mcp-calm-server: Instructions file for Claude Code

CLAUDE.md

mcp-calm-server CLAUDE.md is an instructions file for Claude Code from fr0ster/mcp-calm-server. It costs 2,989 tokens per session, scanned A, original, MIT.

Project instructions for mcp-calm-server, a service that connects Claude or another MCP host to SAP Cloud ALM. MCP is a standard way for an AI tool to call software tools, while stdio is a communication method using input and output streams.

In plain words
What is it for?
Use them when adding or changing SAP Cloud ALM tools, handling MCP messages, updating dependencies, or debugging URL and output-stream issues.
Why use it?
They document boundaries between the client and server and warn about mistakes that can break authentication, retries, error handling, or message transport.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is fr0ster/mcp-calm-server's own configuration. It tells Claude Code how to work on mcp-calm-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-calm-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fr0ster/mcp-calm-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fr0ster/mcp-calm-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/fr0ster/mcp-calm-server

Made for: Claude Code.

Wrote 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.

agentmods badge for mcp-calm-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fr0ster/mcp-calm-server/claude-md.svg)](https://agentmods.dev/instructions/fr0ster/mcp-calm-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fr0ster/mcp-calm-server/claude-md"><img src="https://agentmods.dev/badge/instructions/fr0ster/mcp-calm-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,989 This file is loaded in full into every session.
When invoked 2,989 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02989 $0.02989
Opus 5 $0.01494 $0.01494
Sonnet 5 $0.00598 $0.00598
Haiku 4.5 $0.00299 $0.00299

Measured 8d ago against content hash 2a9ea60d1a60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-calm-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 8d 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.

CLAUDE.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guidance for Claude / AI agents working on mcp-calm-server

Project context that isn't obvious from the code or git history. Read this before non-trivial changes — it documents hidden contracts, known pitfalls, and a few hard-won facts about the upstream SAP API.

Architecture (one-line)

mcp-calm-client  ──HTTP/OData──>  SAP Cloud ALM
       ▲
       │ ICalmConnection, ILogger, ODataQuery (from @mcp-abap-adt/interfaces)
       │
mcp-calm-server  ──MCP/stdio──>  Claude Desktop / Code / any MCP host
  • @mcp-abap-adt/calm-client — HTTP, OData, types, retries, error translation. Lives at ~/prj/mcp-calm-client.
  • @mcp-abap-adt/calm-server (this repo) — tool-shim: JSON Schema, args validation, error mapping, MCP registry. Should never do raw HTTP itself — if a client method is missing, fix it in calm-client first.

When a tool needs a new HTTP capability: add it to calm-client, cut a release there, bump the peer dep here, then wire the tool. Doing it the other way produces hidden direct-HTTP code that doesn't go through the auth/retry/error pipeline.

Critical pitfall: MCP-stdio reserves stdout

MCP over stdio uses stdout for JSON-RPC frames. Any other write to stdout silently corrupts every protocol call.

  • Family loggers (@mcp-abap-adt/loggerPinoLogger, DefaultLogger) write info/debug to stdout by default. Do not use them inside the stdio bin. A local StderrLogger (src/server/stderrLogger.ts) routes every level to stderr — use it for any stdio runtime path.
  • For library consumers wiring BaseCalmMcpServer over HTTP / SSE / custom transports, the family loggers are fine — the stdout-collision concern doesn't apply.
  • The StderrLogger.test.ts includes a guard that fails if anything ever hits stdout. Keep it green.

Critical pitfall: CALM_BASE_URL is consumed verbatim

The connection layer (src/server/connection/) appends service routes to CALM_BASE_URL by plain concatenation — it does not inject /api. A tenant service-key's endpoints.Api already includes /api (e.g. https://eu10-004.alm.cloud.sap/api); copy it 1:1 into CALM_BASE_URL. Sandbox uses https://sandbox.api.sap.com/SAPCALM as before. A bare host (no /api) in OAuth2 mode yields 404 on every call.

Read the full file on GitHub · 230 lines

Changes

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.

  1. 8d ago First seen · 230 lines · 2,989 tokens per session scan A 2a9ea60d1a60

Subscribe to this mod's changes

mcp-calm-server CLAUDE.md is an instructions file published in the GitHub repository fr0ster/mcp-calm-server (5 stars, last pushed today), licensed MIT. It adds 2,989 tokens to every session, about $0.0149 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens