# Productboard MCP connector

Connect Productboard to Elaichi and Claude, ChatGPT, Cursor and the Elaichi Agent can find, read and update product specs, feedback notes, comments and feature status, each person acting inside their own Productboard access with every change logged.

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

## Facts

| | |
| --- | --- |
| Application | Productboard |
| Category | Product Development |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Productboard builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | support@productboard.com |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, 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 Productboard is connected

- Which features changed status this week in the Mobile app product?
- Attach this call summary to the SSO feature as a note
- Summarize open comments on features planned for the Q3 release

## Connect Productboard in Elaichi

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

1. Open Connections, choose Add connection, and pick Productboard.
2. Optionally set Share with, then press Connect.
3. Approve it in Productboard. Productboard'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 Productboard tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Productboard 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.

## Productboard 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 today. The plugin directory lives at chatgpt.com/plugins.

## Productboard 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.

## Connect Productboard 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

Only Read is granted by default, which is not enough to call a Productboard tool. 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. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Productboard through Elaichi

### Catch the feature up after a customer call

Product. Ask the agent to add your call notes to the feature in Productboard and move its status, so the record reflects the conversation before you move on to the next meeting.

### Check where a requested feature stands

Customer success. Before a renewal call, ask what status the features a customer asked for are in and read the latest comments, straight from Productboard.

### Attach a ticket's feedback to the right feature

Support. When a customer describes a gap, have the agent find the matching feature in Productboard and add the feedback as a note so the product team sees it.

### Read the spec without leaving the editor

Engineering. From Cursor, pull up the feature description and acceptance notes in Productboard, then leave a question in the comments for the product manager.

### Answer roadmap questions during a demo

Sales. Ask which release a feature sits in and what its status is in Productboard, then give the prospect a straight answer instead of a follow-up email.

### Summarize what changed this week

Leadership. Ask for the features whose status moved this week in Productboard, with a short summary of the open comments on each.

## Elaichi vs Zapier MCP vs Composio for Productboard

All three can connect Productboard 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 Productboard tools | Allow or restrict single Productboard 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 Productboard 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](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 Productboard to Claude?

Two steps. In Elaichi, choose Productboard and connect it, which opens Productboard's own sign-in page where you sign in and approve access, with no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude signs you in through Elaichi and your Productboard features, notes and comments are available in the conversation.

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

Yes. Once Productboard 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 Productboard once and every client you use picks it up.

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

It can find features and specs in Productboard, read their descriptions, notes and comments, add new comments or feedback notes, and change a feature's status. What is available depends on what your Productboard account has set up, so the agent works with the products, features and releases you already use. Short, concrete asks, like naming the feature and the change you want, work better than long paragraphs.

### Does connecting Productboard give the AI access to my whole workspace?

No. Each person signs in to Productboard as themselves, so the agent sees only the products, features and notes that person can already see in Productboard. Elaichi can narrow that further with roles and restrictions, and it can never widen it beyond what Productboard itself allows.

### Can my team share one Productboard connection?

Yes. One person connects Productboard in Elaichi and shares the connection with a team, and nobody else ever handles a credential. Each teammate still signs in to Elaichi as themselves, so every change to a feature or comment in Productboard is logged under the name of the person who made it.

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

Yes. Restrictions in Elaichi work per action, so you can allow reading features and notes in Productboard while blocking status changes or edits. A restricted action is never shown to Claude, ChatGPT or Cursor at all, so no prompt, however it is worded, can reach it.

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

Offboarding that person in Elaichi ends their access to Productboard through every client at once. If they had shared a Productboard connection with a team, it keeps working for everyone else. Disconnecting Productboard once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together.

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

Yes. Productboard 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 Productboard?

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

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

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