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.
npx agentmods add instructions/jefftiger96/mcp4acumatica/claude-mdgit clone --depth 1 https://github.com/JeffTiger96/mcp4acumaticaWrote 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/jefftiger96/mcp4acumatica/claude-md)<a href="https://agentmods.dev/instructions/jefftiger96/mcp4acumatica/claude-md"><img src="https://agentmods.dev/badge/instructions/jefftiger96/mcp4acumatica/claude-md.svg" alt="Measured on agentmods" 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 | $0.15857 | $0.15857 |
| Opus 5 | $0.07928 | $0.07928 |
| Sonnet 5 | $0.03171 | $0.03171 |
| Haiku 4.5 | $0.01586 | $0.01586 |
Grade C, and why
mcp4acumatica 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 5d 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.
15. **One-line installer.** `install.sh` at the repo root is served by the worker at `/install.sh` (imported as a text module via the `**/*.sh` rule in `wrangler.jsonc`). Users run `curl -fsSL https://<worker>/install.sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
15. **One-line installer.** `install.sh` at the repo root is served by the worker at `/install.sh` (imported as a text module via the `**/*.sh` rule in `wrangler.jsonc`). Users run `curl -fsSL https://<worker>/install.sh This is a copy
100% identical to mcp4acumatica CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Project Memory for MCP4Acumatica
Project Overview
Remote MCP (Model Context Protocol) server on Cloudflare Workers that connects Claude to an Acumatica ERP 2025 R2 instance via the contract-based REST API. Each user authenticates directly with Acumatica — their Acumatica role controls what records they can access.
- License: Apache 2.0 — Copyright 2026 Hall Boys, Inc.
- Copyright header required on all
.tssource files:// Copyright 2026 Hall Boys, Inc.+// SPDX-License-Identifier: Apache-2.0 - Git config (this repo only):
user.email = [email protected] - Current tag:
25R2-0.40.0 - Deployed at:
https://mcp4acumatica.hallboys.com(primary custom domain) /https://acumatica-mcp.hallboys.com(legacy alias, kept active during migration) /https://mcp4acumatica.<account>.workers.dev(workers.dev fallback) - GitHub:
https://github.com/hallboys/MCP4Acumatica
Architecture
Claude (claude.ai / Desktop / API)
│
▼ MCP over streamable-http
┌─────────────────────────────────┐
│ Cloudflare Worker │
│ OAuthProvider wrapper │
│ ├─ /authorize → Acumatica │
│ ├─ /callback ← Acumatica │
│ ├─ /token, /register (DCR+CIMD) │
│ ├─ /docs → Documentation site │
│ └─ /mcp → McpAgent DO │
│ ├─ 49 tools (38 read-only │
│ │ + 6 utility/discovery │
│ │ + 4 schema-knowledge │
│ │ + 1 write) │
└──────────────┬──────────────────┘
│ Bearer token (per-user)
▼
Acumatica 25R2 SaaS
Contract-Based REST API
Default/25.200.001
Storage Abstraction (Platform Portability)
Tool handlers, the Acumatica HTTP client, config, and caching are decoupled from Cloudflare via two abstractions:
IKeyValueStore(src/lib/kv-store.ts) — Platform-agnostic interface for key-value storage (get, put, delete, list). Cloudflare Workers usesCloudflareKVStorewhich wrapsKVNamespace.AppEnv(src/types/acumatica.ts) — Portable environment type containing Acumatica connection settings and astore: IKeyValueStore. All tool handlers and shared libraries useAppEnv. The Cloudflare-specificEnvextendsAppEnvwith CF bindings (TOKEN_STORE,OAUTH_KV,MCP_OBJECT, etc.).
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.
- 5d ago First seen · 484 lines · 15,857 tokens per session scan C 75f5b3e5442e
mcp4acumatica CLAUDE.md is an instructions file published in the GitHub repository JeffTiger96/mcp4acumatica (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 15,857 tokens to every session, about $0.0793 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). It is 100% identical to mcp4acumatica CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.