Borrowing it
Nothing to install: this file belongs to sevalla-hosting/mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sevalla-hosting/mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/sevalla-hosting/mcpWrote 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/sevalla-hosting/mcp/claude-md)<a href="https://agentmods.dev/instructions/sevalla-hosting/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sevalla-hosting/mcp/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.
<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="Reviewed on agentmods" width="80" 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 | $0.03521 | $0.03521 |
| Opus 5.5 | $0.01408 | $0.01408 |
| Sonnet 5.5 | $0.00704 | $0.00704 |
| Haiku 4.5 | $0.00352 | $0.00352 |
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 16d 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 — 96 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), designed to pass Anthropic's Claude connector directory review. It exposes 27 tools: 22 purpose-built workflow tools plus 5 generic tools (sevalla_api_search, sevalla_api_read, sevalla_api_create, sevalla_api_update, sevalla_api_delete) that run any other v3 operation by operation ID. There is no code execution and no sandbox: the model only ever sends structured arguments.
Commands
pnpm dev # Development with --watch (native Node.js)
pnpm start # Run server (node src/index.ts)
pnpm test # Unit + e2e tests (node:test), then the e2e suites again as a 2025-era client
pnpm test:unit # test/*.test.ts
pnpm test:e2e # test/e2e in both protocol eras: real HTTP server, MCP SDK client, fake Sevalla API
pnpm test:live # Live checks: known clients' metadata documents; API smoke test and fake API fidelity with SEVALLA_E2E_API_KEY
pnpm eval # Evals: evals/tasks.ts through headless Claude Code against the fake API; first run (and every harness change) needs --approve-harness
pnpm test:coverage # Tests with coverage (src/** only)
pnpm sync:operations # Regenerate src/sevalla/operations.json from the live OpenAPI spec
pnpm check:operations # Fail if the live spec drifted from operations.json
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 26 is the runtime (Volta, .nvmrc, the Docker image); the code also runs on Node.js 24, which CI tests. TypeScript runs natively via Node's built-in type stripping (no build step), so only erasable TypeScript syntax works (no enums, namespaces or parameter properties). tsc (TypeScript 7) only type-checks. pnpm 12 is pinned in packageManager; Node 25+ no longer bundles corepack, so the Dockerfile installs that pnpm version with npm. pnpm settings go in pnpm-workspace.yaml when needed (there is none today; the Dockerfile copies it when present, and pnpm 11+ ignores the pnpm field of package.json). pnpm refuses packages published less than a day ago unless they are listed in minimumReleaseAgeExclude there, so a bump to a newer release fails pnpm install --frozen-lockfile until the release is a day old.
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.
- 16d ago Changed · +3 lines · +251 tokens per session 8871a1510d28
- 21d ago Changed · +15 lines · +1,833 tokens per session 6a8053cf3a04
- 2mo ago First seen · 78 lines · 1,437 tokens per session scan A cc700e3d5dbb
mcp CLAUDE.md is an instructions file published in the GitHub repository sevalla-hosting/mcp (9 stars, last pushed 15d ago), licensed MIT. It adds 3,521 tokens to every session, about $0.0141 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 2026-08-31.
mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp CLAUDE.mdsevalla-hosting/mcp | Instructions file | 9 | 15d ago | MIT | A | 3,521 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |