Coveralls MCP. Monitor code coverage and manage build status via your agent
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Coveralls (Code Coverage Analytics API) MCP Server tracks code coverage metrics for CI/CD. Manage repositories, submit detailed coverage reports, and monitor build statuses directly through your AI agent.
It lets you check coverage status, manage tokens across GitHub, GitLab, and Bitbucket, and even trigger build reruns without touching the dashboard.
What your AI agents can do
Close parallel build
Closes a parallel build sequence on Coveralls.
Create repo
Creates a new repository on Coveralls using your personal API token.
Get build web data
Gets JSON data representing a build's web page.
Create, retrieve, and update repository configurations and access tokens across GitHub, GitLab, and Bitbucket.
Send detailed coverage reports (jobs) including source file data and Git metadata to the Coveralls API.
Manage parallel CI workflows by triggering final aggregate calculations or closing build sequences.
Quickly trigger a build rerun to resolve temporary calculation issues without manual dashboard work.
Get structured JSON data for repository, job, or source file web pages for deep analysis.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Coveralls (Code Coverage Analytics API) MCP Server: 10 Tools for Code Health
These tools let your AI agent manage and analyze every part of your build lifecycle, from submitting reports to retrieving historical data.
019e5d0eclose parallel build
Closes a parallel build sequence on Coveralls.
019e5d0ecreate repo
Creates a new repository on Coveralls using your personal API token.
019e5d0eget build web data
Gets JSON data representing a build's web page.
019e5d0eget file web data
Gets JSON data representing a source file's web page.
019e5d0eget job web data
Gets JSON data representing a specific job's web page.
019e5d0eget repo
Retrieves core repository information from Coveralls.
019e5d0eget repo web data
Gets JSON data representing a repository's web page.
019e5d0ererun build
Triggers a full rerun of a build on Coveralls.
019e5d0esubmit job
Sends a detailed coverage report (job) to Coveralls, requiring file and Git metadata.
019e5d0eupdate repo
Updates existing repository settings on Coveralls.
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 Coveralls (Code Coverage Analytics API), 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
Coveralls API MCP Server - Code Coverage Analytics
Need to keep an eye on code quality without touching the dashboard? This server lets your AI client manage your whole CI/CD process and track code coverage metrics directly. You can manage your repositories, submit detailed reports, and even kick off build reruns—all through simple commands.
Managing Repositories
- You can
create_repoto set up a new repository on Coveralls using your personal API token. *You'll useget_repoto pull core information about any existing repository. *To keep things current, you canupdate_repoto change existing repository settings. *When you need to get the full web page data for a repository, you've gotget_repo_web_data. *If you just want to pull the core details,get_repodoes the trick. *You can also grab the web data for a source file usingget_file_web_dataor for a specific job usingget_job_web_data.
Submitting Coverage Reports
- You'll use
submit_jobto send a detailed coverage report (job) to Coveralls; this requires both file and Git metadata.
Controlling Builds
- You can
rerun_buildto trigger a full build rerun if the results look sketchy. *If you're dealing with parallel CI workflows, you canclose_parallel_buildto close a parallel build sequence and finalize the calculations.
Getting Data
- To deep-dive into the data, you can
get_build_web_datato get JSON data representing a build's entire web page. *For the full picture of a repository, you can useget_repo_web_data. *You've gotget_job_web_datato pull JSON data for a specific job's web page.
How Coveralls MCP Works
- 1 First, subscribe to the Coveralls server and enter your Personal Access Token.
- 2 Next, tell your AI agent what needs to happen—like submitting a job or checking a repo's status.
- 3 The agent runs the necessary tool calls, and you get back the current code coverage metrics or the requested data JSON.
The bottom line is you use your AI client to talk to the Coveralls API, letting it run the necessary build and data commands for you.
Who Is Coveralls MCP For?
This is for the DevOps Engineer who spends too much time clicking through CI/CD dashboards. It's for the Software Developer who needs to check coverage status directly from their IDE or terminal. If you're a QA Lead who has to manually analyze coverage regressions, this saves you hours of clicking.
Automate the setup of new repositories and monitor coverage trends across the entire organization's CI/CD pipelines.
Check coverage status and submit detailed reports without leaving the terminal or IDE.
Analyze coverage regressions and manage build thresholds to confirm code reliability.
What Changes When You Connect
- Submit full coverage reports directly. Use
submit_jobto send detailed coverage data (including source files and Git metadata) without running manual API scripts. - Manage entire CI/CD lifecycles. You can use
close_parallel_buildorrerun_buildto control complex build sequences and fix transient build errors on the fly. - See repository details instantly. Use
get_repoorget_repo_web_datato pull core repo info or full web data JSON when you need to analyze trends. - Analyze granular build components. Fetch specific web data for jobs or files using
get_job_web_dataorget_file_web_datato pinpoint exactly where coverage failed. - Automate repo setup. Use
create_repoandupdate_repoto set up and maintain repository configurations and tokens programmatically.
Real-World Use Cases
Debugging a Failed Build
A developer sees a build failure, but the cause is unclear. They ask their agent to run get_job_web_data and get_file_web_data. The agent returns the raw JSON, allowing the developer to pinpoint the exact source file and line number where the coverage dipped below threshold, solving the mystery without manual dashboard digging.
Onboarding a New Service
A DevOps engineer needs to track coverage for a new microservice. Instead of manually filling out forms, they ask the agent to run create_repo and then get_repo to get the basic structure and token setup for Coveralls immediately.
Fixing Stale Build Data
A build finishes, but the dashboard shows incomplete data. The QA lead tells the agent to run rerun_build. The agent triggers the re-calculation, and the lead gets the updated coverage metrics, confirming the data was stale.
Analyzing Historical Trends
A team wants to see how coverage has changed over the last quarter. They ask the agent to run get_repo_web_data to pull historical JSON records, which they then feed into their local analysis tool for trend mapping.
The Tradeoffs
Over-relying on the Dashboard
Manually logging into the Coveralls UI, navigating to the repo, clicking the job, and then manually downloading the file data. This takes too long and often misses the context you need.
→
Instead, use the agent to run get_repo_web_data to get the entire repo context, or use get_job_web_data to pull specific job metrics directly into your workflow.
Running Builds Manually
Waiting for a build to fail and then manually going to the dashboard to hit the 'Rerun' button. This adds delay and is easily forgotten.
→
Just ask the agent to run rerun_build. It handles the request and confirms the re-calculation is starting, giving you immediate status updates.
Partial Data Retrieval
Calling one tool (e.g., get_repo) to check the status, then needing file data, and calling a second tool (e.g., get_file_web_data). You lose the context between steps.
→
If you need to analyze the whole system state, let the agent orchestrate calls like get_repo followed by get_job_web_data to ensure all necessary data pieces are retrieved in one flow.
When It Fits, When It Doesn't
Use this if you need to programmatically interact with, analyze, or manage the state of your code coverage metrics. You must be able to send reports (submit_job) or programmatically check build status. Don't use this if you only need to view basic, high-level status information—a simple dashboard might suffice. If your goal is to audit repository structure or track historical data, get_repo_web_data is your key tool. If you just need to manage CI/CD tokens, create_repo handles that. Don't use it if you need a simple text summary; you're dealing with structured JSON data, which requires an agent to process.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Coveralls. 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 coverage status shouldn't require clicking through three different tabs.
Today, checking code coverage means logging into the dashboard, finding the right repository, navigating to the build, and then clicking through multiple pages—sometimes needing separate steps just to get the file list. It's slow, and you often end up with fragmented data.
With this MCP server, you talk to your agent. You ask for the coverage status, and the agent runs `get_job_web_data`. You get the structured JSON data you need, right in your terminal, without opening a single browser tab.
Coveralls (Code Coverage Analytics API) MCP Server: Submit Job Coverage Reports
Before this, submitting a new coverage report meant running complex, multi-step CLI scripts that had to pass dozens of parameters and were prone to breaking if a single metadata field was missing.
Now, you let your agent run `submit_job`. It handles the required `repo_token`, `source_files`, and Git metadata, making the process simple and reliable. You just tell it to run the report.
Common Questions About Coveralls MCP
How do I use `submit_job` to send a coverage report? +
You must provide the agent with the repository token, service name, job ID, source files, and git metadata. The agent packages this info and calls submit_job to push the report to Coveralls.
Can I check the status of a specific build using `get_job_web_data`? +
Yes. get_job_web_data fetches the JSON representation of a single job page. This lets your agent read the status and details programmatically.
What's the difference between `get_repo` and `get_repo_web_data`? +
get_repo gets core, basic repository info. get_repo_web_data provides a much richer, JSON representation of the entire repository web page, including detailed history and metadata.
How do I fix old build data using `rerun_build`? +
You simply ask the agent to run rerun_build. The agent triggers the processing rerun on Coveralls, and you wait for the re-calculated coverage data.
What do I need to use `create_repo` to track a new project? +
You need a personal API token. The create_repo tool handles setting up the repository on Coveralls, which is essential before you can submit any coverage reports.
If I need to get historical data, should I use `get_repo_web_data` or `get_build_web_data`? +
Use get_repo_web_data for general repository details and history. Use get_build_web_data specifically when you want to analyze the JSON representation of a single build's page.
How do I update repository settings using `update_repo`? +
update_repo lets you manage existing repository configurations. You use this to change things like the coverage threshold or access tokens without creating a whole new repo.
Can I use `get_file_web_data` to check source file details? +
Yes, get_file_web_data pulls the JSON data for a specific source file. This is useful for inspecting coverage details or metadata for individual pieces of code.
How do I retrieve my repository's secret token for CI configuration? +
Use the get_repo tool by providing the service (e.g., 'github') and repository name. The agent will return the repository details, including the repo_token needed for your CI environment variables.
Can I submit a coverage report for a specific CI job manually? +
Yes! The submit_job tool allows you to send coverage data directly. You'll need to provide the repo_token, service_name, service_job_id, and the source_files JSON array containing coverage metrics.
How do I finalize a parallel build once all individual jobs are finished? +
Use the close_parallel_build tool. Provide your repo_token and the build_num. This triggers Coveralls to aggregate all parallel jobs and calculate the final coverage percentage for the build.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Cloudflare Tunnel
Manage Cloudflare Tunnels directly from your AI agent — list, create, and configure secure Zero Trust connections to your private infrastructure.
Zoho CRM Admin
Manage Zoho CRM users, roles, profiles, layouts, territories, and tags — complete admin control through conversation.
Pinata Cloud
Automate IPFS pinning and decentralized storage via Pinata — manage files, JSON, and groups directly with AI.
You might also like
DottedSign
E-signature and document management with DottedSign.
Messenger
Control and manage your Facebook Page conversations — audit messages and personas via AI.
Scrapfly
Scrape web data at scale with a managed API that handles proxies, browser rendering, and anti-bot bypassing automatically.