# Globally-installed MCP servers (npm)

> Globally-installed MCP servers (npm) is an officially published AI tool from npm. Anomity scores its risk at 10 out of 100 (low).

- **Canonical URL:** https://catalog.anomity.ai/agent/global-mcp-npm
- **Kind:** AI tool
- **Publisher:** npm
- **Trust level:** official
- **Risk score:** 10/100 (low)
- **Website:** https://www.npmjs.com/search?q=%40modelcontextprotocol
- **Last updated:** 2026-09-02
- **JSON:** https://catalog.anomity.ai/api/entries/agent/global-mcp-npm

## Description

Official @modelcontextprotocol/server-* packages installed via `npm install -g`. Available to any agent on the system; the daemon surfaces them so they get classified and policy-evaluated like configured MCPs.

## Why it scored 10

The score starts at the catalog's neutral base of 50 and moves only through the signals below. The formula is published at https://catalog.anomity.ai/about — there is no model and no hidden heuristic.

| Signal | Contribution | Severity | Evidence |
| --- | --- | --- | --- |
| Published by the vendor | -40 | trust offset |  |

Clamped result: **10/100**, band **low**.

## Configuration surface

Files this tool reads on the host. Anything written here changes what the agent does next.

- `global-mcp-npm-modelcontextprotocol-win-default` — @modelcontextprotocol/server-* (Windows default %APPDATA%\npm prefix)
- `global-mcp-npm-modelcontextprotocol-unix-system` — @modelcontextprotocol/server-* (system-wide /usr/local on macOS/Linux)
- `global-mcp-npm-modelcontextprotocol-unix-userprefix` — @modelcontextprotocol/server-* (user-prefix ~/.npm-global)

## Related AI tools

- [AdaL](https://catalog.anomity.ai/agent/adal) — risk 10 (low)
- [Agent Zero](https://catalog.anomity.ai/agent/agent-zero) — risk 10 (low)
- [Aide](https://catalog.anomity.ai/agent/aide) — risk 10 (low)
- [Aider](https://catalog.anomity.ai/agent/aider) — risk 10 (low)
- [AiderDesk](https://catalog.anomity.ai/agent/aider-desk) — risk 10 (low)
- [Amazon Q Developer](https://catalog.anomity.ai/agent/amazon-q) — risk 10 (low)

---

Source: Anomity Catalog (https://catalog.anomity.ai/). Scoring methodology: https://catalog.anomity.ai/about. Machine-readable index: https://catalog.anomity.ai/llms.txt · https://catalog.anomity.ai/openapi.json