Inforcer MCP Server
OfficialAn MCP server that gives AI assistants mostly read-only access to Inforcer Microsoft 365 baseline-governance data (tenants, baselines, alignment/drift, policies, secure scores, identity, audit logs, reports), plus two confirmed high-impact actions that trigger real work.
Navigate & check status —
inforcer_navigateexplores tools by domain;inforcer_statusperforms a live read-onlybaselines.list()connectivity check.Tenants — list all managed tenants, get one tenant, and resolve a friendly name/DNS/Azure AD GUID to its numeric Client Tenant ID (
inforcer_tenants_list,_get,_resolve).Baselines — list baseline groups and their members, optionally filtered by baseline (owner) tenant ID.
Alignment / drift — list baseline alignment scores across tenants and get detailed per-tenant drift.
Policies — list policies for a tenant.
Secure scores — fetch Microsoft Secure Score data for a tenant.
Identity (Entra ID) — list/get users and groups (paginated, searchable, with group members) and list directory role definitions.
Audit — list available audit event types and search the activity log by date range, event types, and page size with continuation tokens.
Assessments — list runnable assessments, and ⚠
inforcer_assessments_runtriggers an assessment run for a tenant (high-impact write, asks for confirmation).Reports — list report types (formats, collatability, parameters), list runs, poll run status, and download finished outputs base64-encoded; ⚠
inforcer_reports_runqueues one or more reports across one or more tenants asynchronously (high-impact write, asks for confirmation).Tenant flexibility — most tools accept a numeric Client Tenant ID, DNS name, Azure AD GUID, or friendly name, auto-resolved (ambiguous names error clearly).
No create/update/delete — no write tools exist for policies, tenants, or baselines.
Deployment options — stdio for local use and HTTP Streamable (gateway/Docker) with HMAC S2S auth and per-request Inforcer credentials.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Inforcer MCP Server list my tenants"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Inforcer MCP Server
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-mcpSee 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_navigateto explore domains, then call domain-specific tools🧭 Flexible Tenant Resolution: Most tools accept a
tenantas a numeric Client Tenant ID, a tenant DNS name, an Azure AD GUID, or a friendly name — resolved automatically🔒 Secure Authentication:
Inf-Api-Keyheader 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-mcpOption 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-mcpOr 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:latestCompose 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 upOption 3: From Source
git clone https://github.com/WYRE-AI/inforcer-mcp.git
cd inforcer-mcp
export NODE_AUTH_TOKEN=$(gh auth token) # to install @wyre-ai/* from GitHub Packages
npm ci
npm run buildConfiguration
Variable | Required | Description |
| For stdio and | Inforcer API region — one of |
| For stdio and | Inforcer API key, sent as the |
| No |
|
| No |
|
| Yes for HTTP | Service-to-service secret. Generate with |
| No | Set to exactly |
| No | Bind address when |
| No | HTTP port. Defaults to |
| No | Log level ( |
/health stays unauthenticated and does not read credentials. The stdio transport does not use CONDUIT_S2S_SECRET.
Both INFORCER_REGION and INFORCER_API_KEY are required for any API call in stdio and AUTH_MODE=env. Tool discovery (tools/list) works without them; the first real call will error if either is missing.
HTTP authentication
With MCP_TRANSPORT=http and CONDUIT_S2S_SECRET set, every /mcp request must include X-Gateway-S2S. The check is verifyS2sHeader in src/s2s-verify.ts: the header value is t=<unix seconds>,v1=<hex>, where the hex is HMAC-SHA256 of the literal string t=<unix seconds> keyed with CONDUIT_S2S_SECRET (64 lowercase hex characters). The timestamp must be within 300 seconds of the server clock. A missing or invalid header returns HTTP 401 before vendor credentials are read.
CONDUIT_S2S_SECRET must already be in the environment. The example reads that variable inside the process. It does not pass the secret as a command argument.
TS=$(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), ora 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 |
| ✅ |
tenants |
| ✅ |
baselines |
| ✅ |
alignment |
| ✅ |
policies |
| ✅ |
secure-scores |
| ✅ |
identity |
| ✅ |
audit |
| ✅ |
assessments |
| mixed |
reports |
| 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 |
| HMAC proof described under HTTP authentication. Required on every |
|
|
|
|
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 -dSingle-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-mcpLocal 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:httpDevelopment
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:httpTesting
npm test # Run test suite
npm run test:watch # Watch modeContributing
See CONTRIBUTING.md for guidelines.
License
Apache 2.0 — Copyright WYRE Technology
Available Tools
24 toolsinforcer_alignment_detailsARead-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_scoresARead-only
List baseline alignment scores across tenants. Read-only.
Inputs: no named parameters.
inforcer_assessments_listARead-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_typesARead-only
List the audit event types available for filtering the activity log. Read-only.
Inputs: no named parameters.
inforcer_audit_searchARead-only
Search the Inforcer activity (audit) log. All filters are optional; returns a page of events plus a continuation token for paging. Read-only.
Inputs: date_to, date_from, page_size, event_types, +1 more.
inforcer_baselines_listBRead-only
List baseline groups and their members. Optionally filter by the baseline (owner) tenant ID. Read-only.
Inputs: baseline_tenant_id.
inforcer_groups_getARead-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_listARead-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_policies_listARead-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_outputARead-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_listARead-only
List queued and completed report runs. Read-only.
Inputs: no named parameters.
inforcer_reports_run_statusARead-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_listARead-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_listARead-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_getARead-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_getARead-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_listARead-only
List all managed tenants. Read-only.
Inputs: no named parameters.
inforcer_tenants_resolveARead-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_getARead-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_listARead-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
Scored across 24 tools
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.
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.
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.
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
Related MCP Connectors
Official Microsoft MCP Server to query Microsoft Entra data using natural language
Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs (Claude, GPT, Gemini, Cohere). Tools operate only on explicitly authorized customer connections, enabling agents to safely read and write against live third-party systems.
AI governance MCP server for EU AI Act compliance and jurisdiction verification
MCP server providing AI assistants with integration capabilities for QuickBooks Online.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for Microsoft 365 via the Microsoft Graph API, providing read-only access to profile, calendar, email, Teams chats, OneDrive files, and meeting transcripts from any MCP client.17232 npm3MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that enables AI-powered assessment of Active Directory on-premises environments by exposing AD data as queryable tools for LLMs like Claude.MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for AI agent compliance that screens actions before execution and records decisions in an immutable, SIEM-ready audit trail.53 npm-
- AlicenseBqualityCmaintenanceA 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.361MIT