agentmods.dev

mcp-itglue CLAUDE.md

mcp-itglue CLAUDE.md is an instructions file for coding agents from mspstack/mcp-itglue. It costs 810 tokens per session, scanned A, original, MIT.

A set of project instructions for mcp-itglue, a TypeScript server that connects coding agents to the IT Glue documentation API. It describes commands, architecture, authentication roles, and project conventions.

In plain words
What is it for?
Use it when working on the mcp-itglue codebase, including its IT Glue client, authentication, configuration, transports, and tool permissions.
Why use it?
It gives an agent the project context needed to build, test, run, and change the server consistently.

Instructions file

not rated 5 1mo ago A scan 810 tokens original MIT
View the source file mspstack/mcp-itglue
Install

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.

agentmods
npx agentmods add instructions/mspstack/mcp-itglue/claude-md
Clone the repo
git clone --depth 1 https://github.com/mspstack/mcp-itglue

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 mcp-itglue CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mspstack/mcp-itglue/claude-md.svg)](https://agentmods.dev/instructions/mspstack/mcp-itglue/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mspstack/mcp-itglue/claude-md"><img src="https://agentmods.dev/badge/instructions/mspstack/mcp-itglue/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 810 This file is loaded in full into every session.
When invoked 810 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00810 $0.00810
Opus 5 $0.00405 $0.00405
Sonnet 5 $0.00162 $0.00162
Haiku 4.5 $0.00081 $0.00081

Measured 3d ago against content hash e081bc0c0b76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-itglue 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 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.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-itglue

MCP server for the IT Glue API. TypeScript, ESM, Node ≥20. Transports: stdio (local) and streamable HTTP (shared deployments).

Commands

  • npm run build — tsc → dist/ (tests are excluded from the build)
  • npm test — vitest, test files live beside sources (src/**/*.test.ts)
  • npm run dev / npm run dev:http — run from source via tsx

Architecture

  • src/index.ts — CLI entry; src/config.ts — env/flag parsing (ConfigError on bad input)
  • src/itglue/client.ts — fetch-based JSON:API client. Wire format is kebab-case; deserialization converts top-level attribute keys only to snake_case so user-defined keys (flexible-asset traits) survive untouched
  • src/auth/tokens.ts — role tokens (MCP_TOKENS_VIEWER/EDITOR/ADMIN, label:token,… lists, timing-safe compare)
  • src/auth/roles.ts — ToolRegistrar: tools are tiered read/write/destructive (derived from MCP annotations, with an explicit tier override where RBAC intent differs — e.g. itglue_delete_document_section is annotated destructive but tiered write). Disallowed tools are never registered (invisible in tools/list) AND handlers re-check the role at call time
  • src/server.ts — createServer(config, {role, label, apiKey}), one McpServer per session
  • src/http/app.ts — Express app: /mcp (sessions bound to principal = role + label + SHA-256 of any client key; mismatch → 403), /health, /webhook/itglue (HMAC), /index/refresh (shared secret or admin token). BYOK policy via CLIENT_ITGLUE_KEYS (disabled | with-token | open)
  • src/vector/ — embeddings (OpenAI/AzureOpenAI), JSON-file index with cosine search, indexer.ts shared by the build tool, webhook, manual refresh, and post-write self-refresh (queueDocumentRefresh)
  • src/tools/advanced.ts — opt-in escape hatch (ITGLUE_ADVANCED_TOOLSET=true / --advanced, off by default): itglue_get (read-only GET on any path via the verb-locked ITGlueClient.rawGet; password paths and show_password params are hard-blocked so credentials never enter model context) and itglue_find_endpoint (lexical search over src/reference/itglue-endpoints.ts). The catalog is hand-maintained (IT Glue has no OpenAPI spec); the search functions are kept in sync with mcp-connectwise-psa's src/tools/advanced.ts

Read the full file on GitHub · 29 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 First seen · 29 lines · 810 tokens per session scan A e081bc0c0b76

Subscribe to this mod's changes

mcp-itglue CLAUDE.md is an instructions file published in the GitHub repository mspstack/mcp-itglue (5 stars, last pushed 1mo ago), licensed MIT. It adds 810 tokens to every session, about $0.0040 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 2026-08-31.

aiconnectwisedocumentationitgluemcpmcp-server
Related

Other instructions, from other repositories

alcove AGENTS.md

Instructions for epicsagas/alcove, covering claude.md, repository purpose, actual location, structure and karpathy 3-layer architecture.

epicsagas/alcove · 1,840 tokens

documcp copilot-instructions.md

Instructions for tosin2013/documcp, covering documcp ai coding agent instructions, architecture essentials, mcp server design (src/index.ts), tool implementation pattern and knowledge graph memory (src/memory/).

tosin2013/documcp · 1,894 tokens

cudaq-docs-mcp CLAUDE.md

Claude Code instructions for rogerawong/cudaq-docs-mcp, covering cudaq-docs-mcp, commands, architecture and constraints.

rogerawong/cudaq-docs-mcp · 507 tokens

inkdex AGENTS.md

AGENTS.md instructions for antonlunden/inkdex, covering agents.md, general coding guidelines and development.

antonlunden/inkdex · 405 tokens

docshark copilot-instructions.md

Instructions for Michael-Obele/docshark, covering docshark site — copilot instructions, tech stack & architecture, essential commands, coding conventions and quality gate.

Michael-Obele/docshark · 2,719 tokens

docshark AGENTS.md

AI Agent Guidelines & Coding Standards for DocShark.

Michael-Obele/docshark · 1,099 tokens