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 icemage001/local_sharepoint_mcp --skill sharepoint-mcpgit clone --depth 1 https://github.com/icemage001/local_sharepoint_mcpWrote 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/icemage001/local_sharepoint_mcp/sharepoint-mcp)<a href="https://agentmods.dev/skills/icemage001/local_sharepoint_mcp/sharepoint-mcp"><img src="https://agentmods.dev/badge/skills/icemage001/local_sharepoint_mcp/sharepoint-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/icemage001/local_sharepoint_mcp/sharepoint-mcp"><img src="https://agentmods.dev/badge/skills/icemage001/local_sharepoint_mcp/sharepoint-mcp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00084 | $0.00896 |
| Opus 5 | $0.00042 | $0.00448 |
| Sonnet 5 | $0.00017 | $0.00179 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
sharepoint-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 11d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SharePoint MCP
Use only the tools provided by the sharepoint-local MCP server. Do not issue direct HTTP requests, use browser automation as a substitute, expose the local bridge, or reveal a bearer token.
Establish context
Before every write, call get_health and get_active_site. Confirm the active site's siteId and siteUrl match the user’s explicit target. If no matching site is locked:
- Call
list_captured_sites. - With a valid Graph token, call
resolve_sitefor the requested URL. - Lock the returned identity using
set_active_site, then callget_active_siteagain.
Use set_active_site_from_tab only after checking that the captured tab is the requested site and has a resolved site ID. Never reuse a lock just because its hostname looks similar.
Select the API surface
- Prefer a valid Graph token for lists, list items, columns, and modern pages; these tools can fall back to SharePoint REST v2 with a valid SharePoint token. Drives/files remain Graph-only.
- Require a valid SharePoint REST token for groups, permissions, views, and column/view formatting.
- Treat the two token audiences as non-interchangeable. If the required token is missing, ask the user to refresh or navigate the SharePoint page, then re-check
get_health.
See references/tool-catalog.md for every available tool, its input, and its safe use.
Read workflow
Lock the site first, then use the applicable list_*, get_*, search_site_users, get_*_formatting, list_role_definitions, or list_recycle_bin tool. Return the active site and IDs used with the result so the user can verify scope.
Write workflow
Require an explicit target and user approval for every real-site write. For operations that change existing content, permissions, formatting, or delete anything:
- Re-read the target when a
get_*tool is available. - Call the exact matching
preview_*tool immediately before applying. - Inspect the returned
previewId,target.siteId,target.siteUrl, object ID,riskLevel, andsummary. - Apply only that returned
previewIdusing its pairedapply_*ordelete_*tool. Never invent, alter, reuse after expiry, or substitute a preview ID. - Read back through the relevant API and report the result.
What ships with it
2 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.
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.
- 11d ago First seen · 55 lines · 84 tokens per session scan A 9624bdc1512d
sharepoint-mcp is a skill published in the GitHub repository icemage001/local_sharepoint_mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 896 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
ppt-template-creator
Creates self-contained PPT template SKILLS (not presentations) from user-provided PowerPoint templates. Use ONLY when a user wants to create a reusable skill from their template. For creating actual presentations, use the pptx skill instead.
box
Box manages cloud files, sharing, search, and metadata.
cim-builder
Structure and draft a Confidential Information Memorandum for sell-side M&A processes. Organizes company information into a professional, investor-ready document with consistent formatting and narrative flow. Use when preparing sell-side materials, drafting a CIM, or organizing company data for a sale process.…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.