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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.