Skip to main content
Glama
WYRE-AI

Inforcer MCP Server

Official
by WYRE-AI
README.md
# Inforcer MCP Server

[![Build Status](https://github.com/WYRE-AI/inforcer-mcp/actions/workflows/release.yml/badge.svg)](https://github.com/WYRE-AI/inforcer-mcp/actions/workflows/release.yml)
[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![Node.js](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg)](https://nodejs.org/)

A [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that gives AI assistants structured, **mostly read-only** access to [Inforcer](https://www.inforcer.com) Microsoft 365 baseline-governance data — tenants, baselines, alignment/drift, policies, secure scores, identity, audit logs, and report generation — plus two write actions to trigger an assessment run or queue a report.

> **Note:** This project is maintained by [Wyre Technology](https://github.com/WYRE-AI).

## ⚠ Community-sourced API

Inforcer does not (at time of writing) publish an official REST API specification. This server wraps the [`@wyre-technology/node-inforcer`](https://github.com/WYRE-AI/node-inforcer) SDK, whose API surface is **community-sourced** from [royklo/InforcerCommunity](https://github.com/royklo/InforcerCommunity). Endpoints, field shapes, and behavior may change without notice. Treat results accordingly and verify anything load-bearing against the Inforcer portal.

## Read-only scope

Every tool in this server is **read-only** EXCEPT two:

- `inforcer_assessments_run` — triggers an assessment run for a tenant.
- `inforcer_reports_run` — queues one or more report runs across one or more tenants.

Both are **HIGH-IMPACT** (not destructive): they kick off real work in Inforcer and are visible to operators. Both are annotated accordingly and ask for confirmation before running. **Confirm with the user before invoking.**

There are **no** create/update/delete tools for policies, tenants, or baselines — those operations are not exposed by the community API and are intentionally absent here.

## Quick Start

**Claude Code (CLI):**

```bash
claude mcp add inforcer-mcp \
  -e INFORCER_REGION=us \
  -e INFORCER_API_KEY=your-api-key \
  -- npx -y github:WYRE-AI/inforcer-mcp
```

See [Installation](#installation) for Docker and from-source methods.

## Features

- **🔌 MCP Protocol Compliance**: Full support for MCP tools and prompts
- **🛡️ Governance Coverage (read-only)**: Tenants, baselines, alignment/drift, policies, Microsoft Secure Score, Entra ID identity, and the audit log
- **🔍 Decision-Tree Navigation**: Start with `inforcer_navigate` to explore domains, then call domain-specific tools
- **🧭 Flexible Tenant Resolution**: Most tools accept a `tenant` as a numeric Client Tenant ID, a tenant DNS name, an Azure AD GUID, or a friendly name — resolved automatically
- **🔒 Secure Authentication**: `Inf-Api-Key` header auth, region-scoped
- **🌐 Dual Transport**: stdio (local) and HTTP Streamable (gateway/Docker)
- **🐳 Docker Ready**: Containerized deployment with HTTP transport and health checks
- **📊 Structured Logging**: Configurable levels, credentials never logged

## Table of Contents

- [Installation](#installation)
- [Configuration](#configuration)
- [Tenant identifiers](#tenant-identifiers)
- [Domains and tools](#domains-and-tools)
- [Gateway connection](#gateway-connection)
- [Docker Deployment](#docker-deployment)
- [Development](#development)
- [Testing](#testing)
- [Contributing](#contributing)
- [License](#license)

## Installation

### Option 1: Claude Code (CLI)

```bash
claude mcp add inforcer-mcp \
  -e INFORCER_REGION=us \
  -e INFORCER_API_KEY=your-api-key \
  -- npx -y github:WYRE-AI/inforcer-mcp
```

### Option 2: Docker

```bash
docker compose up
```

Or pull the pre-built image:

```bash
docker run -d \
  -e INFORCER_REGION=us \
  -e INFORCER_API_KEY=your-key \
  -p 8080:8080 \
  ghcr.io/wyre-ai/inforcer-mcp:latest
```

### Option 3: From Source

```bash
git clone https://github.com/WYRE-AI/inforcer-mcp.git
cd inforcer-mcp
export NODE_AUTH_TOKEN=$(gh auth token)   # to install @wyre-ai/* from GitHub Packages
npm ci
npm run build
```

## Configuration

| Variable | Description | Default |
|----------|-------------|---------|
| `INFORCER_REGION` | **Required.** Inforcer API region — one of `anz`, `eu`, `uk`, `us`. There is no default; the server errors clearly if it is missing. | — |
| `INFORCER_API_KEY` | **Required.** Inforcer API key, sent as the `Inf-Api-Key` header. | — |
| `MCP_TRANSPORT` | Transport mode (`stdio` or `http`) | `stdio` |
| `MCP_HTTP_PORT` | HTTP server port | `8080` |
| `AUTH_MODE` | Auth mode (`env` or `gateway`) | `env` |
| `LOG_LEVEL` | Log level (`debug`, `info`, `warn`, `error`) | `info` |

Both `INFORCER_REGION` and `INFORCER_API_KEY` are required for any API call. Tool discovery (`tools/list`) works without them; the first real call will error if either is missing.

## Tenant identifiers

Inforcer's tenant-scoped routes use an integer **Client Tenant ID** — which is **NOT** the same as the Azure AD tenant GUID (`msTenantId`). To make tools easy to use, the `tenant` argument accepts any of:

- a numeric **Client Tenant ID** (e.g. `42`),
- a **tenant DNS name** (e.g. `contoso.onmicrosoft.com`),
- an **Azure AD tenant GUID** (`msTenantId`), or
- a **friendly name** (e.g. `Contoso`).

Names/DNS/GUIDs are resolved to the numeric Client Tenant ID via the SDK's `resolveTenantId` before each tenant-scoped call. If a name matches more than one tenant, the call fails with a clear "ambiguous" error — pass the numeric Client Tenant ID instead. Use `inforcer_tenants_resolve` to see exactly which Client Tenant ID an input maps to.

## Domains and tools

The server uses decision-tree navigation. Start with `inforcer_navigate` to pick a domain, or call any tool directly. All tools are read-only except `inforcer_assessments_run` and `inforcer_reports_run`.

| Domain | Tools | Read-only |
|--------|-------|-----------|
| **navigation** | `inforcer_navigate`, `inforcer_status` (live `baselines.list()` connectivity check) | ✅ |
| **tenants** | `inforcer_tenants_list`, `inforcer_tenants_get`, `inforcer_tenants_resolve` | ✅ |
| **baselines** | `inforcer_baselines_list` | ✅ |
| **alignment** | `inforcer_alignment_scores`, `inforcer_alignment_details` (per-tenant drift) | ✅ |
| **policies** | `inforcer_policies_list` (by tenant) | ✅ |
| **secure-scores** | `inforcer_secure_scores_get` (by tenant) | ✅ |
| **identity** | `inforcer_users_list`, `inforcer_users_get`, `inforcer_groups_list`, `inforcer_groups_get`, `inforcer_roles_list` | ✅ |
| **audit** | `inforcer_audit_event_types`, `inforcer_audit_search` | ✅ |
| **assessments** | `inforcer_assessments_list` (✅), `inforcer_assessments_run` (⚠ HIGH-IMPACT, **not** read-only) | mixed |
| **reports** | `inforcer_reports_types_list`, `inforcer_reports_runs_list`, `inforcer_reports_run_status`, `inforcer_reports_download_output` (✅), `inforcer_reports_run` (⚠ HIGH-IMPACT, **not** read-only) | mixed |

`inforcer_reports_run` queues asynchronously — poll the run with `inforcer_reports_run_status` until `isTerminal: true`, then fetch each output with `inforcer_reports_download_output` (returns base64-encoded file content).

## Gateway connection

When hosted behind the WYRE MCP Gateway, set `AUTH_MODE=gateway` and `MCP_TRANSPORT=http`. In this mode the server is stateless (a fresh MCP server + transport per request) and reads credentials from per-request HTTP headers injected by the gateway:

| Header | Maps to |
|--------|---------|
| `x-inforcer-region` | `INFORCER_REGION` |
| `x-inforcer-api-key` | `INFORCER_API_KEY` |

When both headers are present the server updates the environment and invalidates its cached client so the next call uses the freshly-injected credentials. `tools/list` still works without credentials, so discovery is never blocked. The container image defaults to `MCP_TRANSPORT=http`; `/health` reports `ok` when credentials are configured and `degraded` otherwise.

## Docker Deployment

See [docker-compose.yml](docker-compose.yml) for full configuration. Copy `.env.example` to `.env` and fill in your credentials:

```bash
cp .env.example .env
# Edit .env with INFORCER_REGION and INFORCER_API_KEY
docker compose up -d
```

## Development

```bash
export NODE_AUTH_TOKEN=$(gh auth token)
npm ci
npm run build       # Build the project
npm run dev         # Watch mode
npm run test        # Run tests
npm run lint        # Type-check
npm run clean       # Remove dist/
```

## Testing

```bash
npm test            # Run test suite
npm run test:watch  # Watch mode
```

## Contributing

See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.

## License

Apache 2.0 — Copyright WYRE Technology

TDQS

A3.9/5.0

Scored across 24 tools

Disambiguation5/5

Each tool targets a distinct resource/action: tenants, users, groups, roles, policies, baselines, alignment, audit, assessments, and reports. Even close pairs like alignment_scores vs alignment_details or assessments_run vs reports_run are clearly separated by noun and purpose. The discovery and status tools also serve clearly different roles.

Naming Consistency4/5

All tools share the inforcer_ prefix and mostly follow a resource_verb pattern like tenants_list, users_get, and groups_list. A few names omit the verb (inforcer_status, inforcer_alignment_scores, inforcer_audit_event_types) and report actions use compound names like reports_run_status and reports_download_output, but the overall convention remains readable and predictable.

Tool Count3/5

With 24 tools, this server sits at the high end of the reasonable range and feels heavy relative to a tightly scoped MCP server. The count is justified by the breadth of the domain — tenants, identity, alignment, audit, assessments, and reports — but it is more than an agent will typically need in one session.

Completeness4/5

The toolset covers the core workflows well: tenant resolution, identity object listing/detail, baseline alignment, secure scores, audit search, assessment discovery/run, and the full report queue/status/download lifecycle. Minor gaps remain, such as no policy detail view, no role detail view, and no assessment run status polling, but these are not blocking for the main Inforcer use cases.

Maintenance

ActivityActive
ResponsivenessUnresponsive