# Talend MCP connector

The Talend connector lets Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent work with Talend artifacts, connections, crawlers and audit logs as the signed-in person, with every call logged.

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

## Facts

| | |
| --- | --- |
| Application | Talend |
| Category | IPAAS |
| AI tools | 317 |
| Authentication | Connects with an 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 Talend is connected

- Which crawlers errored overnight and what did the logs say?
- Show the latest version of the orders pipeline artifact.
- Run the customer crawler and tell me what datasets it found.

## Connect Talend in Elaichi

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

1. Open Connections, choose Add connection, and pick Talend.
2. Optionally set Share with, then press Connect.
3. Paste a Talend API key. One person generates a token in Talend and pastes it once. Everyone else works through Share with, and never sees it.

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

## Talend 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.

## Talend 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`.

## Talend 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.

## Talend 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.

## Talend 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 Talend 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 Talend 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 Talend through Elaichi

### Find the right artifact version fast

Data engineering. Ask which versions of a pipeline artifact exist, pull the one a colleague deployed last week, and download its archive without opening Talend.

### Run a crawler and read its errors

Data governance. Kick off the customer data crawler, then ask what went wrong when it stops early and get the error log explained in plain words.

### Tidy up connections across workspaces

IT operations. List every Talend connection, update the ones pointing at a retired database, and move the rest into the workspace that owns them.

### Answer who changed what in Talend

Security. Pull the Talend audit logs for a given day and ask which person touched a connection or deleted an artifact.

### See what the crawlers discovered

Analytics. Ask which datasets a crawler picked up overnight and whether the new sales tables made it into the catalog.

### Start a connection scan after a migration

IT operations. Trigger a scan on a freshly created Talend connection and check the result before anyone builds a job on top of it.

## Elaichi vs Zapier MCP vs Composio for Talend

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

Connect Talend in Elaichi first, where it asks for a Talend API key and nothing else, so there is no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in as yourself and Talend is available in your next conversation.

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

Yes. Once Talend is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect Talend once, not once per client.

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

With Talend connected, an agent can list your artifacts and their versions, download an artifact archive, create or update a connection and start a scan on it, create, run and edit crawlers, read crawler error logs and the datasets they found, and pull Talend audit logs. Short, concrete asks work best, such as "run the orders crawler" rather than a long paragraph.

### Does connecting Talend give the AI access to every workspace?

No. Every call into Talend runs as the person who signed in, so an agent only sees the workspaces, connections and artifacts that person already has in Talend. Elaichi can narrow that further with roles and restrictions, but it can never widen it beyond what Talend itself allows.

### Can my team share one Talend connection?

Yes. One person connects Talend in Elaichi with the API key and shares the connection with a team, and nobody else ever handles the key. Each teammate still signs in to Elaichi as themselves, so the audit log names the actual person who ran a crawler or changed a connection.

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

Yes. In Elaichi you can restrict any single action on Talend, such as deleting an artifact or a crawler, for a role or for one person. A restricted action still shows up in tool search flagged as restricted, but no client can run it no matter how the prompt is worded.

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

Offboarding the person in Elaichi ends their access to Talend through every client at once. If they connected a shared Talend account, it keeps working for everyone else on the team. Disconnecting Talend once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.

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

Yes. Talend 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 Talend?

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

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

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

## All 317 Talend tools

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

- **Get single Talend artifact version by ID** (Get). Get Artifact of a specified version. The id is the version. Required: id, artifact_id.
- **Delete a Talend artifact version by ID** (Delete). Delete Artifact of a specified version. The id is the version. Required: id, artifact_id.
- **Talend artifact versions download archive** (Download). Get archive metadata of an artifact for a specified version. Required: artifact_id, version.
- **List all Talend artifacts** (List). Get available Artifacts.
- **Get single Talend artifact by ID** (Get). Get Artifact by id. The id is the artifactId. Required: id.
- **Delete a Talend artifact by ID** (Delete). Delete Artifact by id. The id is the artifactId. Required: id.
- **List all Talend audit logs** (List). Return audit logs for current account with the latest date on top. Return audit logs about the events triggered within the hot period defined by your license. With the latest timestamp on top, the results are paginated with the page number and page size parameters.
- **Get single Talend connection scan by ID** (Get). Retrieve the result of the last scan. This endpoint allows you to retrieve the tables and views held by a connection based on the last connection scan. The id is the connectionId. Required: id.
- **Talend connection scans start** (Start). Scan a JDBC connection. This endpoint allows you to scan the content of a JDBC connection. The scan will search for all the tables and views that are held by this connection. Required: connection_id.
- **List all Talend connections** (List). Get available Connections.
- **Create a Talend connection** (Create). Create a Connection. Required: name, workspaceId, app, parameters.
- **Get single Talend connection by ID** (Get). Get a Connection details. The id is the connectionId. Required: id.
- **Update a Talend connection by ID** (Update). Update a Connection. The id is the connectionId. Required: id.
- **Delete a Talend connection by ID** (Delete). Delete a Connection. The id is the connectionId. Required: id.
- **Talend connections move** (Move). Move a Connection. Move a connection to another workspace. The target workspace must be in the same environment as the original one. Required: connection_id, target_workspace_id.
- **List all Talend crawler datasets** (List). Retrieve all the statuses of the datasets related to a crawler. This endpoint allows you to retrieve the statuses of all the datasets related to a crawler. Required: crawler_id.
- **Talend crawler error logs get log** (Get). Get the error log file. This endpoint allows you to retrieve the error log file of a crawler run. Required: crawler_id.
- **List all Talend crawlers** (List). Retrieve all the crawlers of a tenant. This endpoint lets you retrieve all the crawlers of a tenant. You can also include the crawlers that have been deleted by activating the dedicated option.
- **Create a Talend crawler** (Create). Create a new crawler. At this time, a crawler can only be created on a JDBC connection. You can only have one active crawler per connection. An active crawler is a crawler that has not been deleted. Required: connectionId, name.
- **Get single Talend crawler by ID** (Get). Get a crawler by its ID. Retrieve a crawler using its ID. The response payload contains the crawler itself. The id is the crawlerId. Required: id.
- **Update a Talend crawler by ID** (Update). Update the tables and views selection of an existing crawler. This endpoint allows you to add and remove some tables or views from the crawler configuration. The id is the crawlerId. Required: id, name.
- **Delete a Talend crawler by ID** (Delete). Delete a crawler. Use this method to delete a crawler. Because you can only have one crawler at a time on a JDBC connection, you may need to delete a crawler in order to create a new one. The id is the crawlerId. Required: id.
- **Talend crawlers partial update** (Update). Update the name and description of a crawler. This endpoint allows you to update the name and the description of a crawler. Required: crawler_id.
- **Talend crawlers run** (Run). Run a crawler. This endpoint allows you to start the crawler. When calling this endpoint, the crawler will rely on its configuration in order to retrieve all the selected tables and views and turn them into datasets. Required: crawler_id.
- **Talend crawlers end** (Action). End a crawler while it is running. This endpoint allows you to stop a crawler while it is running. After launching a crawler, the run can take up to a few hours to complete, according the number of objects you selected. Required: crawler_id.
- **List all Talend dataset attribute definitions** (List). List custom attributes definitions. Custom attributes allow you to create a tagging system for your datasets using free text or predefined values for a given category. Use this method to list all the custom attributes definitions created on the account.
- **Create a Talend dataset attribute definition** (Create). Create a custom attribute definition. Custom attributes allow you to create a tagging system for your datasets using free text or predefined values for a given category. Use this method to create a new custom attribute definition. Required: label, mandatory, type.
- **Get single Talend dataset attribute definition by ID** (Get). Get a custom attribute definition. Custom attributes allow you to create a tagging system for your datasets using free text or predefined values for a given category. The id is the definitionId. Required: id.
- **Delete a Talend dataset attribute definition by ID** (Delete). Delete a custom attribute definition. Custom attributes allow you to create a tagging system for your datasets using free text or predefined values for a given category. Use this method to delete a given custom attribute definition based on its id. The id is the definitionId. Required: id.
- **Update a Talend dataset attribute definition by ID** (Update). Update a custom attribute definition. Custom attributes allow you to create a tagging system for your datasets using free text or predefined values for a given category. The id is the definitionId. Required: id, label, mandatory.
- **List all Talend dataset attributes** (List). List custom attributes values for a dataset. A predefined list of values or free text can be used to add metadata to a dataset based on the configured attribute definition. Required: dataset_id.
- **Update a Talend dataset attribute by ID** (Update). Set or update a custom attribute value for a dataset. Use this method to set or update a custom attribute value applied on a given dataset. In the case of a List of values definition, you can select another value among the list of authorized ones. Required: id, dataset_id, values.
- **Delete a Talend dataset attribute by ID** (Delete). Delete a custom attribute value for a dataset. Use this method to remove a custom attribute value applied on a dataset. When configuring a custom attribute definition, a default value can be set. Required: id, dataset_id.
- **List all Talend dataset columns** (List). List metadata of all fields for a dataset. Required: dataset_id.
- **Create a Talend dataset column** (Create). Create or update metadata for multiple fields of a dataset. Required: dataset_id, body.
- **Update a Talend dataset column by ID** (Update). Create or update metadata for a specific field of the dataset. The id is the path. Required: id, dataset_id, description.
- **List all Talend dataset connections** (List). Get the list of connections. Use this method to list all the connections that have been created for a given user account.
- **Get single Talend dataset connection by ID** (Get). Get a connection. Use this method to get information on a given connection based on its id. The id is the connectionId. Required: id.
- **Delete a Talend dataset connection by ID** (Delete). Delete a connection. Use this method to delete a given connection based on its id. You cannot delete connections with existing datasets based on it. The datasets must be deleted first. The id is the connectionId. Required: id.
- **List all Talend datasets** (List). Get the list of datasets. A dataset is a collection of data retrieved from a connection. Use this method to list all the datasets that have been created for a given user account.
- **Get single Talend dataset by ID** (Get). Get a dataset. A dataset is a collection of data retrieved from a connection. Use this method to get information on a dataset based on its id. The id is the datasetId. Required: id.
- **Delete a Talend dataset by ID** (Delete). Delete a dataset. A dataset is a collection of data retrieved from a connection. Use this method to delete a dataset based on its id. The id is the datasetId. Required: id.
- **Talend datasets certify** (Action). Set the certification state of a dataset. Use this method to add a certification level to a dataset that has trusted data. There are three certification statuses: no certification certification pending certified Required: dataset_id, currentCertification.
- **Talend dynamic engine environment deployments get status** (Get). Fetch the Dynamic Engine environment status. The status is the runtime state of processing services belonging to an environment assigned to the given Dynamic Engine instance. Required: dynamic_engine_id, environment_id.
- **Delete a Talend dynamic engine environment deployment by ID** (Delete). Delete an environment assignment. This removes the association between the given environment and the given Dynamic Engine instance. The id is the environmentId. Required: id, dynamic_engine_id.
- **Create a Talend dynamic engine environment** (Create). Create new Dynamic Engine Environment. A Dynamic Engine Environment is an Environment that can be assigned to one Dynamic Engine. Required: name, workspaceName.
- **Get single Talend dynamic engine environment by ID** (Get). Retrieves a Dynamic Engine Environment. The id is the environmentId. Required: id.
- **Update a Talend dynamic engine environment by ID** (Update). Update one Dynamic Engine Environment. Allows to update name, description as well as particular Log and Metrics policy regarding this Dynamic Engine Environment. The id is the environmentId. Required: id.
- **Delete a Talend dynamic engine environment by ID** (Delete). Removes a Dynamic Engine Environment. Allows you to remove this environment. The id is the environmentId. Required: id.
- **Talend dynamic engine environments connect** (Action). Create an assignment between this Environment and a Dynamic Engine. Required: environment_id, dynamicEngineId.
- ...and 267 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
