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.
git clone --depth 1 https://github.com/zhound420/D365FO-claude-connectorWrote 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/mcp/zhound420/d365fo-claude-connector/d365fo-connector)<a href="https://agentmods.dev/mcp/zhound420/d365fo-claude-connector/d365fo-connector"><img src="https://agentmods.dev/badge/mcp/zhound420/d365fo-claude-connector/d365fo-connector/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.
<a href="https://agentmods.dev/mcp/zhound420/d365fo-claude-connector/d365fo-connector"><img src="https://agentmods.dev/badge/mcp/zhound420/d365fo-claude-connector/d365fo-connector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
d365fo-connector 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 12d 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.
What it actually says
{
"d365fo-connector": {
"command": "npx",
"args": [
"-y",
"@zhound/d365fo-mcp-server"
],
"env": {
"D365_TENANT_ID": "",
"D365_CLIENT_ID": "",
"D365_CLIENT_SECRET": "",
"D365_ENVIRONMENT_URL": ""
}
}
}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.
- 12d ago First seen · 15 lines scan A 3d2692c77a70
d365fo-connector is an MCP server published in the GitHub repository zhound420/D365FO-claude-connector (10 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.
Other mcp servers, from other repositories
alm-xpp-mcp
D365 F&O: 90 AI tools over 200K+ objects, 25M+ cross-refs, 24M+ label translations. Runs locally from the almxppmcp npm package. Needs 1 environment variable to run.
mcp-midaz
MCP server for Midaz by Lerian — self-hosted double-entry ledger: accounts, balances, transactions. Runs locally from the @codespar/mcp-midaz npm package. Needs 3 environment variables to run.
mcp-focus-nfe
MCP server for Focus NFe — NFe, NFSe, NFCe emission and management. Runs locally from the @codespar/mcp-focus-nfe npm package. Needs 1 environment variable to run.
frihet
AI-native MCP server for Frihet ERP — 157 canonical operations for invoicing, expenses, CRM, banking, POS and ES/EU fiscal workflows, with conservative capability and side-effect metadata. Runs locally from the @frihet/mcp-server npm package. Needs 1 environment variable to run.
erp
AI-native business management — 52 tools for invoicing, CRM, accounting & tax. Runs locally from the @frihet/mcp-server npm package.
fubon-api-mcp-server
A local Model Context Protocol server for Fubon Securities, a Taiwanese brokerage, exposing its stock-trading API and market-data queries.