workspace/skills/msgraph-teams/SKILL.md
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
npx skillsauth add automateyournetwork/netclaw msgraph-teamsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The Microsoft Graph MCP server is invoked via npx with Azure AD credentials:
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" <tool-name> '<arguments-json>'
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_list_teams '{}'
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_list_channels '{"teamId":"<team-id>"}'
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_send_channel_message '{"teamId":"<team-id>","channelId":"<channel-id>","message":"<html-content>"}'
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_reply_to_message '{"teamId":"<team-id>","channelId":"<channel-id>","messageId":"<msg-id>","message":"<html-content>"}'
AZURE_TENANT_ID=$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>"}'
<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>
<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>
<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>
<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 threads
Record Teams notifications in GAIT:
python3 $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":[]}}'
testing
Human-in-the-loop escalation via HumanRail — route low-confidence agent decisions, pre-destructive operation approvals, and ambiguous incident tickets to real human engineers. Human answers are verified and returned as structured output. Workers are paid via Lightning Network. Use when the agent is uncertain, when a destructive change needs explicit human sign-off beyond a ServiceNow CR, or when an ambiguous ticket requires human triage before automated handling.
testing
Manage EVE-NG node lifecycle. Use when listing nodes, checking runtime state, creating or deleting nodes, starting or stopping nodes or whole labs, verifying node details, or wiping node NVRAM back to factory defaults.
development
Manage EVE-NG labs and platform inventory. Use when listing labs, checking lab metadata, creating or deleting labs, importing or exporting lab archives, checking EVE-NG health or auth, or verifying available node images before build work.
tools
Execute live CLI commands on running EVE-NG nodes over telnet console. Use when running show commands, making live config changes, verifying protocol state, testing connectivity, checking console readiness, or interacting with IOS, Junos, VPCS, EOS, or NX-OS nodes.