Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Send notifications and reports to Microsoft Teams channels via Graph API - alert delivery, report posting, incident updates, and diagram sharing. Use when posting health alerts to Teams, sending security notifications, sharing change completion updates, or delivering reports to a Teams channel
.claude/skills/automateyournetwork-msgraph-teams/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 143% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 105% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 49% | 0% |
The Microsoft Graph MCP server is invoked via npx with Azure AD credentials:
bashAZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \ python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" <tool-name> '<arguments-json>'
bashAZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \ python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_list_teams '{}'
bashAZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \ python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_list_channels '{"teamId":"<team-id>"}'
bashAZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \ python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_send_channel_message '{"teamId":"<team-id>","channelId":"<channel-id>","message":"<html-content>"}'
bashAZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \ python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_reply_to_message '{"teamId":"<team-id>","channelId":"<channel-id>","messageId":"<msg-id>","message":"<html-content>"}'
bashAZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \ python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_list_channel_messages '{"teamId":"<team-id>","channelId":"<channel-id>"}'
html<h3>Health Check Report — 2026-02-22</h3> <table> <tr><th>Device</th><th>CPU</th><th>Memory</th><th>Status</th></tr> <tr><td>R1</td><td>23%</td><td>45%</td><td>HEALTHY</td></tr> <tr><td>SW1</td><td>82%</td><td>67%</td><td>WARNING</td></tr> </table> <p><strong>1 WARNING</strong> — SW1 CPU at 82% (threshold: 80%)</p>
html<h3>CRITICAL — CVE Exposure Detected</h3> <p><strong>Device:</strong> R1 (IOS-XE 17.9.4a)</p> <p><strong>CVE-2023-20198</strong> (CVSS 10.0) — Web UI privilege escalation</p> <p><strong>Exposure:</strong> CONFIRMED — ip http server enabled</p> <p><strong>Action Required:</strong> Disable ip http server or upgrade immediately</p>
html<h3>Change Complete — CHG0012345</h3> <p><strong>Target:</strong> R1 — Add Loopback99 (99.99.99.99/32)</p> <p><strong>Status:</strong> SUCCESS — verified, CR closed</p> <p><strong>GAIT Branch:</strong> config-r1-loopback99-2026-02-22</p>
html<h3>Updated Network Topology</h3> <p>Campus physical topology regenerated from CDP/LLDP discovery.</p> <p><strong>Devices:</strong> 4 | <strong>Links:</strong> 6 | <strong>Changes:</strong> +1 new link (R2-SW2)</p> <p><a href="https://contoso.sharepoint.com/sites/neteng/Topology/campus-physical-2026-02-22.vsdx">Open in Visio</a></p>
Map Teams channels to NetClaw notification types:
### Teams Channel Map (configure in TOOLS.md)
- #netclaw-alerts → P1/P2 critical alerts, CVE exposure
- #netclaw-reports → Health reports, audit results, reconciliation
- #netclaw-changes → Change request updates, completion notices
- #network-general → P3/P4 notifications, topology updates
- #incidents → Active incident investigation threadsRecord Teams notifications in GAIT:
bashpython3 $MCP_CALL "python3 -u $GAIT_MCP_SCRIPT" gait_record_turn '{"input":{"role":"assistant","content":"Posted fleet health report to Teams #netclaw-reports channel. 4 devices assessed: 3 HEALTHY, 1 WARNING (SW1 CPU 82%). Included table with CPU, memory, and interface status per device.","artifacts":[]}}'
Other measured skills in the registry, with their headline benchmark lift.