actual-mcp-server: Command for Claude Code

.claude/commands/local-env.md

local-env is a command for Claude Code from agigante80/actual-mcp-server. It costs 0 tokens per session (974 once invoked), scanned A, original, MIT.

A command that runs the complete local deployment and testing process for the actual-mcp-server development environment.

In plain words
What is it for?
Use it to run smoke, sanity, normal, extended, or full tests, optionally including bank-sync tests for GoCardless or SimpleFIN.
Why use it?
It checks changes against a disposable budget, keeping full tests that create and delete data away from real financial information.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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 runs a file that does not travel with it, so clone the repository first. The line is bash scripts/deploy-and-test.sh [ARGUMENTS].

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/commands/local-env.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 local-env

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/agigante80/actual-mcp-server/local-env"><img src="https://agentmods.dev/badge/commands/agigante80/actual-mcp-server/local-env.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 974 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00974
Opus 5 $0.00000 $0.00487
Sonnet 5 $0.00000 $0.00195
Haiku 4.5 $0.00000 $0.00097

Measured 3d ago against content hash 2fcd74327cb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

local-env 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 3d 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/commands/local-env.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the full local deployment pipeline for the actual-mcp-server dev environment.

Usage

Accepted arguments: [smoke|sanity|normal|extended|full] [--bank-sync] Default test level if no argument given: smoke

Steps

  1. Run the deploy script from the project root:

    cd <the repo root>          # the script derives its own paths from its location
    bash scripts/deploy-and-test.sh [ARGUMENTS]
    

    The path used to be written out here and in the script itself. Both rotted when the repo moved on 2026-09-04, so do NOT reintroduce an absolute path: the script now derives DEV_DIR from its own location and refuses to run if that is not a git working tree.

    • Valid test levels: sanity | smoke | normal | extended | full
    • Optional flag: --bank-sync to include per-account bank sync tests (GoCardless/SimpleFIN)

Which budget the tests run against (since 2026-08-11). The bearer instance (:3601), which is what this pipeline tests, points at a DISPOSABLE budget via BEARER_BUDGET_SYNC_ID in $HOME/docker/librechat-MCP-actual/actual-mcp-server/.env. The OIDC instance (:3600, LibreChat/LobeChat) still serves the REAL budget through ACTUAL_BUDGET_SYNC_ID and must not be repointed. At full the suite creates and deletes objects, so running it against real financial data is not acceptable; before this split it also meant the post-run zero-residue assertion failed on leftovers from earlier runs, making the gate red for reasons unrelated to the change under test.

That same .env sets MCP_TEST_BUDGET_SYNC_ID to the same id, which designates the budget disposable and is what allows the PRE-run residue sweep to delete leftovers from a previously crashed run. scripts/deploy-and-test.sh reads it from there when it is not already exported, and prints whether the sweep is enabled or disabled at the start of the test step, so a skipped sweep is visible rather than silent.

Do not derive MCP_TEST_BUDGET_SYNC_ID from the loaded budget. The guard exists because an operator deliberately named a budget as disposable AND that name matches what the server loaded. Defaulting it to the loaded budget makes the comparison always true and points a deleting sweep at whatever is mounted.

Read the full file on GitHub · 61 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. 3d ago Changed · +5 lines 2fcd74327cb1
  2. 9d ago First seen · 56 lines · 0 tokens per session scan A cceb048ee5de

Subscribe to this mod's changes

local-env is a command published in the GitHub repository agigante80/actual-mcp-server (51 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 974 tokens. 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.