testmo-mcp
Connect Claude, Cursor, and other AI assistants to your Testmo test management instance to manage test cases, folders, runs, milestones, and CI/CD automation.
README
Testmo MCP Server
A Python Model Context Protocol (MCP) server for Testmo — bring AI-assisted test management to Claude Desktop, Cursor, and any MCP-compatible client.
Testmo MCP is an open-source MCP server that connects AI assistants like Claude Desktop, Claude Code, and Cursor directly to your Testmo test management instance. Manage test cases, folders, milestones, runs, attachments, and CI/CD automation sources — all through natural language, without leaving your AI client.
Built for QA engineers, SDETs, and developers who use Testmo and want to stop clicking through the UI for repetitive work. Powered by FastMCP and the Testmo REST API.
✨ Features
- 🧪 Full test case management — create, read, update, delete, search, and bulk-operate on Testmo cases
- 📁 Folder operations — create, rename, move, delete, and traverse folder trees recursively
- 🚀 Bulk & batch operations — create or update up to 100 cases per call, or unlimited with auto-batching
- 🏃 Test runs & results — list runs, fetch run details, and filter run results
- 🎯 Milestones — list and inspect milestones across projects
- 📎 Attachments — upload, list, and delete file attachments on test cases
- 🤖 CI/CD automation sources — manage automation runs, parallel threads, and result submission
- 🔗 Issue integrations — list GitHub, Jira, and other issue connections
- 🌳 Recursive helpers — fetch entire folder subtrees of cases in one call
- 🛠️ Field mapping utilities — resolve priority, type, and state IDs without guessing
- 🤝 Works with any MCP client — Claude Desktop, Claude Code, Cursor, Cline, and more
🚀 Quick start
Prerequisites
- Python 3.11 or newer
uvpackage manager- A Testmo instance and API key (Settings → API Keys in Testmo)
- An MCP-compatible client (Claude Desktop, Cursor, etc.)
Installation
git clone https://github.com/strelec00/testmo-mcp.git
cd testmo-mcp
uv sync
Connect to Claude Desktop
Edit your Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"testmo": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/testmo-mcp",
"run",
"testmo-mcp.py"
],
"env": {
"TESTMO_URL": "https://your-instance.testmo.net",
"TESTMO_API_KEY": "your-api-key"
}
}
}
}
Restart Claude Desktop. The Testmo tools will appear in the MCP tools list.
Connect to Cursor
Open Cursor Settings → MCP (or edit ~/.cursor/mcp.json) and use the same JSON snippet.
Dev / testing mode
uv run mcp dev testmo-mcp.py
💬 Example prompts
Once connected, try asking your AI assistant:
- "List all projects in Testmo and show me the one called Certilligent."
- "Create 20 login test cases covering valid credentials, wrong password, locked account, expired session, and 2FA flows."
- "Find the 'Smoke Tests' folder and list every high-priority case inside it recursively."
- "Bulk update all draft cases in folder 42 to set their priority to high."
- "Show me the latest automation run for the Playwright source and append a new thread of results."
- "Upload this screenshot as an attachment to test case 1234."
🧠 Why use Testmo with MCP?
Traditional Testmo workflows require navigating the UI for every test case, every folder, every bulk update. With Testmo MCP, your AI assistant becomes a QA co-pilot:
- Spin up entire test suites from a feature spec or PRD in seconds
- Refactor folder structures conversationally instead of click-by-click
- Keep Testmo in sync with your codebase without context-switching
- Pair with Claude Code for end-to-end QA automation: generate Playwright tests and register them in Testmo
- Wire CI/CD automation runs straight from your terminal session
🔧 Available tools
Projects
| Tool | Description |
|---|---|
testmo_list_projects |
List all projects |
testmo_get_project |
Get project details |
Folders
| Tool | Description |
|---|---|
testmo_list_folders |
List all folders in a project with full paths |
testmo_get_folder |
Get details of a specific folder |
testmo_create_folder |
Create a new folder (optionally nested under parent) |
testmo_update_folder |
Update folder name, parent, docs, or display order |
testmo_delete_folder |
Delete a folder and all its test cases |
testmo_find_folder_by_name |
Find a folder by name within a project |
Milestones
| Tool | Description |
|---|---|
testmo_list_milestones |
List milestones |
testmo_get_milestone |
Get milestone details |
Test cases
| Tool | Description |
|---|---|
testmo_list_cases |
List cases (paginated) |
testmo_get_all_cases |
Get all cases (auto-pagination) |
testmo_get_case |
Get single case details |
testmo_create_case |
Create one case |
testmo_create_cases |
Create up to 100 cases |
testmo_batch_create_cases |
Create unlimited cases (auto-batched) |
testmo_update_case |
Update one case |
testmo_batch_update_cases |
Bulk update up to 100 cases |
testmo_delete_case |
Delete one case |
testmo_batch_delete_cases |
Delete multiple cases (auto-batched) |
testmo_search_cases |
Search cases with filters |
Test runs
| Tool | Description |
|---|---|
testmo_list_runs |
List test runs |
testmo_get_run |
Get run details |
testmo_list_run_results |
List run results with filters |
Attachments
| Tool | Description |
|---|---|
testmo_list_case_attachments |
List attachments on a test case |
testmo_upload_case_attachment |
Upload a single file (auto-compress) |
testmo_upload_case_attachments |
Upload up to 20 files at once |
testmo_delete_case_attachments |
Delete one or more attachments |
Automation (CI/CD)
| Tool | Description |
|---|---|
testmo_list_automation_sources |
List CI/CD sources |
testmo_get_automation_source |
Get source details |
testmo_list_automation_runs |
List automation runs |
testmo_get_automation_run |
Get automation run details |
testmo_create_automation_run |
Create automation run |
testmo_append_automation_run |
Append artifacts/fields/links |
testmo_complete_automation_run |
Complete automation run |
testmo_create_automation_run_thread |
Create parallel thread |
testmo_append_automation_run_thread |
Submit test results to thread |
testmo_complete_automation_run_thread |
Complete thread |
Issue connections
| Tool | Description |
|---|---|
testmo_list_issue_connections |
List integrations (GitHub, Jira, etc.) |
testmo_get_issue_connection |
Get integration details |
Recursive / composite
| Tool | Description |
|---|---|
testmo_get_folders_recursive |
Get full folder tree from a root |
testmo_get_cases_recursive |
Get all cases across a folder subtree |
testmo_search_cases_recursive |
Search cases within a folder subtree |
Utility
| Tool | Description |
|---|---|
testmo_get_field_mappings |
Get field value IDs (priorities, types, states) |
testmo_get_web_url |
Generate a Testmo web URL for any resource |
🛠️ Troubleshooting
"Tool not found" in Claude Desktop
Use an absolute path in args and fully restart Claude Desktop after editing the config.
401 Unauthorized
Double-check TESTMO_API_KEY and that the key has API access enabled in Testmo under Settings → API Keys.
uv: command not found
Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh
🤝 Contributing
PRs welcome. Open an issue first for larger changes.
📄 License
MIT
🔗 Related projects
- Testmo — unified test management for software teams
- Model Context Protocol — open standard for AI tool integrations
- FastMCP — Pythonic framework for building MCP servers
- Claude Desktop — Anthropic's desktop client with MCP support
Keywords: testmo mcp, testmo claude, testmo ai integration, mcp server testmo, model context protocol testmo, testmo python, testmo api client, fastmcp testmo, ai test management, qa automation claude, testmo cursor, testmo automation api, testmo bulk create cases, anthropic mcp servers
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。