What is valtown-mcp-server CLAUDE.md?

Repository instructions for a Val Town MCP server. Val Town is a cloud platform where TypeScript or JavaScript snippets can run as web endpoints, scheduled jobs, scripts, or email handlers.

Use it when developing or testing the MCP server, working with Val Town’s API, or handling HTTP, scheduled, manually run, and email-triggered functions.

It explains the platform’s concepts, the server’s local and cloud deployment modes, and the project’s architecture and coding rules.

How PrashamTrivedi/valtown-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to PrashamTrivedi/valtown-mcp-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/PrashamTrivedi/valtown-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/PrashamTrivedi/valtown-mcp-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/prashamtrivedi/valtown-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/prashamtrivedi/valtown-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/prashamtrivedi/valtown-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/prashamtrivedi/valtown-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/prashamtrivedi/valtown-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/prashamtrivedi/valtown-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 602 This file is loaded in full into every session.

When invoked 602 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.

Model	Per session	Once invoked
Fable 5.1	$0.00602	$0.00602
Opus 5.5	$0.00241	$0.00241
Sonnet 5.5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 2mo ago against content hash 3836b55842b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

valtown-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 2mo 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 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.

About ValTown

ValTown is a serverless platform for running TypeScript/JavaScript code in the cloud. Key concepts for developers:

Vals: Code snippets that can be HTTP endpoints, scheduled functions, or scripts
HTTP Vals: Functions that handle HTTP requests (similar to serverless functions)
Interval Vals: Functions that run on a schedule (like cron jobs)
Script Vals: One-time or manually triggered functions
Email Vals: Functions that handle incoming emails
API Integration: Full REST API for programmatic access to create/update/delete vals
Remote Execution: Code runs in ValTown's sandboxed environment with built-in npm package support

Architecture Overview

This is a Model Context Protocol (MCP) server that provides AI assistants with access to ValTown's platform. The codebase supports two deployment modes:

Local Binary Mode (mod.ts): Runs as a local MCP server using stdio transport
Remote HTTP Mode (index.http.ts): Deployed on ValTown itself as an HTTP endpoint, accessible via streamable HTTP transport

The server is hosted remotely on ValTown at: https://prashamtrivedi-valtown-mcp-server.val.run/mcp

Key files:

mod.ts: Local stdio MCP server entry point
index.http.ts: Remote HTTP MCP server entry point (deployed on ValTown)
registerTools.ts: Tool registration with CLI exclusion support for remote deployment
config.ts: Configuration loading with remote/local mode support

Commands

Run server locally: deno task start
Development mode: deno task dev
Build binaries: deno task build
Platform-specific builds: deno task build:linux, deno task build:windows, deno task build:macos

Style Guidelines

Use TypeScript strict mode with explicit typing for function parameters/returns
2-space indentation, semicolons at line ends
Use camelCase for variables/functions, PascalCase for types/interfaces, UPPER_SNAKE_CASE for constants
Tool names use kebab-case (e.g., get-val)
Document all public functions with JSDoc
Wrap async operations in try/catch blocks and use getErrorMessage utility
Return consistent error responses with isError flag

Read the full file on GitHub · 55 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.

2mo ago First seen · 55 lines · 602 tokens per session scan A 3836b55842b9

Subscribe to this mod's changes

valtown-mcp-server CLAUDE.md is an instructions file published in the GitHub repository PrashamTrivedi/valtown-mcp-server (15 stars, last pushed 1y ago), licensed MIT. It adds 602 tokens to every session, about $0.0024 per session on Opus 5.5. 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.

valtown-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
valtown-mcp-server CLAUDE.mdPrashamTrivedi/valtown-mcp-server	Instructions file	15	1y ago	MIT	A	602	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

valtown-mcp-server: Instructions file for Claude Code