Codecov Connector for AI agents.
8 live capabilities
Monitor test coverage and software quality metrics for your code repositories.
Waiting for input…
Why people use Codecov
Codecov for Real-Time Engineering Metrics
This Connector lets you stay in your flow. You just ask your agent for the coverage of a specific SHA or a report tree, and the data appears right there. You get immediate answers without the context switching.
What Vinkius changes
You get instant access to your code quality metrics without leaving your IDE or chat window.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Verifying a specific commit
An engineer wants to know if a specific commit hit the target.
- Real-world use case 02
Identifying coverage gaps
A manager needs to see which folders are lagging.
- Real-world use case 03
Checking branch distribution
A developer is unsure about branch coverage.
Complete set · 8capabilities
The complete Codecov capability set.
These are the exact actions your AI can choose when you ask it to work with Codecov.
01—04
4 capabilities in this set.
Part of 8 available through Codecov.
- 01 Capability
Get commit coverage totals
Get the total coverage numbers for a specific commit SHA. This helps you verify if a build meets your quality gates.
- 02 Capability
List repository branches
See all the branches currently tracked in Codecov. Use this to check coverage across different development lines.
- 03 Capability
List repository commits
Get a list of recent commits and their coverage status. It's a fast way to see how recent changes affected your numbers.
- 04 Capability
List coverage flags
See all the coverage flags defined for a repository. This helps you understand how your team categorizes different test types.
05—08
4 capabilities in this set.
Part of 8 available through Codecov.
- 05 Capability
List codecov repositories
List every repository tied to your owner account. Use this to get a bird's eye view of your entire portfolio.
- 06 Capability
Get my codecov profile
Pull your own user profile and account details. Use this to check your permissions or personal settings.
- 07 Capability
Get repository coverage details
Get a deep dive into the coverage of a specific repository. It shows you the overall health of your project.
- 08 Capability
Get coverage report tree
See a hierarchical view of your coverage reports. This lets you see exactly which folders or files are missing tests.
Set up in minutes
One URL. Then ask Codecov to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Codecov from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_BhxY5dMcJ3daTaX2y9iBmjnp8uvuBDxG25b4pKhj/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Codecov, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Codecov for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_BhxY5dMcJ3daTaX2y9iBmjnp8uvuBDxG25b4pKhj/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Codecov URL.
- Step 03
Save and start
Save the connection and enable Codecov in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"codecov": {
"url": "https://edge.vinkius.com/vk_preview_BhxY5dMcJ3daTaX2y9iBmjnp8uvuBDxG25b4pKhj/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Codecov
Open Agent mode in chat and ask: "Using Codecov, help me...". 8 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"codecov": {
"url": "https://edge.vinkius.com/vk_preview_BhxY5dMcJ3daTaX2y9iBmjnp8uvuBDxG25b4pKhj/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Codecov
Ask Copilot: "Using Codecov, help me...". 8 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"codecov": {
"url": "https://edge.vinkius.com/vk_preview_BhxY5dMcJ3daTaX2y9iBmjnp8uvuBDxG25b4pKhj/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Codecov
Open Cascade and ask: "Using Codecov, help me...". 8 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"codecov": {
"url": "https://edge.vinkius.com/vk_preview_BhxY5dMcJ3daTaX2y9iBmjnp8uvuBDxG25b4pKhj/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Codecov
Ask Cline: "Using Codecov, help me...". 8 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add codecov --transport http "https://edge.vinkius.com/vk_preview_BhxY5dMcJ3daTaX2y9iBmjnp8uvuBDxG25b4pKhj/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Codecov
Ask Claude: "Using Codecov, show me...". 8 tools are ready
Where the request belongs
Work Codecov can move forward.
This is for the engineer who's tired of hunting through dashboards to see if a merge is safe or the manager who needs a quick pulse check on team coverage.
Software Engineer
Checks coverage on specific files before submitting a pull request to ensure they meet team standards.
Engineering Manager
Reviews high-level coverage trends across multiple repositories to identify areas needing more testing.
DevOps Engineer
Verifies build health and coverage totals for CI/CD pipelines directly from the terminal or chat.
QA Engineer
Audits test completeness and monitors coverage flags across different branches and platforms.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsCoveralls (Code Coverage Analytics API)
Track code coverage metrics via Coveralls. manage repositories, submit coverage reports, and monitor build statuses directly from your AI agent.
Code Climate
Manage code quality and engineering metrics via Code Climate. track repository grades, monitor snapshots, and audit test coverage directly from any AI agent.
DeepSource
Automate code quality monitoring via DeepSource. analyze issues, vulnerabilities, metrics, and report cards directly from any AI agent.
Codacy
Manage code quality and automated reviews via Codacy. track grades, monitor issues, and audit repository analysis directly from any AI agent.
Coverage Gate Evaluator
Enforce strict code coverage thresholds using deterministic integer math.
SonarCloud
Merge your SaaS DevOps workflow with SonarCloud to review AI code and prevent production vulnerabilities.
Bring your own AI
Change the model, client or framework. Keep Codecov connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Codecov.
The practical details behind the request, access and result.
Can the Codecov MCP show me specific file coverage?
Yes, it pulls the report tree so you can see exactly which folders and files are covered within your project.
How do I see coverage for a specific commit?
You can ask the agent to check a specific SHA to see the exact hits and misses for that build.
Can I use this to see all my repositories?
Yes, the Connector can list every repository tied to your account for a full overview of your portfolio.
Does this work for multiple branches?
It can list all branches and show you how coverage differs across them, making it easy to compare different workstreams.
Can I see my own profile info?
Yes, it can pull your user profile and account metadata directly into the chat for quick reference.
Is this for CI/CD automation?
It's a great way to get coverage data into your agent's context, which helps with monitoring and auditing during your development cycle.
Can I see the coverage percentage for a specific commit?
Yes! Use the get_commit_coverage_totals capability 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 capability. 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.
One connection away
Give your agent a direct line to Codecov.
Connect Codecov once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available