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/octopusdeploy/mcp-server/claude-mdgit clone --depth 1 https://github.com/OctopusDeploy/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/instructions/octopusdeploy/mcp-server/claude-md)<a href="https://agentmods.dev/instructions/octopusdeploy/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/octopusdeploy/mcp-server/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 | $0.02878 | $0.02878 |
| Opus 5 | $0.01439 | $0.01439 |
| Sonnet 5 | $0.00576 | $0.00576 |
| Haiku 4.5 | $0.00288 | $0.00288 |
Grade A, and why
mcp-server 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 5d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Overview
This is the Octopus Deploy Official MCP Server, which provides Model Context Protocol (MCP) tools that allow AI assistants like Claude Code to interact with Octopus Deploy instances. The server is implemented in TypeScript as a Node.js application.
Key Commands
Development
npm install # Install dependencies
npm run build # Compile TypeScript to dist/
npm run dev # Development mode with file watching
npm run lint # Run ESLint on src/ directory
npm start # Run compiled server from dist/
Testing the Server
# Credentials must be supplied via environment variables (they are not accepted as CLI flags
# to avoid exposure in the host process list).
OCTOPUS_API_KEY=API-KEY OCTOPUS_SERVER_URL=https://your-octopus.com npm start
# Server URL may also be supplied via the --server-url flag:
OCTOPUS_API_KEY=API-KEY npm start -- --server-url https://your-octopus.com
Architecture
Core Structure
- src/index.ts: Entry point that sets up the MCP server, parses CLI arguments, and initializes the transport layer
- src/tools/index.ts: Tool registration system that loads all available tools based on configuration
- src/types/toolConfig.ts: Tool configuration system with toolsets and version tracking
Tool System
Tools self-register into TOOL_REGISTRY and are organized by toolsets:
core: Basic operations (spaces, environments)projects,deployments,releases: Project lifecycle operationstasks,tenants,kubernetes,machines,certificates: Specialized operations
Each tool file exports a registration that includes:
- Tool name and handler function
- Toolset classification
- Read-only flag (all tools are currently read-only)
- Minimum Octopus version requirement (optional)
MCP SDK: use registerTool, not tool
Minimum SDK is
^1.22.0— do not lower it. Six tools (find_releases,find_runbooks,find_interruptions,find_events,update_feature_toggle,run_runbook) pass a fullz.object(...)asinputSchemarather than a raw shape. SDK releases before 1.22.0 mistake that ZodObject instance for a raw shape and re-wrap it withz.object(...), dragging the instance's own internals — including the_cached: nullfield every zod v3 ZodObject carries — into the shape. JSON Schema conversion then dies onnull._defandtools/listfails outright with-32603 Cannot read properties of null (reading '_def'), taking every tool down with it.src/tools/__tests__/toolsList.test.tsguards both the floor and the published schemas.
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.
- 5d ago First seen · 244 lines · 2,878 tokens per session scan A c776938d937c
mcp-server CLAUDE.md is an instructions file published in the GitHub repository OctopusDeploy/mcp-server (101 stars, last pushed 2d ago), licensed MPL-2.0. It adds 2,878 tokens to every session, about $0.0144 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 2026-08-30.
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.