MCP-JaCoCo
MCP-JaCoCo is a server tool that converts JaCoCo code coverage reports into formats optimized for Large Language Models (LLMs), making AI-driven analysis easier and more effective.
Why It Matters
As AI and LLMs play a bigger role in software development, traditional code coverage reports—like those from JaCoCo—need a makeover. While great for humans, their XML format isn’t ideal for AI tools to process or analyze. MCP-JaCoCo bridges this gap by transforming these reports into LLM-friendly formats, unlocking powerful benefits for development teams:
- Quick, meaningful summaries of code coverage
- Easy identification of untested or poorly tested code
- Smart suggestions for new test cases
- Streamlined AI-assisted test planning
- Automated documentation of coverage results With MCP-JaCoCo, teams can tap into AI’s full potential, boosting efficiency and insight in testing workflows.
What It Solves
- Complex Formats: Simplifies JaCoCo’s dense XML reports for AI use
- Scattered Data: Pulls coverage metrics into one accessible place
- Slow Analysis: Cuts down on time-consuming manual reviews
- Integration Hurdles: Makes raw data play nicely with AI tools
Key Features
- Smart Conversion: Transforms JaCoCo XML reports into LLM-friendly JSON format
- Flexible Coverage Types: Supports multiple coverage metrics (instruction, branch, line, etc.)
- Efficient Processing: Fast and lightweight report processing
- Structured Output: Well-organized JSON format for easy AI consumption
- Customizable Analysis: Filter coverage data by specific metrics of interest
Installation
Install MCP-JaCoCo using uv with this configuration:
{
"mcpServers": {
"mcp-jacoco-reporter-server": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"/Users/crisschan/workspace/pyspace/mcp-jacoco-reporter/mcp-jacoco-reporter-server.py"
],
"env": {
"COVERED_TYPES": "nocovered, partiallycovered, fullcovered"
},
"alwaysAllow": [
"jacoco_reporter_server"
]
}
}
}
Tool
jacoco_reporter_server
- Reads JaCoCo XML report and returns coverage data in JSON format
- Input:
- jacoco_xmlreport_path: Path to JaCoCo xml report path(jacoco.xml)
- Return:
- String, formatted JSON data containing coverage metrics
Example output format:
[
{
"sourcefile": "PasswordUtil.java",
"package": "com/cicc/ut/util",
"lines": {
"nocovered": [],
"partiallycovered": []
},
"branch": {
"nocovered": [],
"partiallycovered": []
}
},
{
"sourcefile": "UserServiceImpl.java",
"package": "com/cicc/ut/service/impl",
"lines": {
"nocovered": [
33,
67,
69,
71,
72
],
"partiallycovered": []
},
"branch": {
"nocovered": [
67
],
"partiallycovered": [
32
]
}
},
{
"sourcefile": "Constants.java",
"package": "com/cicc/ut/constants",
"lines": {
"nocovered": [],
"partiallycovered": []
},
"branch": {
"nocovered": [],
"partiallycovered": []
}
},
{
"sourcefile": "AuthException.java",
"package": "com/cicc/ut/exceptions",
"lines": {
"nocovered": [],
"partiallycovered": []
},
"branch": {
"nocovered": [],
"partiallycovered": []
}
},
{
"sourcefile": "UserService.java",
"package": "com/cicc/ut/service",
"lines": {
"nocovered": [],
"partiallycovered": []
},
"branch": {
"nocovered": [],
"partiallycovered": []
}
}
]
Metadata
Release files for iflow-mcp_crisschan-server 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| iflow_mcp_crisschan_server-0.1.0.tar.gz | 18.6 kB | Without provenance | Details for iflow_mcp_crisschan_server-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| iflow_mcp_crisschan_server-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for iflow_mcp_crisschan_server-0.1.0-py3-none-any.whl |
Total release size: 27.5 kB
Release files / iflow_mcp_crisschan_server-0.1.0.tar.gz
| Download URL | iflow_mcp_crisschan_server-0.1.0.tar.gz |
|---|---|
| Size | 18.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cce24e4c538ce14f25c4831ac18e1cd633ff7f63e92d61dcd27f07670462a11f
|
|
BLAKE2b-256 checksum How to use checksums |
4420c05fb2708a75b6684442ce0d768ea72c81505131f765dafb1d37d6fd1ddb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / iflow_mcp_crisschan_server-0.1.0-py3-none-any.whl
| Download URL | iflow_mcp_crisschan_server-0.1.0-py3-none-any.whl |
|---|---|
| Size | 8.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
39917a26ba0d197fec0f258632b473bfa7a7134b012a0605b2ea9baaf49fee1e
|
|
BLAKE2b-256 checksum How to use checksums |
7e40c91adac40106667eda719cb27151c08ea964e7f679173c2122d9bcf0dc0a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for iflow-mcp_crisschan-server 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.