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/sap-samples/hana-developer-cli-tool-example/mcp-server-developmentgit clone --depth 1 https://github.com/SAP-samples/hana-developer-cli-tool-exampleWhat 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 | $0.04811 | $0.04811 |
| Opus 5 | $0.02405 | $0.02405 |
| Sonnet 5 | $0.00962 | $0.00962 |
| Haiku 4.5 | $0.00481 | $0.00481 |
Grade A, and why
hana-developer-cli-tool-example mcp-server-development.instructions.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 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 — 742 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Development Guidelines
Use this guide when creating or modifying TypeScript files in the mcp-server/src/ directory.
Scope and Purpose
This guide applies to all TypeScript files implementing the Model Context Protocol (MCP) server that exposes hana-cli commands as MCP tools, resources, and prompts for LLM consumption.
Critical Principles
- JSON-RPC Protocol Compliance: MCP communicates via JSON-RPC over STDIO
- Logging Discipline: ONLY use
console.error()for logging, NEVERconsole.log() - Tool Naming: Sanitize tool names to
[a-z0-9_-]character set only - Schema Generation: Convert yargs builders to JSON Schema accurately
- Error Enrichment: Provide actionable error analysis and suggestions
- Type Safety: Use TypeScript interfaces and explicit typing throughout
- CLI Integration: Maintain consistency with CLI command metadata and structure
CRITICAL: Logging Rules
NEVER write to stdout using console.log() - it will break the JSON-RPC protocol.
// ❌ WRONG - Breaks MCP protocol
console.log('Debug info:', data);
console.log(JSON.stringify(result));
// ✅ CORRECT - Write to stderr
console.error('[MCP Debug]', data);
console.error('[MCP Info]', JSON.stringify(result));
Why: MCP clients expect ONLY JSON-RPC messages on stdout. Any other output causes parsing failures like "Failed to parse message: ...".
Apply to:
- The main
index.tsfile header comment documents this - All imported modules that might log (
executor.ts,command-parser.ts, etc.) - Error handling and debugging code
File Structure and Organization
Main Entry Point: index.ts
#!/usr/bin/env node
/**
* MCP Server for SAP HANA CLI
*
* CRITICAL: This file implements the Model Context Protocol (MCP) server.
* MCP communicates via JSON-RPC over STDIO. All logging MUST use console.error()
* to write to stderr, never console.log() which writes to stdout.
*/
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
// ... more imports
class HanaCliMcpServer {
private server: Server;
private commands: Map<string, any> = new Map();
constructor() {
this.server = new Server(
{
name: 'hana-cli-mcp-server',
version: '1.0.0',
icons: [/* icon configuration */],
},
{
capabilities: {
tools: {},
resources: {},
prompts: {},
},
}
);
this.setupHandlers();
this.setupErrorHandling();
}
private setupHandlers(): void {
// Register handlers for tools, resources, prompts
}
private setupErrorHandling(): void {
this.server.onerror = (error) => {
console.error('[MCP Error]', error);
};
process.on('SIGINT', async () => {
await this.server.close();
process.exit(0);
});
}
async run(): Promise<void> {
const transport = new StdioServerTransport();
await this.server.connect(transport);
console.error('[MCP Server] Running on stdio');
}
}
const server = new HanaCliMcpServer();
server.run().catch(console.error);
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 · 742 lines · 4,811 tokens per session scan A d6e7da98b2b7
hana-developer-cli-tool-example mcp-server-development.instructions.md is an instructions file published in the GitHub repository SAP-samples/hana-developer-cli-tool-example (109 stars, last pushed 7d ago), licensed Apache-2.0. It adds 4,811 tokens to every session, about $0.0241 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
rtk CLAUDE.md
Claude Code instructions for rtk-ai/rtk, covering claude.md, project overview, name collision warning, development commands and build & run.
rtk copilot-instructions.md
Copilot instructions for rtk-ai/rtk, covering copilot instructions for rtk, using rtk in this session, instead of: use, build, test & lint and pre-commit gate (must all pass before any pr).
awesome-vscode CLAUDE.md
Instructions for viatsko/awesome-vscode, covering claude.md, what this repo is, adding an entry, themes and linting / ci.
vscode-peacock AGENTS.md
Instructions for johnpapa/vscode-peacock, covering peacock — agent guide, project overview, repository structure, tech stack and build & run.
cs CLAUDE.md
Instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).
docs-mcp-server AGENTS.md
Instructions for arabold/docs-mcp-server, covering agent instructions for docs-mcp-server, repository context, development workflow, key commands and git workflow.