Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add okapi-ca/ms-365-admin-mcp-server --skill ms365-admin-mcpgit clone --depth 1 https://github.com/okapi-ca/ms-365-admin-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/okapi-ca/ms-365-admin-mcp-server/ms365-admin-mcp)<a href="https://agentmods.dev/skills/okapi-ca/ms-365-admin-mcp-server/ms365-admin-mcp"><img src="https://agentmods.dev/badge/skills/okapi-ca/ms-365-admin-mcp-server/ms365-admin-mcp.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.02682 |
| Opus 5 | $0.00041 | $0.01341 |
| Sonnet 5 | $0.00016 | $0.00536 |
| Haiku 4.5 | $0.00008 | $0.00268 |
Grade A, and why
ms365-admin-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ms365-admin-mcp
A reusable Claude Code skill that wraps ms-365-admin-mcp-server with a structured safety pattern: discover the right tool by use case, dry-run first, confirm explicitly, audit after. The skill is a router — its reference files index the server's 515 tools by domain and point back to the authoritative documentation in docs/USE_CASES.md and docs/playbooks/.
When to load this skill
Load this skill when the request involves a Microsoft 365 administrative operation requiring tenant-level permissions. Typical signals:
- "List security alerts / open incidents / risky users"
- "Audit sign-ins for…", "what changed in the directory yesterday"
- "Permanent Global Admin members", "PIM assignments"
- "Non-compliant Intune devices", "wipe the device of user X"
- "Create a Conditional Access policy", "audit current CA policies"
- "Applications with expiring secrets", "suspicious OAuth grants"
- "Run a hunting query", "threat intel on this IP"
- "Create an eDiscovery case", "apply a hold on user X's mailbox"
When NOT to load this skill
This server uses application permissions (client credentials). Do not load it when the request concerns the operator's own data: their personal mailbox, calendar, OneDrive, Teams chats, or anything that should run as a connected user. Those scenarios belong to a delegated companion server such as Softeria/ms-365-mcp-server.
| Situation | Server to use |
|---|---|
| "Read my emails" | Delegated companion |
| "List tenant message traces" | ms-365-admin-mcp-server |
| "Create an event in my calendar" | Delegated companion |
| "List risky sign-ins for the last 7 days" | ms-365-admin-mcp-server |
| "Send an email to the team" | Delegated companion |
"Disable user [email protected]" |
ms-365-admin-mcp-server |
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/graph-permissions.md 5.7 KB
- references/tools-catalog.md 10 KB
- references/usecase-audit.md 3.7 KB
- references/usecase-callrecords.md 2.1 KB
- references/usecase-cloudpc.md 2.5 KB
- references/usecase-compliance.md 9.1 KB
- references/usecase-ediscovery.md 6.0 KB
- references/usecase-exchange.md 4.4 KB
- references/usecase-governance.md 11 KB
- references/usecase-health.md 2.3 KB
- references/usecase-identity.md 13 KB
- references/usecase-infoprotection.md 3.1 KB
- references/usecase-intune.md 14 KB
- references/usecase-print.md 1.2 KB
- references/usecase-reports.md 4.3 KB
- references/usecase-response.md 7.8 KB
- references/usecase-retention.md 1.3 KB
- references/usecase-security.md 4.0 KB
- references/usecase-sharepointadmin.md 4.2 KB
- references/usecase-teamsadmin.md 4.5 KB
- references/usecase-threatintel.md 6.1 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 155 lines · 82 tokens per session scan A b717e6c2266b
ms365-admin-mcp is a skill published in the GitHub repository okapi-ca/ms-365-admin-mcp-server (12 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 2,682 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…