- Home
- Skills
- DevOps & Cloud
- Jenkins MCP
Jenkins MCP
Diagnose failed builds, manage queues, and update Jenkins pipelines safely via MCP.
$29
Works with the AI Agents you already use
Jenkins MCP
Example session with this skill installed
Check why the 'auth-service/deploy-prod' job is stuck in the queue and see if there are any available nodes.
- Read your context and instructions
- Compiled the jenkins mcp
I have inspected the Jenkins queue and node status for the requested job.
Jenkins Queue and Node Audit
| Category | Detail | Value |
|---|---|---|
| Target Job | auth-service/deploy-prod | ID: 442 |
| Queue Status | Blocked | "Waiting for next available executor on 'production-slave'" |
| Queue Item ID | 9821 | Entered queue at 2023-10-27 14:02:10 UTC |
| Node: master | Online | 0/2 executors free (Building: gateway-service #102, api-docs #45) |
| Node: production-slave | Online | 0/4 executors free (Building: auth-service #441, db-migration #12, heavy-test #9, cleanup #2) |
| Node: build-agent-01 | Offline | Disconnected by admin: "Disk space low" |
Assessment
The job is blocked because the required label production-slave is at full capacity (4/4 executors active). Additionally, one general-purpose build agent is offline, causing overflow contention on the remaining nodes. Confidence: High.
Next steps
- Authorize bringing
build-agent-01back online if disk space has been cleared. - Wait for
auth-service #441to complete (currently at 85% progress) to free an executor. - Optionally cancel the
cleanup #2task if the production deployment has higher priority.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing Jenkins at scale through a chat interface often leads to blind retries, credential leaks, or destructive configuration overwrites. This skill provides a systematic approach for interacting with Jenkins via an MCP server, ensuring every action is grounded in live state rather than assumptions. It enforces a strict "read-before-write" workflow to prevent duplicate builds and accidental data loss.
What it does
- Root cause analysis parses build logs from byte offsets to identify the earliest causal failure in the pipeline.
- Queue troubleshooting inspects specific queue items and node capacity to explain why a job is pending or blocked.
- Safe build triggering handles parameterized jobs, monitors queue IDs, and tracks progress through to terminal status.
- Infrastructure management allows for updating pipeline XML, offlining nodes, or stopping builds with explicit authorization gates.
- State verification reads back job and node configurations after changes to confirm the intended effect was achieved.
How it works
- Scope discovery uses
list_jobsandget_jobto resolve the exact folder-qualified path of the target project. - Evidence collection retrieves build info, console logs, or queue state to build a diagnostic context.
- Change authorization prepares a reviewable diff or parameter set and waits for explicit user approval before execution.
- Action execution performs the trigger, update, or stop command using the verified ID or configuration XML.
Frameworks & tools
Specifically designed for the grglzrv/jenkins-mcp-server. It interacts with Jenkins pipelines, multibranch jobs, and node infrastructure via the Jenkins remote API.
Why this beats prompting it yourself
Generic prompts often guess build numbers or hallucinate pipeline syntax that breaks your XML configuration. This skill follows a specific sequence to correlate queue IDs with build numbers, ensuring you never lose track of a triggered job or overwrite a config without a backup.
Use cases
- Diagnose why a specific CI build failed and identify the exact failing stage.
- Resolve "pending" status by checking node labels and executor availability.
- Update Jenkinsfile pipeline scripts or job XML configurations safely.
- Trigger deployments with specific parameters and follow the progress to completion.
Known limitations
Requires an active Jenkins MCP server connection and pre-configured Jenkins access. It cannot recover deleted jobs without external backups and does not support bypassing server-side permissions.
Requires a connected Jenkins MCP server. Cannot recover deleted jobs without external backups. Access is limited to jobs visible to the provided credentials and server allowlist.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 26 days ago
Requires