BOD-25-01-CSA-Microsoft-Policy-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLIENT_ID | Yes | Your Azure AD application client ID | |
| TENANT_ID | Yes | Your Azure AD tenant ID | |
| CLIENT_SECRET | Yes | Your Azure AD application client secret |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| block_legacy_authB | Block legacy authentication (MS.AAD.1.1v1) |
| block_high_risk_usersB | Block users detected as high risk (MS.AAD.2.1v1) |
| block_high_risk_signinsB | Block sign-ins detected as high risk (MS.AAD.2.3v1) |
| enforce_phishing_resistant_mfaC | Enforce phishing-resistant MFA for all users (MS.AAD.3.1v1) |
| enforce_alternative_mfaB | Enforce alternative MFA method if phishing-resistant MFA not enforced (MS.AAD.3.2v1) |
| configure_authenticator_contextB | Configure Microsoft Authenticator to show login context (MS.AAD.3.3v1) |
| complete_auth_methods_migrationC | Set Authentication Methods Manage Migration to Complete (MS.AAD.3.4v1) |
| enforce_privileged_mfaB | Enforce phishing-resistant MFA for privileged roles (MS.AAD.3.6v1) |
| restrict_app_registrationB | Allow only administrators to register applications (MS.AAD.5.1v1) |
| restrict_app_consentB | Allow only administrators to consent to applications (MS.AAD.5.2v1) |
| configure_admin_consentC | Configure admin consent workflow for applications (MS.AAD.5.3v1) |
| restrict_group_consentB | Prevent group owners from consenting to applications (MS.AAD.5.4v1) |
| disable_password_expiryB | Disable password expiration (MS.AAD.6.1v1) |
| configure_global_adminsC | Configure Global Administrator role assignments (MS.AAD.7.1v1) |
| enforce_granular_rolesB | Enforce use of granular roles instead of Global Administrator (MS.AAD.7.2v1) |
| enforce_cloud_accountsB | Enforce cloud-only accounts for privileged users (MS.AAD.7.3v1) |
| enforce_pamB | Enforce PAM system for privileged role assignments (MS.AAD.7.5v1) |
| configure_global_admin_approvalB | Configure approval requirement for Global Administrator activation (MS.AAD.7.6v1) |
| configure_role_alertsC | Configure alerts for privileged role assignments (MS.AAD.7.7v1) |
| configure_admin_alertsC | Configure alerts for Global Administrator activation (MS.AAD.7.8v1) |
| get_policy_statusB | Get current status of all CISA M365 security policies |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 21 tools
Each tool has a clearly distinct purpose targeting specific security policy controls - blocking sign-ins vs. users, configuring different admin workflows, enforcing various MFA methods, restricting different consent types. The descriptions with MS.AAD codes further clarify boundaries, leaving no ambiguity about which tool to use for each security requirement.
All tools follow a consistent verb_noun pattern using snake_case throughout - every tool starts with an action verb (block, complete, configure, disable, enforce, get, restrict) followed by a specific noun phrase describing the security control. This creates a highly predictable and readable naming convention across all 21 tools.
21 tools is slightly high but reasonable for the comprehensive CISA M365 security policy domain. The server covers authentication methods, admin controls, application consent, and privileged access management - each area requiring multiple specific controls. While borderline heavy, each tool addresses a distinct security requirement that earns its place in the set.
The tool set provides complete coverage for CISA M365 security policy implementation with get_policy_status for assessment and enforcement tools for every major control area: authentication methods (MFA, migration), admin security (global admins, alerts, PAM), and application governance (consent, registration). There are no obvious gaps - agents can implement the full security framework without dead ends.