Codecov MCP. Audit code quality and coverage totals in chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Codecov MCP Server manages test coverage and engineering metrics. You can pull detailed coverage reports, list all repos, check coverage totals for specific commits, and audit code quality right from your agent.
It lets you track exactly what part of the code is covered and what's missing without leaving your chat client.
What your AI agents can do
Get commit coverage totals
Gets the overall coverage score and metrics for a specific commit SHA.
Get coverage report tree
Retrieves the full coverage report, structured like the project's file directory.
Get my codecov profile
Gets information about the authenticated user linked to the Codecov account.
Retrieves a list of all repositories connected to the Codecov account, showing key details like current coverage percentage.
Calculates and retrieves the overall coverage score and metrics for a specific commit SHA.
Retrieves the full coverage report in a file structure tree, allowing you to see coverage per folder or component.
Retrieves comprehensive metadata for a single repository, including its owner and service provider.
Monitors coverage metrics across specific branches or custom coverage flags defined in the project.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Codecov MCP Server: 8 Tools for Code Quality Reporting
Use these tools to query and analyze code coverage data, listing repositories, checking commit totals, and auditing file structures via natural language prompts.
019d7576get commit coverage totals
Gets the overall coverage score and metrics for a specific commit SHA.
019d7576get coverage report tree
Retrieves the full coverage report, structured like the project's file directory.
019d7576get my codecov profile
Gets information about the authenticated user linked to the Codecov account.
019d7576get repository coverage details
Gets detailed coverage metrics for a specific, named repository.
019d7576list codecov repositories
Lists all repositories associated with the Codecov owner account.
019d7576list coverage flags
Lists all custom coverage flags set up for a repository.
019d7576list repository branches
Lists all branches that Codecov is currently tracking.
019d7576list repository commits
Lists recent commits and their corresponding coverage status.
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 Codecov, 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
You're gonna get full control of your test coverage and engineering metrics through your AI agent. This server lets you check what parts of your code are covered and what's missing, all without leaving your chat client. You can pull detailed coverage reports and audit code quality right from your agent.
list_codecov_repositories lets you pull a list of every repo connected to your Codecov account, showing key details like the current coverage percentage for each one. get_repository_coverage_details pulls comprehensive metadata for a specific repo, including the owner and service provider. list_repository_commits shows you recent commits and what their corresponding coverage status is. get_commit_coverage_totals calculates and gives you the overall coverage score and metrics for a specific commit SHA. get_coverage_report_tree retrieves the full coverage report, structured exactly like your project's file directory, so you can see coverage per folder or component. get_my_codecov_profile pulls info about the user linked to your Codecov account. list_repository_branches tracks coverage metrics across specific branches, and list_coverage_flags lets you list all custom coverage flags set up for a repo.
How Codecov MCP Works
- 1 Subscribe to the server and paste your Codecov Global API Token.
- 2 Ask your AI agent a question, like 'What's the coverage for the main branch of the core-api repo?'
- 3 The agent runs the necessary tool (e.g.,
list_repository_branchesorget_commit_coverage_totals) and gives you a direct answer.
The bottom line is that you talk to your agent, and it uses Codecov's data to answer questions about your code's quality.
Who Is Codecov MCP For?
This is for the software engineer who needs instant feedback on code quality, or the DevOps engineer who needs to verify build health without opening a dashboard. If you spend too much time clicking between dashboards to check coverage, this is for you.
Checks coverage changes and audits specific file reports using natural language prompts. They verify if a feature branch meets the required test standards.
Quickly looks up commit coverage totals and verifies build status directly from the chat interface, eliminating the need to jump to the CI dashboard.
Reviews team coverage trends and repository health by asking high-level questions, rather than running reports for individual team members.
What Changes When You Connect
- See the full picture of your codebase. Instead of guessing, use
list_codecov_repositoriesto list every connected repo and see its current coverage percentage immediately. - Verify build health on the fly. When you need to know if a commit passed testing, run
get_commit_coverage_totalsto get the overall score and hit/miss count for that SHA. - Drill down into failures. Use
get_coverage_report_treeto see exactly which folder or file is missing test coverage, giving you the precise spot to fix. - Track multiple lines of code. Check coverage across different branches or specific flags using
list_repository_branchesandlist_coverage_flags. - Know your project boundaries. Use
get_repository_coverage_detailsto pull detailed metadata, like the service provider or owner, without navigating to the web UI.
Real-World Use Cases
Checking a new feature's readiness
A developer just merged a PR to core-api. They ask their agent: 'What's the coverage for the latest commit in core-api?' The agent runs get_commit_coverage_totals and confirms the SHA has an 85.4% overall coverage, verifying the build passed testing thresholds.
Investigating a slow build failure
The DevOps engineer sees a build fail and suspects insufficient testing. They use list_codecov_repositories to check all 5 repos, quickly identifying that web-frontend is the only one below 90% coverage. They then use get_repository_coverage_details to get the owner and service provider info.
Comparing branch quality
A QA engineer needs to know if the staging branch is stable. They ask the agent to list branches (list_repository_branches) and check the coverage for the 'staging' branch using get_coverage_report_tree. This lets them verify test completeness before release.
Auditing repository scope
A manager needs to know what repos the team is responsible for. They use list_codecov_repositories to get the full list of owned repositories and confirm all necessary services are accounted for.
The Tradeoffs
Guessing the overall coverage.
Opening the Codecov dashboard and scrolling through multiple tabs to manually find the total coverage score for a repo.
→
Just ask your agent. Use get_repository_coverage_details or list_codecov_repositories to pull the current percentage instantly into your chat.
Assuming all code is covered.
Merging code and assuming the tests cover everything, only to find a critical bug in production later.
→
Before merging, check the detailed file structure using get_coverage_report_tree to pinpoint exactly which folder or function is under-tested.
Ignoring branch differences.
Checking the main branch coverage and assuming the feature branch has the same quality.
→
Always check the specific branch coverage using list_repository_branches and then query the detailed report for that branch.
When It Fits, When It Doesn't
Use this if you need a single source of truth for code quality metrics. You need to know if a specific commit, branch, or repository meets a threshold before merging. It's best for automated gatekeeping and quick auditing. Don't use this if you just need to see a single metric—use the native Codecov dashboard. If you need to analyze historical data trends across years, you might need a separate data warehousing tool. However, if the data source is Codecov, this MCP Server is the most direct way to get actionable coverage data.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Codecov. 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 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Checking code coverage used to mean clicking through five different dashboards.
Today, checking coverage is a nightmare. You have to jump to the Codecov site, select the repo, find the branch, and then click through commit details, the file tree, and the coverage percentage. You end up copy-pasting numbers between Slack and Jira just to prove a point.
With Codecov MCP, you just ask your agent. You want to know the coverage for a specific branch? You ask. You want the commit total? You ask. The agent runs the right tool and spits out the number right here in your chat.
Codecov MCP Server: Audit code quality from your chat.
You no longer need to open the Codecov UI or juggle multiple tabs. You ask the agent to list all repositories, and it gives you the current coverage percentages for every repo instantly. You can then ask for the detailed report tree for just one of them.
It makes the entire process atomic. You get the data, you review it, and you move on. No more context switching. That's the difference.
Common Questions About Codecov MCP
How do I use the `get_commit_coverage_totals` tool with Codecov MCP Server? +
You provide the specific commit SHA (e.g., 'abc1234'). The agent runs the tool and returns the overall coverage percentage, hits, and misses for that exact commit.
What is the difference between `list_codecov_repositories` and `get_repository_coverage_details`? +
Listing repositories shows a summary of all repos. get_repository_coverage_details pulls deep, specific metadata and coverage details for one single, named repository.
Can I check coverage for a branch using Codecov MCP Server? +
Yes. You can first use list_repository_branches to see available branches, and then ask for the report tree or coverage totals for the specific branch name.
Does Codecov MCP Server support custom coverage flags? +
Yes. You can use list_coverage_flags to see what custom flags are defined for a repository, helping you focus your audit on specific quality areas.
How do I use `get_coverage_report_tree` to understand file structure coverage? +
The get_coverage_report_tree tool returns a hierarchical view of your coverage report, matching your project's file structure. This lets you pinpoint exactly which directories or components are lacking test coverage.
Can I list all available coverage flags using `list_coverage_flags`? +
Yes, list_coverage_flags retrieves all custom flags defined for a repository. You can use this list to check coverage distribution across specific, custom criteria.
What information does `list_repository_commits` provide regarding coverage? +
list_repository_commits shows recent commits and their associated coverage status. This helps you quickly verify if a specific commit meets your team's coverage standards.
What does `get_my_codecov_profile` retrieve for user context? +
get_my_codecov_profile retrieves core metadata about the authenticated user. This allows your AI agent to identify who is running the checks or who owns the repository being analyzed.
Can I see the coverage percentage for a specific commit? +
Yes! Use the get_commit_coverage_totals tool with the commit SHA. The agent will return the aggregate coverage percentage, hits, misses, and other metrics for that specific version of the code.
How do I check the coverage distribution across my project's folders? +
Use the get_coverage_report_tree tool. Your agent will fetch a hierarchical view of the report, showing you exactly which directories have high coverage and which need more tests.
Where do I find my Codecov API Token? +
Log in to your Codecov account, go to Settings, and select Access. You can generate and copy a new API token from the 'Tokens' section.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Cronitor (Cron Monitoring)
Monitor cron jobs, heartbeats, and websites. Track performance, receive alerts, and manage uptime directly from your AI agent.
Smithery
AI MCP registry: discover, search, and connect MCP servers to your agents via Smithery.
Markdown Frontmatter Harvester
Scan local Obsidian or Hugo vaults and extract all YAML frontmatter (tags, dates, status) into a single structured JSON. Let your AI query your scattered notes metadata instantly.
You might also like
Impala
Search hotels, check availability, compare rates, and browse reviews through a unified global hotel data platform via natural conversation.
Novu
Automate multi-channel notifications via Novu — trigger workflows, manage subscribers, and handle preferences directly from any AI agent.
EOD Historical Data
Access global financial market data — historical EOD, intraday, real-time prices, and deep fundamentals for stocks, ETFs, and indices.