Skip to main content
Glama
Inforcer MCP Server

Inforcer MCP Server

Official
by WYRE-AI

Inforcer MCP Server

Build Status License Node.js

A Model Context Protocol (MCP) server that gives AI assistants structured, mostly read-only access to Inforcer 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.

⚠ Community-sourced API

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

Related MCP server: LegacyMCP

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):

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 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

Option 1: Claude Code (CLI)

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

The image listens on 0.0.0.0 inside the container and defaults to AUTH_MODE=gateway. Publish the port on loopback and pass a real S2S secret. In gateway mode the Inforcer region and API key arrive on each request as headers; they are not read from the environment.

docker build -t inforcer-mcp .
docker run \
  -e CONDUIT_S2S_SECRET \
  -p 127.0.0.1:8080:8080 \
  inforcer-mcp

Or pull the pre-built image:

docker run -d \
  -e CONDUIT_S2S_SECRET \
  -p 127.0.0.1:8080:8080 \
  ghcr.io/wyre-ai/inforcer-mcp:latest

Compose reads CONDUIT_S2S_SECRET from the project .env and refuses to start when that value is unset. Do not assign the variable on the command line: an empty shell value overrides .env.

docker compose up

Option 3: From Source

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

Required

Description

INFORCER_REGION

For stdio and AUTH_MODE=env

Inforcer API region — one of anz, eu, uk, us. There is no default. The Compose gateway service does not load this variable.

INFORCER_API_KEY

For stdio and AUTH_MODE=env

Inforcer API key, sent as the Inf-Api-Key header. The Compose gateway service does not load this variable.

MCP_TRANSPORT

No

stdio (default) or http

AUTH_MODE

No

gateway (Docker image and Compose default) or env. Gateway mode requires X-Inforcer-Region and X-Inforcer-API-Key on each /mcp request and never falls back to INFORCER_*. env uses those variables only after S2S auth succeeds.

CONDUIT_S2S_SECRET

Yes for HTTP

Service-to-service secret. Generate with openssl rand -hex 32. The HTTP server logs an error and exits non-zero when this is empty or a known placeholder (changeme, your-s2s-secret, secret, placeholder, and similar public examples). Compose will not start without it. Never commit a real value. The value is never logged.

MCP_ALLOW_INSECURE_DEV

No

Set to exactly 1 only for local development to start HTTP without CONDUIT_S2S_SECRET. The process logs a warning, does not enforce X-Gateway-S2S, and forces the listener onto 127.0.0.1 even if MCP_HTTP_HOST is a wider address. A known placeholder secret is still refused.

MCP_HTTP_HOST

No

Bind address when MCP_TRANSPORT=http. Defaults to 127.0.0.1 when unset. A configured CONDUIT_S2S_SECRET honors this value. The container image sets 0.0.0.0.

MCP_HTTP_PORT

No

HTTP port. Defaults to 8080.

LOG_LEVEL

No

Log level (debug, info, warn, error). Defaults to info.

/health stays unauthenticated and does not read credentials. The stdio transport does not use CONDUIT_S2S_SECRET.

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

HTTP authentication

With MCP_TRANSPORT=http and CONDUIT_S2S_SECRET set, every /mcp request must include X-Gateway-S2S. The check is verifyS2sHeader in src/s2s-verify.ts: the header value is t=<unix seconds>,v1=<hex>, where the hex is HMAC-SHA256 of the literal string t=<unix seconds> keyed with CONDUIT_S2S_SECRET (64 lowercase hex characters). The timestamp must be within 300 seconds of the server clock. A missing or invalid header returns HTTP 401 before vendor credentials are read.

CONDUIT_S2S_SECRET must already be in the environment. The example reads that variable inside the process. It does not pass the secret as a command argument.

TS=$(date +%s)
SIG=$(printf 't=%s' "$TS" | node -e 'const {createHmac}=require("node:crypto"); const chunks=[]; process.stdin.on("data",(c)=>chunks.push(c)); process.stdin.on("end",()=>{ const secret=process.env.CONDUIT_S2S_SECRET; if(!secret){ console.error("CONDUIT_S2S_SECRET is not set"); process.exit(1); } process.stdout.write(createHmac("sha256", secret).update(Buffer.concat(chunks)).digest("hex")); });')
curl -sS http://127.0.0.1:8080/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H "X-Gateway-S2S: t=${TS},v1=${SIG}" \
  -H 'X-Inforcer-Region: us' \
  -H "X-Inforcer-API-Key: $INFORCER_API_KEY" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

In AUTH_MODE=gateway, /mcp also requires X-Inforcer-Region and X-Inforcer-API-Key. Those headers are the only credential source for the request. With AUTH_MODE=env, the signed request uses INFORCER_REGION and INFORCER_API_KEY from the environment.

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. A request missing either header gets HTTP 401 and does not fall back to INFORCER_REGION or INFORCER_API_KEY.

Header

Maps to

X-Gateway-S2S

HMAC proof described under HTTP authentication. Required on every /mcp request when CONDUIT_S2S_SECRET is set.

X-Inforcer-Region

INFORCER_REGION

X-Inforcer-API-Key

INFORCER_API_KEY

The container image defaults to MCP_TRANSPORT=http and AUTH_MODE=gateway. /health always returns 200, does not require authentication, and does not read vendor credentials.

Docker Deployment

See docker-compose.yml. The checked-in Compose service is gateway mode. It publishes 127.0.0.1:8080:8080, requires CONDUIT_S2S_SECRET, and does not set INFORCER_REGION, INFORCER_API_KEY, or env_file.

cp .env.example .env
# Set CONDUIT_S2S_SECRET in .env (openssl rand -hex 32). Leave INFORCER_* empty
# for the gateway service; those credentials arrive as request headers.
# Compose loads .env itself. Do not prefix the command with a shell assignment.
docker compose up -d

Single-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses INFORCER_REGION and INFORCER_API_KEY. It is separate from the gateway Compose service:

docker run \
  -e CONDUIT_S2S_SECRET \
  -e AUTH_MODE=env \
  -e INFORCER_REGION=us \
  -e INFORCER_API_KEY=your-key \
  -p 127.0.0.1:8080:8080 \
  inforcer-mcp

Local HTTP without a secret is development-only. It binds 127.0.0.1 only and logs a warning. A non-loopback MCP_HTTP_HOST is ignored and the override is logged:

MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm run start:http

Development

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/

# HTTP refuses to start until CONDUIT_S2S_SECRET is a real secret
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" npm run start:http

# Local HTTP only, without a service-to-service secret (always binds 127.0.0.1)
MCP_ALLOW_INSECURE_DEV=1 npm run start:http

Testing

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

Contributing

See CONTRIBUTING.md for guidelines.

License

Apache 2.0 — Copyright WYRE Technology

Available Tools

24 tools
inforcer_alignment_detailsA
Read-only

Get detailed baseline-alignment drift for a tenant. Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Read-only.

Inputs: tenant (required).

inforcer_alignment_scoresA
Read-only

List baseline alignment scores across tenants. Read-only.

Inputs: no named parameters.

inforcer_assessments_listA
Read-only

List the assessments available to run (use to discover assessment IDs). Read-only.

Inputs: no named parameters.

inforcer_assessments_runA

⚠ HIGH-IMPACT. Triggers an assessment run for a tenant. This is not destructive, but it kicks off real work in Inforcer and is visible to operators. Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Confirm with the user before invoking.

Inputs: tenant (required), assessment_id (required).

inforcer_audit_event_typesA
Read-only

List the audit event types available for filtering the activity log. Read-only.

Inputs: no named parameters.

inforcer_baselines_listB
Read-only

List baseline groups and their members. Optionally filter by the baseline (owner) tenant ID. Read-only.

Inputs: baseline_tenant_id.

inforcer_groups_getA
Read-only

Get full detail for a single group, including members. Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Read-only.

Inputs: tenant (required), group_id (required).

inforcer_groups_listA
Read-only

List Entra ID group summaries for a tenant (paginated). Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Read-only.

Inputs: tenant (required), search, continuation_token.

inforcer_navigateA

Discover available Inforcer tools by domain. Returns tool names and descriptions for the selected domain. All tools are callable at any time — this is a help/discovery aid, not a prerequisite.

Inputs: domain (required).

inforcer_policies_listA
Read-only

List policies for a tenant. Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Read-only.

Inputs: tenant (required).

inforcer_reports_download_outputA
Read-only

Download a single finished report output (discovered via inforcer_reports_run_status). Returns the file content base64-encoded along with its filename and content type. Read-only.

Inputs: run_id (required), output_id (required).

inforcer_reports_runA

⚠ HIGH-IMPACT. Queues one or more reports across one or more tenants. This is not destructive, but it kicks off real report-generation work in Inforcer. Reports run asynchronously — use inforcer_reports_run_status to poll the returned run(s) to completion, then inforcer_reports_download_output to fetch each finished output. Confirm with the user before invoking.

Inputs: reports (required), tenants (required).

inforcer_reports_runs_listA
Read-only

List queued and completed report runs. Read-only.

Inputs: no named parameters.

inforcer_reports_run_statusA
Read-only

Poll a report run. Returns isTerminal:false with no outputs while the run is still in progress, or isTerminal:true with the list of downloadable outputs once it finishes. Read-only.

Inputs: run_id (required).

inforcer_reports_types_listA
Read-only

List the catalog of available report types — key, supported output formats, whether the type is collatable (single cross-tenant output), and accepted parameters. Use to discover valid (type, output_format) pairs before calling inforcer_reports_run. Read-only.

Inputs: no named parameters.

inforcer_roles_listA
Read-only

List Entra ID directory role definitions for a tenant. Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Read-only.

Inputs: tenant (required).

inforcer_secure_scores_getA
Read-only

Get the Microsoft Secure Score data for a tenant. Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Read-only.

Inputs: tenant (required).

inforcer_statusA

Check Inforcer API connectivity and available domains. Performs a live baselines.list() call as a read-only connectivity check.

Inputs: no named parameters.

inforcer_tenants_getA
Read-only

Get a single tenant. Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Ambiguous names throw a clear error. Read-only.

Inputs: tenant (required).

inforcer_tenants_listA
Read-only

List all managed tenants. Read-only.

Inputs: no named parameters.

inforcer_tenants_resolveA
Read-only

Resolve a tenant name, DNS name, or Azure AD GUID to its numeric Inforcer Client Tenant ID (which is NOT the Azure AD tenant GUID). Read-only.

Inputs: tenant (required).

inforcer_users_getA
Read-only

Get full detail for a single user. Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Read-only.

Inputs: tenant (required), user_id (required).

inforcer_users_listA
Read-only

List Entra ID user summaries for a tenant (paginated). Tenant identifier — accepts a numeric Client Tenant ID, a tenant DNS name, an Azure AD tenant GUID, or a friendly name. Resolved to the numeric Client Tenant ID before the request. Read-only.

Inputs: tenant (required), search, continuation_token.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    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
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP server that enables AI-powered assessment of Active Directory on-premises environments by exposing AD data as queryable tools for LLMs like Claude.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      MCP server for AI agent compliance that screens actions before execution and records decisions in an immutable, SIEM-ready audit trail.
      53 npm
      -
    • A
      license
      B
      quality
      C
      maintenance
      A read-only MCP server for Microsoft Intune and Entra ID that enables list, get, search, and reporting operations for tenant visibility, audits, troubleshooting, and health reporting without write actions. It includes authentication helpers, report exports, and metadata discovery tools.
      36
      1
      MIT