Gitee MCP. Manage repos, issues, and code from your agent.
Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Gitee MCP Server manages your entire development lifecycle. Use your AI client to list repositories, check commit history, and track bugs without opening the web browser.
Your agent can create new issues, manage pull requests, and retrieve file contents instantly. It’s your command line for all Gitee projects.
What your AI agents can do
Create issue
Creates a new issue within a specified repository.
Create pull request
Creates a new pull request to merge code changes.
Create repo
Creates a brand new repository on Gitee.
Get the actual text content of any file or directory structure in a repository.
List all commits and changes across a repository's branches and branches.
List, filter, and create new issues to keep development tasks and bugs organized.
List and create pull requests to manage code review and merging processes.
List all repositories tied to your authenticated user account.
Ask AI about this MCP
Supported MCP Clients
Waiting for input…
Gitee MCP Server: 10 Tools for Code Management
Use these tools to interact with Gitee's core features—from creating issues to listing commit history—all through your natural language agent.
019d8440create issue
Creates a new issue within a specified repository.
019d8440create pull request
Creates a new pull request to merge code changes.
019d8440create repo
Creates a brand new repository on Gitee.
019d8440get file content
Retrieves the actual text content for a specific file path in a repository.
019d8440get repo
Fetches detailed metadata for a single repository.
019d8440get user
Retrieves the authenticated user's profile information.
019d8440list pull requests
Lists all pull requests for a given repository.
019d8440list repo commits
Lists the commit history for a specific repository.
019d8440list repo issues
Lists issues associated with a specific repository.
019d8440list user repos
Lists all repositories belonging to the connected user.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Gitee, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Your AI client handles all your Gitee stuff. You'll manage your whole dev lifecycle right from your prompt. You don't gotta open the web browser for status updates or to make records. Your agent acts like a real-time dev assistant, keeping your projects moving and your code organized.
View User Projects: Your agent uses list_user_repos to show you all the repos attached to your account. You can get detailed info on a single repo with get_repo, and you can even create_repo to spin up a brand new one.
Manage Codebase Files: If you need the actual text from a file, get_file_content pulls it for you, no matter how deep the file path is.
Audit Development History: You can check the commit history for any repo using list_repo_commits to track all the changes. You can also get a list of issues for a repo with list_repo_issues.
Control Code Review Flow: To manage code review, your agent uses list_pull_requests to show all open PRs, and you can use create_pull_request to start a new one. You can also create_issue to file a new bug or task.
How Gitee MCP Works
- 1 Subscribe to the server and provide your Gitee Personal Access Token (PAT).
- 2 Connect the Gitee MCP Server to your AI client (e.g., Claude or Cursor).
- 3 Ask your agent a command: 'List all my repositories on Gitee.' The agent executes the tool and returns the data.
The bottom line is, your AI client handles the API calls to Gitee and presents the results directly in the chat interface.
Who Is Gitee MCP For?
The software developer who gets frustrated clicking through dozens of tabs just to see if a feature was merged. The project manager who needs a quick status report on 50 bugs across 10 teams. This is for anyone whose job involves coordinating complex software development cycles.
Use the server to list repos, get file contents, and audit commit logs without leaving their terminal.
Run checks against list_repo_commits and list_user_repos to ensure all environment setup is complete before deployment.
Use the agent to track development progress by listing issues and monitoring pull request status via natural language queries.
What Changes When You Connect
- See your entire project roster with
list_user_repos. You don't have to manually check every project dashboard to know what's active. - Get instant code context. Instead of browsing directories to find a file, use
get_file_contentto pull the README or source code right into your chat. - Audit changes with
list_repo_commits. You can track exactly who changed what, and when, across any branch history. - Streamline code reviews by listing and creating pull requests using
list_pull_requestsandcreate_pull_request. The whole process is conversational. - Keep bugs and tasks organized. Quickly create or list issues using
create_issueandlist_repo_issueswithout switching applications. - Manage the project structure. You can create new repositories with
create_repowhen a new feature branch needs a home, all from a simple prompt.
Real-World Use Cases
Onboarding a New Feature Branch
A developer needs to start a new service. They ask their agent: 'I need a new repo for the billing service.' The agent uses create_repo to spin up the empty project. They then use get_repo to confirm the details, getting the project ready for development instantly.
Debugging a Reported Bug
A QA tester finds a bug. They ask the agent to 'Create an issue in the auth repo titled 'Login fails on mobile'.'. The agent uses create_issue. Next, they ask the agent to run list_repo_commits to see if a fix was deployed since the issue started.
Reviewing a Major Code Change
A team lead needs to review a PR. They ask the agent to 'List all open pull requests for the core service.' The agent uses list_pull_requests. They can then ask the agent to get_file_content for the specific files mentioned in the PR to review the code without leaving the chat.
Checking Project Status Before a Meeting
A PM needs an update. They ask the agent: 'What are the 3 highest priority issues in the marketing site repo?'. The agent uses list_repo_issues and filters the results, giving the PM an immediate, actionable status report.
The Tradeoffs
Treating Gitee like a document repository
Manually opening the web UI, clicking 'Files', finding the branch, and then copying the README content into a document for review. This is slow and prone to missing version context.
→
Use get_file_content to pull the file content directly into your chat. You get the exact, current version of the code or documentation without the UI friction.
Forgetting the commit history
A developer sees a bug fix but assumes it was done last week. They have to guess or ask a teammate for the exact commit ID, which wastes time.
→
Run list_repo_commits to see a full, auditable timeline of changes. You know exactly when the fix went in and who signed off on it.
Ignoring PR status
A developer finishes a feature and pushes the code, but doesn't know if it's ready to merge. They must wait for a manual review cycle, leading to stalled work.
→
Use list_pull_requests to check the status of all open PRs. You can then create_pull_request to formally open the review cycle immediately.
When It Fits, When It Doesn't
Use this if your workflow requires coordinating multiple distinct Gitee actions (e.g., 'list issues, then get file content, then create a PR'). It's best for developers and ops engineers who need to maintain a strict process around code state.
Don't use this if you just need to view a single piece of data (e.g., just checking the repo name). Use a simple API client or the native Gitee UI. This server is for action and workflow management, not just passive viewing. If your goal is to read documentation, use get_file_content—don't try to read the whole repo history at once.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Gitee. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Checking code status shouldn't require three different tabs.
Today, checking a project status means navigating to the repo dashboard, clicking 'Issues' to see the bug count. Then you jump to 'Pull Requests' to see if the fixes are pending review. Finally, you might click 'Commits' just to see which commit introduced the bug. This is a painful sequence of clicks and context switches.
With the Gitee MCP Server, you just ask your agent: 'What's the status of the authentication service?' It runs `list_repo_issues` and `list_pull_requests` and spits out a unified, conversational report. The whole process happens in the chat.
Gitee MCP Server: Manage Code History and Issues
You no longer have to switch between the Issues tab to see a bug and the Commits tab to see the fix. You can use `list_repo_issues` to track the bug, and then `list_repo_commits` to see the exact commit that resolved it. The tools work together in one prompt.
It's about continuous context. You get a unified view of the problem, the fix, and the official record of the change. That's the difference.
Common Questions About Gitee MCP
How do I use the `list_user_repos` tool with Gitee MCP Server? +
It lists all repositories attached to your Gitee account. Use it when you need to see a list of all projects you have access to before targeting a specific one.
Can I create an issue using the `create_issue` tool? +
Yes, you can. You just need to tell the agent the target repository name and the title/body of the issue. It handles the API call for you.
What is the best way to check commit history with `list_repo_commits`? +
You must specify the target repository and the branch you want to check. The agent needs this context to fetch the correct commit log.
Does `get_file_content` show the current version of a file? +
Yes, it retrieves the exact content of the file at the specified path. This is crucial for confirming what code is actually in the repository.
How do I manage pull requests using `list_pull_requests`? +
You use list_pull_requests to see which PRs are open. Then, you can use create_pull_request to formally open a review cycle.
What is the purpose of the `get_user` tool in the Gitee MCP Server? +
The get_user tool retrieves your authenticated profile details. This allows your agent to confirm who's running the task, which is helpful for auditing or knowing the user's team affiliation.
How do I handle errors or rate limits when using `list_repo_issues`? +
The server handles standard API rate limits with specific HTTP error codes. When you hit a limit, your AI client receives the error, and you can ask your agent to wait and retry later.
Can I use `create_repo` if I don't know the full name of the organization? +
You must specify the full, correct name of the repository or organization for create_repo to work. The tool requires a fully qualified name to prevent naming conflicts.
How do I find my Gitee Personal Access Token? +
Log in to Gitee, go to Settings -> Personal Access Tokens, and click 'Generate new token'. Make sure to copy it immediately as it won't be shown again.
Can I read the content of a file in a private repository? +
Yes, as long as your Personal Access Token has the necessary permissions (scopes) to access your private repositories, the get_file_content tool will work perfectly.
Is it possible to filter issues by their state? +
Yes. When using list_repo_issues, you can provide an optional state parameter (e.g., 'open', 'closed', or 'all') to filter the results according to your needs.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Relay Workflow Automation
List, run, and manage workflow automations via Relay API.
DummyJSON
Access a comprehensive suite of dummy data for testing and prototyping — products, carts, and user authentication directly from your AI agent.
api.video
Host, encode, and stream video content with a developer-first API that handles everything from upload to playback.
You might also like
Equinix Metal
Manage Equinix Metal API keys, email settings, and project invitations directly from your AI agent.
Zoho CRM Service
Manage support cases and knowledge base solutions — customer service operations through Zoho CRM.
emfluence Marketing
Equip your AI agent to manage marketing emails, track contact groups, and monitor performance via the emfluence API.