# Azure DevOps MCP connector

The Azure DevOps connector brings pull requests, reviewers, branch policy configurations and work item states into Claude, ChatGPT, Cursor and Microsoft Copilot through Elaichi, so everyone asks in plain language and works inside their own Azure DevOps access.

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

## Facts

| | |
| --- | --- |
| Application | Azure DevOps |
| Category | Ticketing |
| AI tools | 7 |
| Authentication | Connects over OAuth |
| 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 Azure DevOps is connected

- Which pull requests are still waiting on a reviewer?
- Show me the branch policies on the main repository.
- Who is reviewing pull request 4821?

## Connect Azure DevOps in Elaichi

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

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

## Azure DevOps 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.

## Azure DevOps 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`.

## Azure DevOps 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.

## Azure DevOps 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.

## Azure DevOps 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 Azure DevOps 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 Azure DevOps 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 Azure DevOps through Elaichi

### See which pull requests are still open

Engineering. Ask for the open pull requests across a project and get the list back without opening Azure DevOps. Pull up one pull request by number to check its title, branch and status before standup.

### Find out who is reviewing what

Engineering managers. List the reviewers on any pull request and spot the ones waiting on a single person. Ask which pull requests have no reviewer yet and chase them before the day ends.

### Check branch policies before a release

Release management. Pull the policy configurations on a repository and confirm the required reviewer and build checks are in place. Open one policy by ID when something in the release checklist looks off.

### Confirm review rules match the standard

Security. Review every policy configuration in Azure DevOps against your sign-off standard and flag any branch that lets code in with fewer approvals than it should. Do it before an audit instead of after.

### Know which states a work item can take

Project management. Look up the work item states for a project so a new board or report uses the right names. Explain to a new team member what New, Active and Resolved actually mean in your process.

### Clear out a duplicate work item

Project management. Give the ID of a duplicate or mistaken work item and have it deleted from Azure DevOps, with the action logged under your name.

## Elaichi vs Zapier MCP vs Composio for Azure DevOps

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

Connect Azure DevOps in Elaichi by signing in with the Microsoft account you already use for Azure DevOps and approving access, which takes about a minute. There is no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude will ask you to sign in to Elaichi and Azure DevOps is ready.

### Does Azure DevOps work with ChatGPT and Cursor as well as Claude?

Yes. The Azure DevOps connector sits behind one Elaichi endpoint, https://api.elaichi.ai/mcp, and Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent all use that same address. You connect Azure DevOps once in Elaichi and every client picks it up.

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

With Azure DevOps connected, an agent can list open pull requests, open a single pull request by number, show who is reviewing it, list the branch policy configurations on a repository and look up the work item states a project uses. It can also delete a work item when you give it the ID. Short, concrete asks such as "who is reviewing pull request 4821" work better than long paragraphs.

### Does connecting Azure DevOps give the AI access to every project and repository?

No. Every call to Azure DevOps runs as the person who signed in, so an agent sees only the projects, repositories and pull requests that person can already see in Azure DevOps. Elaichi can narrow that further with roles and restrictions, and it never widens it beyond what Azure DevOps already allows.

### Can my team share one Azure DevOps connection?

Yes. One person connects Azure DevOps in Elaichi and shares the connection with a team, and nobody else ever handles a token or credential. Each teammate still signs in to Elaichi as themselves, so the audit log names the actual person behind every pull request lookup or work item deletion.

### Can I stop an agent from deleting work items in Azure DevOps?

Yes. In Elaichi you restrict actions one at a time, such as deleting a work item in Azure DevOps, and the restriction applies to a role or to 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 an Azure DevOps connection when someone leaves?

Offboarding a person in Elaichi ends their Azure DevOps access through every client at once. If they shared the Azure DevOps connection with a team, it keeps working for everyone else. If you ever want it gone entirely, disconnecting Azure DevOps once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.

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

Yes. Azure DevOps 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 Azure DevOps?

Yes. Both let Claude, ChatGPT or Cursor use Azure DevOps. 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 Azure DevOps call.

### How is Elaichi different from Composio for Azure DevOps?

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

## All 7 Azure DevOps tools

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

- **Delete a Azure DevOps work item by ID** (Delete). Deletes a work item: it goes to the project's recycle bin and can be restored (destroy is not sent).
- **List all Azure DevOps pull requests** (List). List pull requests in a Git repository. Defaults to active PRs; pass searchCriteria.status=all for every PR.
- **Get single Azure DevOps pull request by ID** (Get). Get a pull request by ID within a project.
- **List all Azure DevOps pull request reviewers** (List). List reviewers on a pull request with their vote (10 approved, 5 approved with suggestions, 0 no vote, -5 waiting for author, -10 rejected).
- **List all Azure DevOps policy configurations** (List). List branch policy configurations (required reviewers, minimum approvers, build validation) in a project.
- **Get single Azure DevOps policy configuration by ID** (Get). Get a branch policy configuration by ID.
- **List all Azure DevOps work item states lookup** (List). Used by the ticketing mappings to read each state's category. Never fails: an error returns an empty list.
