (actual, observation, planned, recommendation, or work order) and are surfaced under the Pests & Problems grouping in the UI. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld activity product application IDS** (List). List Activity Product Applications IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld activity product application by ID** (Get). Get an Activity Product Application. Retrieves a single activity product application by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld activity product applications** (List). List Activity Product Applications. Retrieves a paginated list of activity product applications for a specific grower company. This endpoint follows the JSON:API specification and supports: - Pagination - Sorting - Filtering - Sparse fieldsets. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld activity seeding IDS** (List). List Activity Seedings IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld activity seeding by ID** (Get). Get an Activity Seeding. Retrieves a single activity seeding by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld activity seedings** (List). List Activity Seedings. Retrieves a paginated list of activity seedings for a specific grower company. This endpoint follows the JSON:API specification and supports: - Pagination - Sorting - Filtering - Sparse fieldsets. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld activity weather record IDS** (List). List Activity Weather Records IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld activity weather record by ID** (Get). Get an Activity Weather Record. Retrieves a single activity weather record by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld activity weather records** (List). List Activity Weather Records. Retrieves a paginated list of activity weather records for a specific grower company. This endpoint follows the JSON:API specification and supports: - Pagination - Sorting - Filtering - Sparse fieldsets. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld actual IDS** (List). List Grower Actuals IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **List all Agworld actual request IDS** (List). List Grower Actual Requests IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: grower_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Create a Agworld actual request** (Create). Submit an Actual for asynchronous creation. Records an Actual - a completed piece of field work such as a spray pass, a seeding, or an operation - against a grower company. Creation is asynchronous: the request does not return the Actual, it returns a ticket (an actual-request) that tracks the work. Agworld API v3. Required: grower_id, data.
- **Get single Agworld actual request by ID** (Get). Get an Actual Request. Retrieves a single actual-request ticket - the poll target of the asynchronous create flow. POST .../actual-requests returns 202 with a ticket in pending; poll this endpoint until the ticket reaches a terminal state: - created - the activity exists. Agworld API v3. Required: id, grower_id.
- **List all Agworld actual requests** (List). List Grower Actual Requests. Retrieves a paginated list of actual-request tickets (asynchronous actual-creation requests) for a grower company - the audit/monitoring view of the asynchronous create pipeline. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **Get single Agworld actual by ID** (Get). Get an Actual. Retrieves a single actual activity by its ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, grower_id.
- **List all Agworld actuals** (List). List Growers Actuals. Retrieves a paginated list of actual activities for a specific grower company. This endpoint follows the JSON:API specification and supports: - Pagination - Sorting - Filtering - Sparse fieldsets. Agworld API v3. Required: grower_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld application method IDS** (List). List Application Methods IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld application method by ID** (Get). Get Application Method. Retrieves a single application method by ID. Application methods are seeded reference data that define the method of applying a product in a farm activity. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id.
- **List all Agworld application methods** (List). List Application Methods. Retrieves a list of application methods available in the system. Application methods are seeded reference data that define the method of applying a product in a farm activity. This endpoint follows the JSON:API specification and supports: - Pagination - Sorting - Filtering - Sparse fieldsets. Agworld API v3. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **Get single Agworld asset category by ID** (Get). Get Asset Category. Retrieves a single asset category by ID. Asset categories are seeded reference data that classify different types of farm assets. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id.
- **List all Agworld asset categories** (List). List Asset Categories. Retrieves a list of asset categories available in the system. Asset categories are reference data that classify different types of farm assets (e.g., vehicles, equipment, infrastructure). Agworld API v3. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld asset category IDS** (List). List Asset Categories IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **List all Agworld asset IDS** (List). List Assets IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: organization_id, company_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- **Get single Agworld asset by ID** (Get). Get Asset. Retrieves a single farm asset by ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, organization_id, company_id.
- **List all Agworld assets** (List). List Assets. Retrieves the farm assets available to a company: those it owns directly, plus any shared down the company hierarchy from a farm_asset ancestor (e.g. a head office). This is the set attachable to the company's actuals. Agworld API v3. Required: organization_id, company_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **Agworld business summaries costs** (Action). Fetch costs. OAuth scope: access:api_v2. Agworld API v2. Returns CSV text (Content-Type text/csv).
- **Agworld business summaries field crop areas** (Action). Fetch field crop areas. OAuth scope: access:api_v2. Agworld API v2. Returns CSV text (Content-Type text/csv).
- **Agworld business summaries revenues** (Action). Fetch revenues. OAuth scope: access:api_v2. Agworld API v2. Returns CSV text (Content-Type text/csv).
- **Get single Agworld company by ID** (Get). Get Company. Retrieves a single company by ID. This endpoint follows the JSON:API specification and supports: - Sparse fieldsets. Agworld API v3. Required: id, organization_id.
- **List all Agworld companies** (List). List Companies. Retrieves a list of companies within the requested organization the authenticated user has permission to access. This endpoint follows the JSON:API specification and supports: - Pagination - Sorting - Filtering - Sparse fieldsets. Agworld API v3. Required: organization_id. The connector pages with page[number]; page[size] from the caller's limit (max 100); records at data.
- **List all Agworld company IDS** (List). List Companies IDs. Lists the IDs of the records that the list endpoint returns to the caller, 1,000 per page by default. Follow links.next for the next page. Filters work as on the list endpoint. Agworld API v3. Required: organization_id. The connector follows links.next (page[after]); page[size] from the caller's limit (max 5000); records at data.
- ...and 105 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
