What is beaver-mcp CLAUDE.md?

A project instruction guide for beaver-mcp, a personal MCP server hosted on Cloudflare Workers that connects AI assistants to external services.

It helps develop, test, check, format, and extend beaver-mcp services, including adding a new external API service.

It gives contributors the project rules, commands, architecture, and access-control details needed to change the server safely.

How alanko0511/beaver-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to alanko0511/beaver-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.

Copy the file

curl -O https://raw.githubusercontent.com/alanko0511/beaver-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/alanko0511/beaver-mcp

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/alanko0511/beaver-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/alanko0511/beaver-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/alanko0511/beaver-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alanko0511/beaver-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/alanko0511/beaver-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alanko0511/beaver-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,102 This file is loaded in full into every session.

When invoked 1,102 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	$0.01102	$0.01102
Opus 5	$0.00551	$0.00551
Sonnet 5	$0.00220	$0.00220
Haiku 4.5	$0.00110	$0.00110

Measured 8d ago against content hash ad091f6860e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

beaver-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 8d 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

beaver-mcp

Personal MCP server on Cloudflare Workers. Streamable-HTTP transport at /mcp (prod: https://mcp.alanko.dev/mcp), gated by GitHub OAuth (@cloudflare/workers-oauth-provider) with a login allowlist. Services wrap external APIs (currently Lunch Money) as MCP tools.

Commands

pnpm dev — wrangler dev (port 8788)
pnpm test — vitest (runs in workerd via @cloudflare/vitest-pool-workers)
pnpm check — Biome lint/format + tsc --noEmit
pnpm format — auto-fix
pnpm cf-typegen — regenerate worker-configuration.d.ts after changing wrangler.jsonc or adding secrets to .dev.vars

Architecture

src/index.ts — OAuthProvider wiring + BeaverMCP (McpAgent Durable Object). Tools register in init() by iterating the services array.
src/auth/ — GitHub OAuth handler (Hono), allowlist, OAuth utils. Access control lives in TWO places on purpose: the /callback route (rejects non-allowlisted logins with 403 before completing authorization) and BeaverMCP.init() (throws if props fail the same check).
src/services/<name>/ — one folder per external API. types.ts defines ToolDef/ServiceModule/registerService. The framework also supports MCP Apps widget tools (widget: field + WidgetResource with CSP domains); no service currently uses one.
test/ — vitest; upstream APIs mocked by stubbing global fetch (test/helpers.ts). Do NOT use fetchMock from cloudflare:test — removed in vitest-pool-workers 0.18.
Deploys: merge to main → GitHub Actions deploys after checks pass. Manual: pnpm deploy.

Public-repo rules (repo is public!)

NO personal identifiers in code or committed config: no GitHub usernames, emails, account IDs, API keys. The allowlist is the ALLOWED_GITHUB_LOGINS secret (comma-separated; empty = deny all).
Every credential is a Worker secret (wrangler secret put NAME) + .dev.vars locally (gitignored; keep .dev.vars.example in sync with placeholders).
wrangler.jsonc deliberately has no account_id — CI uses the CLOUDFLARE_ACCOUNT_ID repo secret; local wrangler resolves it from login. The KV namespace ID in wrangler.jsonc is an opaque resource ID and OK to commit.

Read the full file on GitHub · 44 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.

8d ago First seen · 44 lines · 1,102 tokens per session scan A ad091f6860e8

Subscribe to this mod's changes

beaver-mcp CLAUDE.md is an instructions file published in the GitHub repository alanko0511/beaver-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,102 tokens to every session, about $0.0055 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.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

beaver-mcp: Instructions file for Claude Code