space-mcp
MCP server for JetBrains Space merge requests and Patronus CI dry runs, enabling creation, viewing, and management of merge requests as well as starting and monitoring CI dry runs.
README
Space MCP
MCP server and CLI for JetBrains Space merge requests and Patronus CI dry runs.
Installation
Install uv, then:
uv tool install git+https://github.com/bindreams/space-mcp.git
This installs two entry points:
| Command | Purpose |
|---|---|
space |
CLI for merge requests, CI runs, and auth |
space-mcp |
MCP server (stdio transport) |
Authentication
A JetBrains Space personal token is required. Generate one at Personal Tokens.
Token is resolved in order:
SPACE_TOKENenvironment variable- OS keyring (stored via
space auth login) ~/.config/space/credentials.json(plaintext fallback)
space auth login # store token in keyring (prompted)
space auth login --token PAT # non-interactive
space auth status # show token source and detected context
space auth logout # remove stored credentials
During login you will also be offered to authenticate Docker with registry.jetbrains.team.
MCP Tools
| Tool | Description | Parameters |
|---|---|---|
get_merge_request |
Get MR details (title, state, author, reviewers) | project, repository, review_id |
get_merge_requests |
List MRs for a repository | project, repository, branch?, state?, limit? |
get_merge_request_timeline |
Full MR timeline: comments, reviews, dry run results | project, repository, review_id |
put_merge_request |
Create a new merge request | project, repository, source_branch, target_branch, title, description? |
post_close_merge_request |
Close a merge request | project, review_id |
post_reopen_merge_request |
Reopen a closed merge request | project, review_id |
get_attachment |
Download a file attachment from MR discussion | attachment_id |
get_patronus_runs |
List Patronus runs (dry runs / safe merges) for an MR | project, review_id |
get_patronus_run |
Run details with TeamCity checks and problems | run_id |
put_patronus_dry_run |
Start a CI dry run for an MR | project, review_id |
post_cancel_patronus_run |
Cancel a running Patronus run | run_id |
Most tools return YAML; timeline returns Markdown. Parameters marked with ? are optional.
MCP server configuration
First, authenticate via the CLI — the MCP server picks up stored credentials automatically:
space auth login
Then add to .mcp.json (project) or ~/.claude.json (global):
{
"mcpServers": {
"space": {
"command": "space-mcp"
}
}
}
CLI
Global options: -P/--project, -R/--repo, --json, --no-color.
Project and repo are auto-detected from the git remote when inside a Space repository.
space mr — Merge requests
space mr view [REF] # MR details (number, URL, branch, or current branch)
space mr list # list MRs (-s open|closed|merged|all, -A author, -H branch)
space mr create BRANCH # create MR from branch (-t title, -b base, -d description)
space mr close [REF] # close an MR
space mr reopen [REF] # reopen a closed MR
space mr timeline [REF] # full timeline with discussions and dry run results
space mr checks [REF] # Patronus CI check status (--watch to poll)
space mr diff [REF] # diff between target and source (--stat, --name-only)
space mr checkout [REF] # fetch and checkout the MR branch
space mr merge [REF] # safe merge via Patronus (--rebase, --squash, --dry-run)
space mr download ID # download attachment by ID (-o output path)
space run — Patronus CI runs
space run list # list runs for current branch (-b branch, -B base)
space run view RUN # run details with TeamCity checks (UUID or URL)
space run start [REF] # start dry run (--merge, --rebase, --squash, --watch)
space run cancel RUN # cancel a running Patronus run
space run watch RUN # live progress with terminal animation
space auth — Authentication
space auth login # store token (--token, --insecure-storage)
space auth logout # remove credentials
space auth status # show token source and context
space api — Raw API access
space api /api/http/... # authenticated GET to Space
space api /app/rest/... --patronus # authenticated GET to Patronus
space api /api/http/... -X POST -f key=val # POST with JSON body
space status — Dashboard
space status # MR and latest CI run for current branch
Development
See CONTRIBUTING.md for development setup and testing.
License
Copyright 2026, Anna Zhukova
This project is licensed under MPL-2.0. The license text can be found at LICENSE.md.
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。