invgate-mcp
A read-only MCP server for InvGate Asset Management, enabling natural language queries for assets, people, computers, servers, software, and API health.
README
invgate-mcp
A curated Model Context Protocol (MCP) server that exposes 12 read-only tools over stdio for InvGate Asset Management. Any MCP-compatible client (Claude Desktop, etc.) can query assets, people, computers, servers, software, and API health through natural language.
- Transport: stdio only (the universal default for local agents).
- Auth: OAuth2 client-credentials flow (
scope=read), in-memory token cache with a 60-second expiry buffer and one-shot 401 retry. - Validation: every tool input is validated with zod;
invalid input returns a structured
validation_errorwithout calling the API. - Resilience: HTTP, auth, and network failures are converted to MCP text
content with
isError: true— the server never crashes the host. - Distribution: published to npm, runnable via
npx invgate-mcp.
Install
# Run without installing
npx invgate-mcp
# Or install globally
npm install -g invgate-mcp
invgate-mcp
Configuration
The server reads three required environment variables at startup:
| Env var | Description | Example |
|---|---|---|
INVGATE_BASE_URL |
InvGate public API base URL (ends with /public-api/v2) |
https://acme.invgate.net/public-api/v2 |
INVGATE_CLIENT_ID |
OAuth2 client ID | my-client-id |
INVGATE_CLIENT_SECRET |
OAuth2 client secret | my-client-secret |
If any are missing the server prints a descriptive error to stderr and exits with code 1.
The OAuth2 token endpoint is derived from INVGATE_BASE_URL by stripping the
/public-api/v2 segment and appending /oauth2/token/, so
https://acme.invgate.net/public-api/v2 → https://acme.invgate.net/oauth2/token/.
Claude Desktop config
Add invgate-mcp to your mcpServers block
(~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"invgate": {
"command": "npx",
"args": ["-y", "invgate-mcp"],
"env": {
"INVGATE_BASE_URL": "https://acme.invgate.net/public-api/v2",
"INVGATE_CLIENT_ID": "your-client-id",
"INVGATE_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Tools
| Tool | Input | Behavior |
|---|---|---|
invgate_list_asset_types |
none | Returns all asset types |
invgate_list_assets |
page, per_page, asset_type_id, criteria |
Paginated asset list with optional filters |
invgate_get_asset |
asset_id (required) |
Single asset by ID |
invgate_list_people |
page, per_page, criteria |
Paginated people list |
invgate_get_person |
person_id (required) |
Single person by ID |
invgate_get_person_assets |
person_id (required), page, per_page |
Assets assigned to a person |
invgate_list_computers |
page, per_page, criteria |
Assets of type "computer" |
invgate_get_computer |
asset_id (required) |
Single computer asset |
invgate_list_servers |
page, per_page, criteria |
Assets of type "server" |
invgate_get_server |
asset_id (required) |
Single server asset |
invgate_get_health |
none | API connectivity status |
invgate_list_software |
page, per_page, criteria |
Paginated installed-software catalog |
Parameter mapping
Tool inputs use snake_case; the server maps them to the InvGate API query
parameters. per_page → page_size, asset_type_id → asset_types.
The criteria object maps to InvGate's nested syntax:
{ "name": "cont:MacBook" } becomes criteria[name]=cont:MacBook on the
query string (op examples: cont, eq, startswith, …).
Results & errors
- Success: the raw JSON response body, pretty-printed, as MCP
textcontent. - Errors: structured JSON
{ "error": "...", "message": "...", "status": ... }as text content withisError: true. Types:validation_error,auth_error,api_error,network_error.
Development
npm install
npm run build # tsup → dist/index.js (single ESM bundle)
npm run typecheck # tsc --noEmit
npm test # vitest run (59 tests, MSW for HTTP interception)
npm run test:coverage # vitest run --coverage (80% gate on src/**)
npm run dev # tsx src/index.ts
Requires Node.js 20+ (uses native fetch).
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.