agentmods.dev

mcp CLAUDE.md

mcp CLAUDE.md is an instructions file for coding agents from sevalla-hosting/mcp. It costs 1,437 tokens per session, scanned A, original, MIT.

Project instructions for a remote MCP server that exposes the Sevalla hosting platform’s API. The server lets agents search for API operations and execute them through isolated JavaScript code.

In plain words
What is it for?
Developing, testing, formatting, linting, and checking the Sevalla MCP server and its API-access code.
Why use it?
They explain the repository layout, required Node.js version, commands, and safety-related runtime details needed to work on the server.

Instructions file

not rated 8 +1 10d ago A scan 1,437 tokens original MIT
View the source file sevalla-hosting/mcp
Install

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.

agentmods
npx agentmods add instructions/sevalla-hosting/mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/sevalla-hosting/mcp

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sevalla-hosting/mcp/claude-md.svg)](https://agentmods.dev/instructions/sevalla-hosting/mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sevalla-hosting/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sevalla-hosting/mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,437 This file is loaded in full into every session.
When invoked 1,437 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01437 $0.01437
Opus 5 $0.00718 $0.00718
Sonnet 5 $0.00287 $0.00287
Haiku 4.5 $0.00144 $0.00144

Measured 4d ago against content hash cc700e3d5dbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp 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 4d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 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.

What This Is

Remote MCP server for the Sevalla PaaS API (mcp.sevalla.com). Exposes 200 API endpoints through 2 tools (search + execute) instead of one tool per endpoint. AI agents write JavaScript code that runs in sandboxed V8 isolates to discover and call the Sevalla API. The sandbox tooling (originally based on the codemode approach) is vendored in src/sandbox/.

Commands

pnpm dev              # Development with --watch (native Node.js)
pnpm start            # Run server (node src/index.ts)
pnpm test             # Run tests (node:test)
pnpm test:coverage    # Tests with coverage (src/** only)
pnpm lint             # oxlint
pnpm fmt              # oxfmt (auto-fix)
pnpm fmt:check        # oxfmt (check only)
pnpm check:code       # Full check: tsc + oxlint + oxfmt

Node.js Version

Node.js 24+ is required. TypeScript runs natively via Node's built-in type stripping (no build step). The isolated-vm native addon segfaults on Node 25. Pinned via Volta in package.json (24.14.0) and .nvmrc.

Source Layout

  • src/index.ts — Hono HTTP server: routing, Bearer token extraction, per-request MCP server wiring, spec cache, graceful shutdown. Also supports --stdio mode (token from SEVALLA_API_KEY env var).
  • src/api.ts — createAuthenticatedFetch: URL rewriting (/v3 prefix) + Bearer token injection.
  • src/oauth.ts — stateless OAuth flow and .well-known metadata endpoints.
  • src/sandbox/ — vendored sandbox tooling:
    • spec.ts — OpenAPI spec processing: $ref resolution (circular-safe, prototype-pollution-safe), field extraction, tag ranking.
    • bridge.ts — request bridge for the execute tool: validates the request shape (single options object, method/path strings), path safety, header filtering, request-count and response-size limits.
    • isolate.ts — runs code in isolated-vm with memory/CPU/wall-clock limits and marshals host functions into the isolate.
    • tools.ts — builds the search and execute tool definitions and handlers.

Read the full file on GitHub · 78 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. 4d ago First seen · 78 lines · 1,437 tokens per session scan A cc700e3d5dbb

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository sevalla-hosting/mcp (8 stars, last pushed 10d ago), licensed MIT. It adds 1,437 tokens to every session, about $0.0072 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.

hostingmcpmcp-serverpaas
Related

Other instructions, from other repositories

mcp CLAUDE.md

Claude Code instructions for shipstatic/mcp, covering claude.md, readme positioning (public docs), architecture, one product, two transports — the shape that survives oauth and quick reference.

shipstatic/mcp · 9,899 tokens

mcp AGENTS.md

AGENTS.md instructions for shipstatic/mcp: Read CLAUDE.md (same directory). It is the single source of truth for this repo's instructions; everything in it applies to every agent, not just Claude. Do not duplicate its content here.

shipstatic/mcp · 55 tokens

blockrun-mcp AGENTS.md

AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.

BlockRunAI/blockrun-mcp · 282 tokens

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).

stabgan/openrouter-mcp-multimodal · 793 tokens

intervals-icu-mcp CLAUDE.md

Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.

hhopke/intervals-icu-mcp · 2,035 tokens

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).

pipefy/ai-toolkit · 3,184 tokens