actual-mcp-server: Instructions file for Claude Code

CLAUDE.md

actual-mcp-server CLAUDE.md is an instructions file for Claude Code from agigante80/actual-mcp-server. It costs 23,184 tokens per session, scanned C, original, MIT.

Project instructions for an Actual Budget integration server that connects AI assistants to financial-management tools through the Model Context Protocol.

In plain words
What is it for?
Use them when working on this TypeScript server, its HTTP or local connections, its financial tools, and its repository workflow.
Why use it?
They give the coding agent project-specific rules and technical context, reducing incorrect changes and inconsistent output.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is agigante80/actual-mcp-server's own configuration. It tells Claude Code how to work on actual-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything actual-mcp-server configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { createTool } from '../lib/toolFactory.js';.

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/actual-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/agigante80/actual-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-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.

agentmods badge for actual-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/agigante80/actual-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/agigante80/actual-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/agigante80/actual-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/agigante80/actual-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.

agentmods 80×15 button for actual-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/agigante80/actual-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/agigante80/actual-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23,184 This file is loaded in full into every session.
When invoked 23,184 The same file — it is already loaded in full.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.23184 $0.23184
Opus 5 $0.11592 $0.11592
Sonnet 5 $0.04637 $0.04637
Haiku 4.5 $0.02318 $0.02318

Measured 2d ago against content hash 06991f300ffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

actual-mcp-server CLAUDE.md scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

**There is no `npm run lint`.** Do not go looking for one. CI's `Lint Code` job is `npm run build` (type check) plus `npm run typecheck:e2e`, `npm run check:coverage`, `npm run knip`, and `actionlint` (installed by `scri

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**There is no `npm run lint`.** Do not go looking for one. CI's `Lint Code` job is `npm run build` (type check) plus `npm run typecheck:e2e`, `npm run check:coverage`, `npm run knip`, and `actionlint` (installed by `scri
CLAUDE.md · 540 lines

How it starts

The opening of the file, as written. The whole thing — 540 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.

Project Overview

Actual MCP Server bridges AI assistants with Actual Budget via the Model Context Protocol (MCP), exposing 81 tools for conversational financial management. Supports two transports: HTTP (for LibreChat/LobeChat/multi-user deployments) and stdio (for Claude Desktop/Claude Code local use; pass the --stdio flag).

Tech Stack: TypeScript (NodeNext/ESM), Node.js 22+, @actual-app/api v26, @modelcontextprotocol/sdk, Express 5, Zod v4, Playwright

Output Convention: never use em or en dashes

Hard project rule. Applies to ALL output: chat, commits, GitHub comments and PR/issue bodies, file content, code comments, release notes. Never write the unicode em dash character (U+2014) or en dash character (U+2013).

When you would have written one, restructure the sentence so no dash is needed at all. Do NOT substitute with a regular ASCII hyphen (the hyphen is reserved for genuine compound words like post-merge, cherry-pick, off-budget).

Replacement patterns:

  • Introducing an explanation or list: use a colon. "Result: it shipped."
  • Parenthetical aside: use commas or parentheses. "The fix, cherry-picked, landed cleanly." Or "The fix (cherry-picked) landed cleanly."
  • Range: use the word "to" or "through". "v0.6.4 to v0.6.6", "Monday through Friday".
  • Strong pause or contrast: split into two sentences.

Mechanical enforcement: a PreToolUse hook at .claude/hooks/block-dashes.py (forge-kit canonical block-dashes-version: 1, registered in .claude/settings.local.json) blocks any Write, Edit, MultiEdit, NotebookEdit, or Bash tool call whose payload contains an em or en dash, and tells the model how to restructure. The hook script's output is shown back to the model verbatim. Self-check before submitting tool calls regardless of whether the hook is currently armed.

Common slip patterns to watch for (described abstractly to avoid the literal characters):

  • Tables that use a wide horizontal-bar punctuation as a separator inside cells (replace with a colon, or restructure into a sub-table).
  • A definitional pause like X PAUSE Y where PAUSE is a wide horizontal bar (use X: Y instead).
  • Range expressions like X PAUSE Y where PAUSE is a wide horizontal bar (use X to Y).
  • Bulleted lists in the form - item PAUSE description where PAUSE is a wide horizontal bar (use - item: description).

Read the full file on GitHub · 540 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. 2d ago Changed · +3 lines · +607 tokens per session 06991f300ffa
  2. 3d ago Changed · +3 lines · +480 tokens per session 46e56b1695d1
  3. 6d ago Changed · +43 lines · +5,263 tokens per session 1fe50c6a0caa
  4. 10d ago First seen · 491 lines · 16,834 tokens per session scan C eb9a72a9e9da

Subscribe to this mod's changes

actual-mcp-server CLAUDE.md is an instructions file published in the GitHub repository agigante80/actual-mcp-server (53 stars, last pushed today), licensed MIT. It adds 23,184 tokens to every session, about $0.1159 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

vibetags com-example-service-EvidenceBasedShowcase.instructions.md

Instructions for PIsberg/vibetags, covering copilot instructions for evidencebasedshowcase, generated — edit the source, rules for field settledorderids, rules for method totalwithtax and rules for method refreshcartbadge.

PIsberg/vibetags · 443 tokens

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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens