What is happy-platform-mcp AGENTS.md?

Development instructions for a ServiceNow MCP server, a tool connection for reading and changing ServiceNow records. They require using the available ServiceNow tools before considering scripts or manual steps.

Use them when querying, creating, updating, or inspecting ServiceNow records and table schemas across supported IT service-management data.

They provide a fixed order for ServiceNow operations and reduce unnecessary scripting when a direct tool already supports the task.

How Happy-Technologies-LLC/happy-platform-mcp configures Codex and Ope

Reuse

Borrowing it

Nothing to install: this file belongs to Happy-Technologies-LLC/happy-platform-mcp. 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/Happy-Technologies-LLC/happy-platform-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Happy-Technologies-LLC/happy-platform-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/happy-technologies-llc/happy-platform-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/happy-technologies-llc/happy-platform-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/happy-technologies-llc/happy-platform-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/happy-technologies-llc/happy-platform-mcp/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/happy-technologies-llc/happy-platform-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/happy-technologies-llc/happy-platform-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,214 This file is loaded in full into every session.

When invoked 6,214 The same file — it is already loaded in full.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.06214	$0.06214
Opus 5.5	$0.02486	$0.02486
Sonnet 5.5	$0.01243	$0.01243
Haiku 4.5	$0.00621	$0.00621

Measured 3d ago against content hash a4d391126094, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

happy-platform-mcp AGENTS.md scanned grade B 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 755 /scripts/business_rules

Makes network callslowCapability

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

curl -H "Authorization: Bearer $HAPPY_MCP_API_TOKEN" http://localhost:3000/instances

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

happy-platform-mcp CLAUDE.md — 89% identical, 4 lines differ

AGENTS.md · 784 lines

How it starts

The opening of the file, as written. The whole thing — 784 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ServiceNow MCP Server v2.0 - Development Guide

For: Codex (Codex.ai/code) Version: 2.0 Instance: Multi-instance support enabled

🚨 CRITICAL: MCP-FIRST POLICY

ALWAYS use MCP tools as the PRIMARY method for ServiceNow operations.

Priority Order (MANDATORY):

FIRST: Use MCP tools (SN-Create-Record, SN-Update-Record, SN-Query-Table, etc.)
SECOND: If MCP fails, use SN-Execute-Background-Script
LAST RESORT: Document as manual step only if both fail

When to Write Background Scripts:

NEVER as first choice
ONLY when MCP tools have documented limitations
ALWAYS try MCP batch operations first (5-10+ parallel calls)

🎯 MCP Tools (40+ Total)

Generic Tools (Work on ANY table)

Core CRUD:

SN-Query-Table - Query records with filtering
SN-Create-Record - Create records in any table
SN-Get-Record - Get single record by sys_id
SN-Update-Record - Update existing records
SN-Get-Table-Schema - Get table structure
SN-Discover-Table-Schema - Deep schema with relationships
SN-List-Available-Tables - List all available tables

Specialized Tables (Convenience)

ITSM:

SN-List-Incidents, SN-Create-Incident, SN-Get-Incident
SN-List-ChangeRequests
SN-List-Problems

Administration:

SN-List-SysUsers
SN-List-SysUserGroups
SN-List-CmdbCis

Convenience Tools (Incident Operations)

SN-Update-Incident - Update incident by sys_id
SN-Close-Incident - Close incident with resolution
SN-Assign-Incident - Assign incident to user/group
SN-Add-Work-Notes - Add work notes to incident
SN-Search-Incidents - Natural language incident search

Update Set Management

SN-Set-Update-Set - Set current update set (AUTOMATED!)
SN-Get-Current-Update-Set - Get active update set
SN-List-Update-Sets - List available update sets
SN-Move-Records-To-Update-Set - Fix records in wrong set
SN-Clone-Update-Set - Clone entire update set
SN-Inspect-Update-Set - Inspect update set contents

Read the full file on GitHub · 784 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.

3d ago Changed · +4 tokens per session a4d391126094
10d ago Changed · +8 lines · +255 tokens per session 42acc3cd3a8a
1mo ago Changed · +38 tokens per session 34feefe31b63
2mo ago First seen · 776 lines · 5,917 tokens per session scan B 39561982231a

Subscribe to this mod's changes

happy-platform-mcp AGENTS.md is an instructions file published in the GitHub repository Happy-Technologies-LLC/happy-platform-mcp (55 stars, last pushed 4d ago), licensed Apache-2.0. It adds 6,214 tokens to every session, about $0.0249 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

happy-platform-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
happy-platform-mcp AGENTS.mdHappy-Technologies-LLC/happy-platform-mcp	Instructions file	55	4d ago	Apache-2.0	B	6,214	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

happy-platform-mcp: Instructions file for Codex