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/sshadows/business-central-mcp/claude-mdgit clone --depth 1 https://github.com/SShadowS/business-central-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/sshadows/business-central-mcp/claude-md)<a href="https://agentmods.dev/instructions/sshadows/business-central-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sshadows/business-central-mcp/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 | $0.07662 | $0.07662 |
| Opus 5 | $0.03831 | $0.03831 |
| Sonnet 5 | $0.01532 | $0.01532 |
| Haiku 4.5 | $0.00766 | $0.00766 |
Grade A, and why
business-central-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 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.
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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BC MCP Server v2
Development Philosophy
This project is NOT released and in active development:
- Always choose the best solution, not the quickest compromise
- Refactor aggressively when architecture is flawed
- Fix problems properly, not with workarounds
- No stubs, mocks, or skeleton implementations -- everything must be fully functional
- No backwards compatibility concerns -- make breaking changes freely
Quick Start
Project Location
- v2 source:
U:/git/bc-mcp/ - v1 reference (deprecated):
C:\bc4ubuntu\Decompiled\bc-poc\ - Decompiled BC28:
U:/git/bc-mcp/reference/bc28/decompiled/ - Decompiled BC27:
C:\bc4ubuntu\Decompiled\(various Microsoft.Dynamics.* directories) - Architecture spec:
C:\bc4ubuntu\Decompiled\bc-poc\docs\superpowers\specs\2026-04-03-bc-mcp-v2-design.md
BC Test Environments
| BC28 | |
|---|---|
| URL | http://cronus28/BC/?tenant=default |
| Username | sshadows |
| Password | 1234 |
| Auth | NavUserPassword |
| License popup | Auto-dismissed |
| Protocol version | 15041 |
Uses NavUserPassword authentication (not Windows/NTLM).
Essential Commands
cd U:/git/bc-mcp
npx tsc --noEmit # Type check
npx vitest run # Unit + protocol tests (292 tests)
npx vitest run --config vitest.integration.config.ts # Integration tests against real BC28 (111 tests)
npm start # HTTP server on port 3000
npm run start:stdio-direct # Direct stdio for Claude Desktop
Rules
- Use Windows paths with forward slashes in bash
- NEVER use
2>nul(creates undeletable files on Windows) - NEVER use emojis -- Windows rendering issues
- Always run
npx tsc --noEmitafter changes - Run integration tests after any protocol-level change
- ESM project -- use
.jsextensions in all imports
Protocol Verification Procedure
CRITICAL: Always verify protocol behavior against decompiled BC source, not v1 code.
V1 had several incorrect assumptions (per-page connections, SaveValue not echoing, etc.). When implementing or debugging any BC protocol interaction:
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 · 386 lines · 7,662 tokens per session scan A a5790d572d12
business-central-mcp CLAUDE.md is an instructions file published in the GitHub repository SShadowS/business-central-mcp (38 stars, last pushed 3d ago), licensed MIT. It adds 7,662 tokens to every session, about $0.0383 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 2026-08-30.
Other instructions, from other repositories
mcp-server-powerpoint architecture-patterns.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering architecture patterns, .net class design (mandatory), layered architecture (critical), command pattern and structure (per domain).
mcp-server-powerpoint mcp-server-guide.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering mcp server development guide, llm-facing content rules, two kinds of tools: hand-written vs. generated, implementation pattern: single hand-written dispatch tool and error handling (mandatory).
1ai-skills CLAUDE.md
Claude Code instructions for oyi77/1ai-skills: This is a Claude Code project configuration for a 1ai-ecosystem repository.
babysitter CLAUDE.md
Claude Code instructions for a5c-ai/babysitter, covering claude.md, repo-specific overrides, read these first, quick commands and claude code local notes.
initrunner CLAUDE.md
Claude Code instructions for vladkesler/initrunner, covering initrunner and project map.
lhremote copilot-instructions.md
Copilot instructions for alexey-pelykh/lhremote, covering copilot review instructions — lhremote, project structure, naming conventions, commit message format and code patterns.