Model Context Protocol (MCP) server for uploading files and Markdown to SharePoint via Microsoft Graph
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"sharepoint-upload-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# sharepoint-upload-mcp Python MCP server that uploads files or Markdown to SharePoint using Microsoft Graph (same behavior as the ChartSwap `scripts/upload-to-sharepoint.py` CLI). ## Install From PyPI (after publish): ```bash pip install sharepoint-upload-mcp ``` From this monorepo (editable, for development): ```bash pip install -e ./packages/sharepoint-upload-mcp ``` ## Environment Set in `.env` at the workspace root (or in the process environment): - `SHAREPOINT_SITE_HOST`, `SHAREPOINT_SITE_PATH`, `SHAREPOINT_UPLOAD_BASE_PATH` - `MICROSOFT_TENANT_ID`, `MICROSOFT_CLIENT_ID` (or `GRAPH_ACCESS_TOKEN`) Optional: - `SHAREPOINT_MCP_REPO_ROOT` — directory used to resolve relative file paths and to load `.env`. If unset, the current working directory is used. ## Run (stdio MCP) ```bash python -m sharepoint_upload_mcp ``` Or use the console script: ```bash sharepoint-upload-mcp ``` ## Cursor / MCP config example ```json "sharepoint-upload": { "command": "py", "args": ["-m", "sharepoint_upload_mcp"], "env": { "SHAREPOINT_MCP_REPO_ROOT": "${workspaceFolder}" } } ``` ## Tools - `sharepoint_upload_file` — upload a file from disk (relative paths use `SHAREPOINT_MCP_REPO_ROOT` or cwd). - `sharepoint_upload_markdown` — upload UTF-8 Markdown with `text/markdown`.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.