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/mitchallen/mcp-hello-typescript-server/claude-mdgit clone --depth 1 https://github.com/mitchallen/mcp-hello-typescript-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/mitchallen/mcp-hello-typescript-server/claude-md)<a href="https://agentmods.dev/instructions/mitchallen/mcp-hello-typescript-server/claude-md"><img src="https://agentmods.dev/badge/instructions/mitchallen/mcp-hello-typescript-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 5.1 | $0.02438 | $0.02438 |
| Opus 5 | $0.01219 | $0.01219 |
| Sonnet 5 | $0.00488 | $0.00488 |
| Haiku 4.5 | $0.00244 | $0.00244 |
Grade A, and why
mcp-hello-typescript-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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-hello-typescript-server — notes for Claude
A minimal MCP server built with TypeScript and the official
@modelcontextprotocol/sdk
— a good starting point for a new server or a demo. It exposes two tools:
server_info (a health/status check) and greet (a friendly greeting in one of
a handful of languages, defaulting to English). Built with npm, tsc, and
make; a multi-stage Docker build compiles the TypeScript and runs it on a
distroless Chainguard/Wolfi node base (cgr.dev/chainguard/node). It is the
TypeScript port of the sibling Python mcp-hello-server,
following the official MCP
Build a server (TypeScript)
reference (alongside the Go mcp-hello-go-server and
Rust mcp-hello-rust-server ports).
Layout
src/greetings.ts— greeting data (GREETINGS), language resolution (names, aliases, ISO codes), and thegreet()builder. Unit-tested intests/greetings.test.ts.src/server.ts—createServer()builds theMcpServer, defines the tool input/output schemas (zod) and handlers, and registers them withserver.registerTool. Tools returnstructuredContentfor the structured result.src/version.ts— reads theversionfrompackage.jsonat runtime (the single source of truth) so the MCP handshake andserver_infostay in sync.src/index.ts— the entry point; picks the transport fromMCP_TRANSPORTand wires up stdio (StdioServerTransport) or streamable HTTP (StreamableHTTPServerTransporton anode:httpserver, stateless, mounted at/mcp).tests/server.test.ts— integration tests connecting a client and server overInMemoryTransport.createLinkedPair()(the analog of the Python suite's in-memory FastMCP client). No network, no subprocess.
Conventions
- Build / deps: npm.
package.json/package-lock.jsonare committed and the Dockerfile installsnpm cifrom the lockfile.make build=tsc→build/. Runnpm installafter changing dependencies to refresh the lock. - Version: the source of truth is
"version"inpackage.json;make releasebumps it withnpm version.src/version.tsreads it at runtime. - Running:
make run(stdio, the default MCP transport, from source viatsx),make run-http(streamable HTTP onPORT, default 8000). The transport is chosen byMCP_TRANSPORT(stdio|http); the HTTP endpoint is/mcp. - Tests / gate:
make test(node --test),make check(prettier check +tsc --noEmit+ tests) — the CI gate. - Adding a language: add a row to
GREETINGSingreetings.ts(and, optionally, an alias / ISO code toALIASES).server_inforeports the set automatically. - Docker: the image defaults to HTTP transport (
MCP_TRANSPORT=http,HOST=0.0.0.0,PORT=8000). TypeScript is compiled in a builder stage oncgr.dev/chainguard/node:latest-dev; the pruned productionnode_modules, the compiledbuild/, andpackage.jsonare copied ontocgr.dev/chainguard/node:latest, which has no shell / package manager and runs as the non-rootnodeuser (uid 65532). Its entrypoint isnode, so the Dockerfile usesCMD ["build/index.js"].make scanshould report 0 CRITICAL/HIGH. - Releasing:
make release(BUMP=patch|minor|major, default patch) bumps theversioninpackage.json(+package-lock.json), commits, tagsvX.Y.Z, pushes, and creates the matching GitHub Release from theCHANGELOG.mdsection. The tag triggers the GHCR + Docker Hub publish workflows. It refuses to run unless the tree is clean, you're onmain, andCHANGELOG.mdalready has the new version's section.
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 · 159 lines · 2,438 tokens per session scan A 3f568e211c8b
mcp-hello-typescript-server CLAUDE.md is an instructions file published in the GitHub repository mitchallen/mcp-hello-typescript-server (0 stars, last pushed 2d ago), licensed MIT. It adds 2,438 tokens to every session, about $0.0122 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 2026-09-01.
Other instructions, from other repositories
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).
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.
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.
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.
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).
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.