# matrix42-mcp

Model Context Protocol server for Matrix42 — lets AI assistants explore the API, read the data model, search the service desk, and act on tickets

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.1.6
- **Author:** S&S Technologies GmbH
- **License:** MIT
- **npm:** matrix42-mcp
- **Source:** https://github.com/sus-tech-gmbh/matrix42-mcp
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-04T19:34:41.844Z
- **Version scanned:** 0.1.6
- **CVEs:** none found by OSV at scan time

## Tools

19 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `data_query` — Read records from the connected Matrix42 instance (read-only).
- `explore_instance` — Survey an unfamiliar instance: what it runs, which modules are installed, and where the data you care about lives.
- `interest` — What you care about, e.g. "assets" or "the service desk"
- `build_query` — Turn a question in plain language into a correct ASQL query, checking every attribute name against the live schema before running it.
- `goal` — What you want to find, in plain language
- `data_definition` — Target data definition, if you already know it
- `triage_ticket` — Work through one ticket: what it is, who it belongs to, what the service level says, and what should happen next.
- `ticket` — Ticket number, object id, or a description of it
- `concern` — What you specifically want to know or decide
- `safe_change` — Walk a write through the preview-then-confirm protocol, so nothing reaches the instance before you have seen exactly what it will send.
- `intent` — The change you want to make, in plain language
- `find_endpoint` — Locate the operation that does what you need and read its real contract — for writing integration code against Matrix42.
- `task` — What the integration needs to do
- `language` — Language or tool you are writing it in
- `schema_discovery` — Explore the Matrix42 data model of the connected instance (read-only metadata).
- `server_info` — Report which Matrix42 instance this MCP server is connected to (base URL, authentication mode, response language), which account the credentials authenticate as
- `service_desk` — Read the service desk and the business objects around it.
- `ticket_actions` — MODIFIES Matrix42 data. Every action here previews first: called WITHOUT confirm:true it returns the exact request it would send and changes nothing, so show th
- `webservice_discovery` — Discover the Matrix42 REST API of the connected instance (read-only metadata).

## Install

**Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"matrix42\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"matrix42-mcp\"\n      ],\n      \"env\": {\n        \"M42_API_TOKEN\": \"<YOUR_M42_API_TOKEN>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `M42_API_TOKEN` — M42 API Token (required)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 1 credential (1 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Moderate blast radius — holds an api key; runs on your machine.
- Floor 22, ceiling 22 (tier: moderate)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/matrix42-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/matrix42-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/matrix42-mcp
- HTML page: https://forgeregistry.com/registry/matrix42-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.