What is mcp-itglue CLAUDE.md?

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.

Use it when working on the mcp-itglue codebase, including its IT Glue client, authentication, configuration, transports, and tool permissions.

It gives an agent the project context needed to build, test, run, and change the server consistently.

How mspstack/mcp-itglue configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mspstack/mcp-itglue. 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/mspstack/mcp-itglue/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mspstack/mcp-itglue

Made for: Claude Code.

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/mspstack/mcp-itglue/claude-md/github.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/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/mspstack/mcp-itglue/claude-md"><img src="https://agentmods.dev/badge/instructions/mspstack/mcp-itglue/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,259 This file is loaded in full into every session.

When invoked 1,259 The same file — it is already loaded in full.

Security scan A 0 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	$0.01259	$0.01259
Opus 5.5	$0.00504	$0.00504
Sonnet 5.5	$0.00252	$0.00252
Haiku 4.5	$0.00126	$0.00126

Measured 1mo ago against content hash 998c0bd77103, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 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 · 31 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.

1mo ago Changed · +1 lines · +218 tokens per session 998c0bd77103
1mo ago Changed · +1 lines · +231 tokens per session 6b6dc650d3c2
2mo 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 1,259 tokens to every session, about $0.0050 per session on Opus 5.5. 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.

ai connectwise documentation itglue mcp mcp-server

mcp-itglue CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-itglue CLAUDE.mdmspstack/mcp-itglue	Instructions file	5	1mo ago	MIT	A	1,259	Claude Code
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

mcp-itglue: Instructions file for Claude Code