Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add saurprince/jenkins-mcp-server --skill jenkins-cicdgit clone --depth 1 https://github.com/saurprince/jenkins-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/saurprince/jenkins-mcp-server/jenkins-cicd)<a href="https://agentmods.dev/skills/saurprince/jenkins-mcp-server/jenkins-cicd"><img src="https://agentmods.dev/badge/skills/saurprince/jenkins-mcp-server/jenkins-cicd/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/saurprince/jenkins-mcp-server/jenkins-cicd"><img src="https://agentmods.dev/badge/skills/saurprince/jenkins-mcp-server/jenkins-cicd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.01273 |
| Opus 5.5 | $0.00026 | $0.00509 |
| Sonnet 5.5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
jenkins-cicd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jenkins CI/CD with jenkins-mcp-server
This skill tells you when and how to use the jenkins-mcp-server MCP tools
(PyPI package: jenkins-mcp-tools). It does not replace the server: the MCP
server must be installed and configured first (see Setup).
Setup
- Install:
pip install jenkins-mcp-tools - Create a Jenkins API token: Jenkins -> your username -> Configure -> API Token -> Add new Token.
- Register the server in your agent's MCP config (Cursor:
~/.cursor/mcp.json; Claude Code:claude mcp add):
{
"mcpServers": {
"jenkins": {
"command": "jenkins-mcp-server",
"args": ["--url", "https://jenkins.example.com", "--username", "USER", "--token", "TOKEN", "--mode", "read-only"]
}
}
}
- Verify:
jenkins-mcp-server --test --url ... --username ... --token ...
Prefer the environment variables JENKINS_URL, JENKINS_USERNAME, JENKINS_TOKEN,
JENKINS_MODE over putting the token in a shared config file. Never print, log, or
commit the token. Only use --no-verify-ssl / JENKINS_VERIFY_SSL=false for
self-signed internal servers, and tell the user you are doing so.
Access modes (check before acting)
| Mode | What it allows |
|---|---|
read-only |
Inspect only: jobs, builds, logs, tests, queue, nodes, views, plugins |
standard (default) |
Read tools + trigger_build, stop_build |
admin |
Everything, including create/delete/copy/update jobs, folders, replay |
If a tool returns a mode error, do not try to work around it. Tell the user which
mode is needed and let them decide whether to change it. Recommend read-only
for exploration and shared setups.
Which tool for which question
"What's the state of Jenkins / job X?"
list_jobs -> get_job_details -> get_build_info
"Why did build N fail?" (work from cheap to expensive)
get_build_info- result, duration, causeget_pipeline_stages- which stage failed (pipelines)get_test_report- failing tests and countsget_build_console- read the tail first (the failure is usually at the end), then page backwards if neededget_build_parameters- did a parameter cause it?
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 98 lines · 66 tokens per session scan A 24ebc5383aed
jenkins-cicd is a skill published in the GitHub repository saurprince/jenkins-mcp-server (1 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,273 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.
jenkins-cicd compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jenkins-cicdsaurprince/jenkins-mcp-server | Skill | 1 | 2d ago | MIT | A | 66 | Claude Code, Codex |
| chinese-git-workflowjnMetaCode/superpowers-zh | Skill | 8.5k | 12d ago | MIT | A | 69 | Claude Code |
| atmos-profilescloudposse/atmos | Skill | 1.4k | today | Apache-2.0 | A | 35 | Claude Code |
| webhook-managementhoangsonww/Claude-Code-Agent-Monitor | Skill | 1.2k | yesterday | MIT | A | 56 | Claude Code, Codex |
| monorepo-managementwshobson/agents | Skill | 42k | 2d ago | MIT | C | 54 | Claude Code |
| postman-newman-automationLambdaTest/agent-skills | Skill | 391 | 3d ago | MIT | A | 156 | Claude Code, Codex |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |