🚀 PipelineIQ: CI/CD Intelligence Layer
PipelineIQ is a high-performance Model Context Protocol (MCP) server that empowers LLMs to diagnose CI/CD failures with surgical precision. By bridging the gap between raw logs and actionable insights, PipelineIQ slashes MTTR and eliminates context-switching fatigue for modern DevOps teams. 🛠️
⚡ TL;DR
Stop hunting through Jenkins console output. PipelineIQ gives your LLM (Claude, GPT) direct, structured access to Jenkins logs, offering automated Failure Pattern Detection and Sensitive Data Redaction to get your builds back to green faster and safer. 🚀
✨ Core Features
🔍 Advanced Log Pattern Matching
PipelineIQ doesn't just "read" logs—it analyzes them across a vast tech stack:
- Liferay / OSGi: Bundle resolution and Blade CLI deployment errors.
- Java / Spring Boot: Compilation, dependency conflicts, and bean creation failures.
- Node.js / React: ESLint violations, Vite/Webpack compilation, and Hydration mismatches.
- Python / Django / FastAPI: Import errors, migration conflicts, and Pydantic validation.
- Infrastructure: Out-of-memory (OOM) kills, timeouts, and Docker build failures.
🛡️ Built-in Security (Log Redaction)
PipelineIQ automatically redacts sensitive information (passwords, API tokens, keys) from build logs before they are sent to the LLM, ensuring your secrets stay private.
🤖 Industry-Standard MCP
Built on FastMCP, PipelineIQ follows the latest Model Context Protocol standards, providing:
- Recursive Job Discovery: Navigate deep Jenkins folder structures with ease.
- Standardized Tools:
list_jobs,list_builds,get_build_info,get_build_log,analyze_failure, andget_suggestions. - Diagnostic Prompt: A pre-defined
debug-failureprompt to guide AI agents. - Patterns Resource: Access internal failure patterns via
patterns://config.
🛠️ Tool Reference
| Tool | Purpose |
|---|---|
list_jobs |
Discover Jenkins jobs and folders (sorted by latest activity). |
list_builds |
List history for a specific job. |
get_build_info |
Get metadata (status, duration, timestamp) for a build. |
get_build_log |
Fetch and sanitize console output. |
analyze_failure |
Detect known failure patterns in logs. |
get_suggestions |
Get actionable fix instructions for detected patterns. |
🚀 Quick Start (using uvx)
No installation required! Run PipelineIQ instantly using uvx:
uvx pipeline-iq
🔑 Jenkins API Token Setup
Follow these steps to generate a secure API token:
-
Generate Token:
- Log in to your Jenkins dashboard.
- Click on your Username (top right) > Configure.
- Locate the API Token section and click Add new Token.
- Provide a name (e.g.,
PipelineIQ) and click Generate. - IMPORTANT: Copy the token immediately; it will not be shown again.
-
Required Permissions: PipelineIQ requires the following Read-Only permissions (using Matrix Authorization or Role-Based Strategy):
- Overall:
Read - Job:
Read,Extended Read(to view logs) - View:
Read
- Overall:
[!TIP] Always follow the Principle of Least Privilege. Use a dedicated service account if possible rather than your personal admin account.
⚙️ Installation & Configuration
Recommended: Install via pip
pip install pipeline-iq
From Source
# Clone the repo
git clone https://github.com/dev-joshi-ops/PipelineIQ.git
# Initialize virtual environment
python -m venv venv
source venv/bin/activate # Windows: .\venv\Scripts\activate
# Install dependencies (Editable Mode)
pip install -e .
# OR run instantly using uv (no manual install needed)
uv run pipeline-iq
Environment Configuration 🔒
Create a .env file in the root directory or export these variables:
| Variable | Required | Default | Description |
|---|---|---|---|
JENKINS_URL |
Yes | — | Base URL of Jenkins server |
JENKINS_USER |
Yes | — | Jenkins username |
JENKINS_TOKEN |
Yes | — | Jenkins API token (read-only) |
LOG_LEVEL |
No | INFO |
Logging verbosity (DEBUG, INFO, etc.) |
MAX_LOG_LINES |
No | 2000 |
Max lines to retrieve from build log |
REQUEST_TIMEOUT |
No | 30 |
HTTP request timeout in seconds |
Example .env:
JENKINS_URL=https://jenkins.yourdomain.com
JENKINS_USER=admin
JENKINS_TOKEN=your_api_token_here
🔌 Client Configuration (Recommended: uvx)
The easiest way to use PipelineIQ is with uvx.
1. Claude Desktop
Edit your claude_desktop_config.json (Windows: %APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"pipeline-iq": {
"command": "uvx",
"args": ["pipeline-iq"],
"env": {
"JENKINS_URL": "https://your-jenkins-url",
"JENKINS_USER": "your-username",
"JENKINS_TOKEN": "your-api-token"
}
}
}
}
2. Antigravity
Edit your mcp_config.json (Windows: %APPDATA%\.gemini\antigravity\mcp_config.json):
{
"mcpServers": {
"pipeline-iq": {
"command": "uvx",
"args": ["pipeline-iq"],
"env": {
"JENKINS_URL": "https://your-jenkins-url",
"JENKINS_USER": "your-username",
"JENKINS_TOKEN": "your-api-token"
}
}
}
}
⚙️ Development Setup (Manual)
If you want to contribute or run from source:
# Clone the repo
git clone https://github.com/dev-joshi-ops/PipelineIQ.git
# Initialize virtual environment
python -m venv venv
source venv/bin/activate # Windows: .\venv\Scripts\activate
# Install dependencies (Editable Mode)
pip install -e .
✍️ About the Author
Built with <3 by Dev Joshi
📄 License
MIT © 2026 PipelineIQ
Metadata
Release files for pipeline-iq 0.1.2
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 | |
|---|---|---|---|---|
| pipeline_iq-0.1.2.tar.gz | 23.4 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pipeline_iq-0.1.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 46.6 kB
Release files / pipeline_iq-0.1.2.tar.gz
| Download URL | pipeline_iq-0.1.2.tar.gz |
|---|---|
| Size | 23.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e233203939e6ed9723e3206e5f4b397f4eb44427e3663e2f0be13b18b30a29b8
|
|
BLAKE2b-256 checksum How to use checksums |
44524a7bc521e3b58e6ba1c1c5b201078b39e06b2572783f0a40bef0971a5976
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.6 {"installer":{"name":"uv","version":"0.11.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / pipeline_iq-0.1.2-py3-none-any.whl
| Download URL | pipeline_iq-0.1.2-py3-none-any.whl |
|---|---|
| Size | 23.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fa15dd8f5b26c6d2d5773188204bc14643b9e16ab72807f4a59d245a300b0ec2
|
|
BLAKE2b-256 checksum How to use checksums |
418237306473ab602036172cfe9c08a99431a6d6caecba2b6600869600a34b49
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.6 {"installer":{"name":"uv","version":"0.11.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for pipeline-iq 0.1.2
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.