# ITM Platform MCP server

> Connect AI assistants to ITM Platform to manage projects, tasks, budgets, risks, and team workloads.

- Repository: https://github.com/itmplatform/mcp-server
- Page: https://hostedmcp.org/servers/itmplatform/mcp-server
- Transport: stdio, remote
- Stars: 0
- License: MIT
- Latest version: 1.0.24

## Install

### Claude Code

```sh
claude mcp add mcp-server -- npx -y @itm-platform/mcp-server
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@itm-platform/mcp-server"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@itm-platform/mcp-server"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"mcp-server","type":"stdio","command":"npx","args":["-y","@itm-platform/mcp-server"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@itm-platform/mcp-server"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add mcp-server -- npx -y @itm-platform/mcp-server
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@itm-platform/mcp-server"]
```

### Gemini CLI

```sh
gemini mcp add -s user mcp-server npx -- -y @itm-platform/mcp-server
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@itm-platform/mcp-server"
      ]
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `ITM_API_KEY` | no | no | Your personal API key |
| `ITM_API_URL` | no | no | ITM Platform API gateway URL |
| `ITM_COMPANY` | no | no | Your company/account slug |

## Tools (47)

- `search_projects`
- `get_project`
- `search_services`
- `get_service`
- `list_project_tasks`
- `get_task`
- `search_tasks`
- `get_project_budget`
- `get_project_purchases`
- `get_project_revenues`
- `get_project_risks`
- `get_project_issues`
- `get_risk`
- `get_issue`
- `list_task_progress`
- `get_task_effort`
- `get_project_progress`
- `list_service_activities`
- `get_service_purchases`
- `get_service_revenues`
- `aggregate_portfolio`
- `query_datamart`
- `search_users`
- `get_user`
- `get_reference_data`
- `get_custom_fields`
- `get_custom_field_options`
- `create_project`
- `create_task`
- `update_task`
- `create_task_progress`
- `update_task_progress`
- `update_task_effort`
- `log_time_entry`
- `create_project_progress`
- `update_project_progress`
- `create_risk`
- `update_risk`
- `create_issue`
- `update_issue`
- `update_project`
- `create_service`
- `update_service`
- `create_activity`
- `update_activity`
- `bulk_update_task_status`
- `bulk_update_activity_status`

## FAQ

### How do I connect to the hosted ITM Platform server?

You can use the hosted server if your AI client supports remote MCP servers by adding the URL and signing in with your ITM Platform account via OAuth.

### Can I run the ITM Platform MCP server locally?

Yes, you can use the npm package to run the server locally, which is useful for working behind a firewall or connecting to a self-hosted instance.

### Does the AI assistant have access to my password?

No, the server uses OAuth or API keys so your AI client never sees your ITM Platform password.