mcp-itglue
Connects AI assistants to IT Glue, the MSP documentation platform. Browse organizations, read and write documents and flexible assets, and answer natural-language questions via semantic vector search (OpenAI/Azure embeddings). Viewer/editor/admin roles gate tool access; bring-your-own-key applies IT Glue's native permissions. Runs over stdio or HTTP; Docker image available.
README
mcp-itglue
An MCP (Model Context Protocol) server for the IT Glue API, built for MSPs that want AI assistants to read — and safely write — their documentation.
- Documents & sections — list, read, create, update, publish, delete
- Flexible assets — browse asset types and their fields, list/read/create/update/delete assets
- Semantic vector search — "how do I remove a backup agent" finds the Veeam decommissioning runbook, even when the words don't match (OpenAI or Azure OpenAI embeddings, local JSON index)
- Role-based access control — viewer / editor / admin bearer tokens decide which tools each session can even see
- Bring your own key — clients may supply their own IT Glue API key per session, so IT Glue's own permissions apply
- Index freshness — IT Glue webhook, post-write self-refresh, and a manual refresh endpoint
- Transports — stdio for local use, streamable HTTP for shared deployments; Docker image included
Installation
You need an IT Glue API key (IT Glue → Account → Settings → API Keys). Non-US accounts set ITGLUE_REGION to eu or au.
npx (recommended)
Claude Desktop (claude_desktop_config.json) or Claude Code (.mcp.json):
{
"mcpServers": {
"itglue": {
"command": "npx",
"args": ["-y", "mcp-itglue"],
"env": { "ITGLUE_API_KEY": "ITG.xxxx" }
}
}
}
Claude Code one-liner:
claude mcp add itglue --env ITGLUE_API_KEY=ITG.xxxx -- npx -y mcp-itglue
Claude Desktop users can instead grab mcp-itglue.mcpb from the latest release — open it with Claude Desktop and fill in the API key when prompted.
stdio always runs with the full tool surface — it is a local, single-user transport using your own key.
Docker
The container image defaults to the HTTP transport (for shared deployments):
docker run --rm -p 3000:3000 \
-e ITGLUE_API_KEY=ITG.xxxx \
ghcr.io/selic/mcp-itglue
For local stdio use under Docker:
{
"mcpServers": {
"itglue": {
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "ITGLUE_API_KEY", "ghcr.io/selic/mcp-itglue", "--transport", "stdio"],
"env": { "ITGLUE_API_KEY": "ITG.xxxx" }
}
}
}
From source
git clone https://github.com/selic/mcp-itglue.git && cd mcp-itglue
npm install && npm run build
ITGLUE_API_KEY=ITG.xxxx node dist/index.js
HTTP deployment
ITGLUE_API_KEY=ITG.xxxx \
MCP_TOKENS_VIEWER="alice:$(openssl rand -hex 32)" \
MCP_TOKENS_EDITOR="automation:$(openssl rand -hex 32)" \
MCP_TOKENS_ADMIN="ops:$(openssl rand -hex 32)" \
npx -y mcp-itglue --transport http --port 3000
Or with Docker:
docker run --rm -p 3000:3000 \
-e ITGLUE_API_KEY -e MCP_TOKENS_VIEWER -e MCP_TOKENS_EDITOR -e MCP_TOKENS_ADMIN \
ghcr.io/selic/mcp-itglue
Endpoints:
| Route | Purpose |
|---|---|
POST/GET/DELETE /mcp |
MCP streamable-http endpoint |
GET /health |
Liveness probe |
POST /webhook/itglue |
IT Glue webhook → incremental index update |
POST /index/refresh |
Manual index refresh (shared secret or admin token) |
Sessions are held in memory — run a single instance (or add sticky sessions) behind your load balancer.
Access control
Role tokens
Three env vars hold comma-separated label:token lists:
MCP_TOKENS_VIEWER="alice:tokA,bob:tokB" # read-only tools
MCP_TOKENS_EDITOR="hatz:tokC" # + create/update/publish, delete section
MCP_TOKENS_ADMIN="ops:tokD" # + delete documents / flexible assets
Clients authenticate with Authorization: Bearer <token>. The label appears in the audit log ([rbac] session … for alice (viewer)) and lets you revoke one person's token without rotating everyone's.
Tools a role cannot use are not registered for that session — a viewer doesn't even see itglue_create_document in tools/list — and a runtime guard re-checks the role on every call as defense in depth. Session ids never carry privilege: every request re-authenticates, and presenting a different principal against an existing session returns 403.
If no tokens are configured, the server runs in dev mode: all requests get admin access and a loud startup warning. Don't do this in production.
Bring your own IT Glue key (BYOK)
Clients may send their own IT Glue API key in the x-itglue-api-key header on the initialize request. The session then talks to IT Glue with that key and gets the full tool surface — IT Glue's own key permissions are the effective access control. CLIENT_ITGLUE_KEYS controls the policy:
| Value | Behavior |
|---|---|
with-token (default) |
BYOK allowed, but a valid bearer token is still required — protects your server from being an open proxy |
open |
An IT Glue key alone authenticates (trusted networks / local use) |
disabled |
The header is rejected; only the server-wide key is used |
With BYOK enabled the server-wide ITGLUE_API_KEY becomes optional: sessions without a client key are rejected with a clear error. Client keys are never logged; sessions are bound to a SHA-256 hash of the key and audit-labeled byok:<hash-prefix>.
Tools
| Tool | Tier |
|---|---|
itglue_list_organizations, itglue_get_organization |
read |
itglue_list_documents, itglue_get_document |
read |
itglue_list_document_folders |
read |
itglue_list_document_sections, itglue_get_document_section |
read |
itglue_list_flexible_asset_types, itglue_get_flexible_asset_type |
read |
itglue_list_flexible_assets, itglue_get_flexible_asset |
read |
itglue_vector_search, itglue_vector_index_status |
read |
itglue_create_document, itglue_update_document, itglue_publish_document |
write |
itglue_create_document_section, itglue_update_document_section |
write |
itglue_delete_document_section † |
write |
itglue_create_flexible_asset, itglue_update_flexible_asset |
write |
itglue_build_vector_index |
write |
itglue_delete_documents |
destructive |
itglue_delete_flexible_asset |
destructive |
Viewer = read. Editor = read + write. Admin = everything. † Permanent, but editor-tier: editors need it to restructure documents and can already blank section content via update.
Vector tools appear only when an embedding provider is configured.
Vector search
Set OPENAI_API_KEY (or AZURE_OPENAI_API_KEY + AZURE_OPENAI_ENDPOINT, where EMBEDDING_MODEL is your deployment name), then run itglue_build_vector_index per organization. The index is a JSON file at VECTOR_INDEX_PATH (default ./vector-index.json) — on ephemeral hosts, point it at a persistent volume.
The index stays fresh three ways:
-
IT Glue webhook — in IT Glue, webhooks are sent by Workflows (Admin → Workflows): add a Document trigger (created/updated) with a Webhook action. Workflow actions cannot send custom headers, so put the shared secret in the URL:
https://<host>/webhook/itglue?secret=<ITGLUE_WEBHOOK_SECRET>and use a JSON payload template like:
Key Value event[trigger_name]resource_url[resource_url]resource_name[resource_name]organization_name[organization_name]The document id is parsed from
resource_url; the trigger name maps to created/updated/deleted by keyword. Classic JSON:API-style payloads with anx-itglue-webhook-signatureHMAC-SHA256 header are also accepted. -
Self-refresh — documents created/updated/published/deleted through this server's tools are re-indexed automatically in the background.
-
Manual refresh —
POST /index/refreshwithAuthorization: Bearer <ITGLUE_WEBHOOK_SECRET>(or anx-refresh-secretheader, or an admin token). Body{"document_id": "123"}refreshes one document; an empty body re-crawls every indexed organization. Returns202and processes in the background.
Configuration reference
| Variable | Default | Purpose |
|---|---|---|
ITGLUE_API_KEY |
— | Server-wide IT Glue API key |
ITGLUE_REGION |
us |
us, eu, or au |
ITGLUE_BASE_URL |
per region | Override the API base URL |
TRANSPORT |
stdio |
stdio or http |
PORT |
3000 |
HTTP port |
MCP_TOKENS_VIEWER/EDITOR/ADMIN |
— | label:token,label:token per role |
CLIENT_ITGLUE_KEYS |
with-token |
BYOK policy: disabled, with-token, open |
ALLOWED_ORIGINS |
— | Extra browser origins allowed on /mcp (comma-separated). Requests without an Origin header and localhost origins always pass; other browser origins are rejected with 403 |
ITGLUE_WEBHOOK_SECRET |
— | Webhook signature + /index/refresh secret |
VECTOR_INDEX_PATH |
./vector-index.json |
Vector index file |
OPENAI_API_KEY |
— | Enables vector search (OpenAI) |
AZURE_OPENAI_API_KEY / AZURE_OPENAI_ENDPOINT / AZURE_OPENAI_API_VERSION |
— | Enables vector search (Azure OpenAI) |
EMBEDDING_MODEL |
text-embedding-3-small |
Embedding model / Azure deployment |
CLI flags --transport, --port, --region, --base-url override the environment. Run mcp-itglue --help for details.
Notes & limits
- IT Glue rate limit: 3000 requests / 5 minutes per key.
- The IT Glue documents API is only partially documented; document/section endpoints follow observed API behavior.
- Flexible-asset trait updates replace the whole traits object — the update tool's description warns the model to send all traits back.
- List tools return summary fields per item (in both text and
structuredContent) so default page sizes stay within client token limits; theitglue_get_*tools return the complete record. - IT Glue has no user impersonation: a given API key always acts as itself. RBAC here controls what tool calls a session may make; BYOK delegates to IT Glue's own key permissions.
Development
npm install
npm run dev # stdio via tsx
npm run dev:http # http via tsx
npm test # vitest
npm run build # tsc → dist/
Author
Built by Eugene Samotija (@selic) — defency.net. More projects: github.com/selic · LinkedIn
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。