workspace/skills/msgraph-files/SKILL.md
Manage files on OneDrive and SharePoint via Microsoft Graph API - upload, download, list, search, and organize network documentation and artifacts. Use when uploading reports to SharePoint, retrieving network docs from OneDrive, organizing config backups, or searching for topology diagrams
npx skillsauth add automateyournetwork/netclaw msgraph-filesInstall 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 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_list_files '{"driveId":"<drive-id>","folderId":"root"}'
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_search_files '{"query":"network topology diagram","driveId":"<drive-id>"}'
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_get_file_content '{"driveId":"<drive-id>","itemId":"<item-id>"}'
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_upload_file '{"driveId":"<drive-id>","parentId":"<folder-id>","fileName":"health-report-2026-02-22.md","content":"<file-content>"}'
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_create_folder '{"driveId":"<drive-id>","parentId":"root","folderName":"NetClaw Reports"}'
AZURE_TENANT_ID=$AZURE_TENANT_ID AZURE_CLIENT_ID=$AZURE_CLIENT_ID AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET \
python3 $MCP_CALL "npx -y @anthropic-ai/microsoft-graph-mcp" graph_list_sites '{}'
AZURE_TENANT_ID=$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_get_site_drive '{"siteId":"<site-id>"}'
SharePoint: Network Engineering/
├── Health Reports/
│ ├── 2026-02-22-fleet-health.md
│ └── 2026-02-21-r1-health.md
├── Security Audits/
│ └── 2026-02-22-cis-audit.md
├── Topology/
│ ├── campus-topology.vsdx
│ └── dc-fabric.vsdx
├── Configuration Backups/
│ ├── R1/
│ └── SW1/
└── Change Records/
└── CHG0012345-loopback99.md
Record file operations in GAIT:
python3 $MCP_CALL "python3 -u $GAIT_MCP_SCRIPT" gait_record_turn '{"input":{"role":"assistant","content":"Uploaded fleet health report (2026-02-22-fleet-health.md) to SharePoint Network Engineering/Health Reports/. 4 devices assessed, 1 WARNING (SW1 CPU 82%), 3 HEALTHY.","artifacts":[]}}'
tools
Federate your NetClaw with other NetClaw operators over the BGP mesh — exchange capability inventories and ask your claw what a peer can do. (US1; remote invocation and chat land in later phases.)
tools
3D network topology visualization and interactive digital twin in Unreal Engine 5.8 via the built-in UE5 MCP server.
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
IPv4 and IPv6 subnet calculator - CIDR breakdown, usable hosts, previous/next subnets, address classification, VLSM planning, and dual-stack analysis. Use when calculating subnets, figuring out how many hosts fit in a prefix, planning IP addressing, getting wildcard masks for ACLs, or checking if two IPs are in the same subnet.