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 agentmods add instructions/zwitbaum/mcp-devops-on-prem/claude-mdgit clone --depth 1 https://github.com/zwitbaum/mcp-devops-on-premWrote 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/instructions/zwitbaum/mcp-devops-on-prem/claude-md)<a href="https://agentmods.dev/instructions/zwitbaum/mcp-devops-on-prem/claude-md"><img src="https://agentmods.dev/badge/instructions/zwitbaum/mcp-devops-on-prem/claude-md.svg" alt="Measured on agentmods" 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 | $0.01257 | $0.01257 |
| Opus 5 | $0.00629 | $0.00629 |
| Sonnet 5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
mcp-devops-on-prem CLAUDE.md 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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP DevOps On-Premise
Project context for recommenders and repository analysis tools.
Component Metadata
- Name:
mcp-devops-onpremise - Display name:
DevOps On-Premises - Type:
mcp-server - Primary language:
Python - Runtime:
uv - SDK:
FastMCP - License:
Apache-2.0 - Repository:
https://github.com/zwitbaum/mcp-devops-on-prem - Docs:
https://zwitbaum.github.io/mcp-devops-on-prem - Entrypoint:
mcp_devops:main - CLI:
mcp-devops-onpremise - Target system:
Azure DevOps Server / TFS (on-prem) - Plugin status: not a native Claude plugin package; connect as an MCP server
Connection and Auth
- Default transport:
stdio - Optional transport:
streamable-http/http - HTTP endpoint:
/mcp - Default local HTTP URL:
http://127.0.0.1:8000/mcp - Required env:
DEVOPS_API_URL - Auth mode rule: configure exactly one mode
- NTLM:
DEVOPS_USERNAME+DEVOPS_PASSWORD - PAT:
DEVOPS_PAT - Bearer token:
DEVOPS_TOKEN - Optional runtime env:
MCP_TRANSPORT,MCP_HOST,MCP_PORT,MCP_PATH,DEVOPS_AUTH_DEBUG
Codebase Anchors
src/mcp_devops/__init__.py: CLI entrypoint, transport parsing, startup validationsrc/mcp_devops/shared.py: FastMCP instance, auth selection, config validation, REST helperssrc/mcp_devops/tools/pull_request_tools.py: pull request and thread/comment toolssrc/mcp_devops/tools/repository_tools.py: repository, commit, diff, and file toolssrc/mcp_devops/tools/work_item_tools.py: work item CRUD, WIQL, comments, links, attachmentssrc/mcp_devops/tools/wiki_tools.py: wiki page toolstests/: pytest unit and smoke testsmanifest.json: MCP-facing metadata and tool descriptions
Exposed Tool Groups
- Repositories: list repos, get repo details, list commit changes, diff commits, read file content, line-level diff
devops_repository_listdevops_repository_getdevops_repository_commit_changesdevops_repository_diffs_commitsdevops_repository_item_contentdevops_get_item_content_diff
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.
- 4d ago First seen · 111 lines · 1,257 tokens per session scan A b2b1bea5a82e
mcp-devops-on-prem CLAUDE.md is an instructions file published in the GitHub repository zwitbaum/mcp-devops-on-prem (0 stars, last pushed today), licensed Apache-2.0. It adds 1,257 tokens to every session, about $0.0063 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.