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.
git clone --depth 1 https://github.com/vivy-yi/finance-skillsWrote 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/mcp/vivy-yi/finance-skills/sharepoint)<a href="https://agentmods.dev/mcp/vivy-yi/finance-skills/sharepoint"><img src="https://agentmods.dev/badge/mcp/vivy-yi/finance-skills/sharepoint/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/mcp/vivy-yi/finance-skills/sharepoint"><img src="https://agentmods.dev/badge/mcp/vivy-yi/finance-skills/sharepoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sharepoint 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 1mo 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.
What it actually says
{
"sharepoint": {
"type": "http",
"url": "https://{tenant}.sharepoint.com/_api/v2.0",
"description": "SharePoint REST API — finance document library, audit reports, board decks, compliance documents, integration with Microsoft 365.",
"auth": {
"type": "oauth2",
"provider": "microsoft-entra"
},
"tools": [
"sp_finance_library_read",
"sp_finance_library_write",
"sp_board_deck_read",
"sp_audit_report_read",
"sp_compliance_doc_read",
"sp_search"
],
"scenarios": [
"board-reporting",
"audit-support",
"compliance-reporting",
"internal-control",
"m-and-a"
]
}
}What else .mcp.json configures
This page is one entry in a file that holds 14. Installing the file brings all of them; each is measured and scanned on its own page.
- MCP server anaplan A not measured
- MCP server blackline A not measured
- MCP server bloomberg A not measured
- MCP server finereport A not measured
- MCP server kyriba A not measured
- MCP server power-bi A not measured
- MCP server refinitiv A not measured
- MCP server sap-concur A not measured
- MCP server sap-s4hana A not measured
- MCP server tableau A not measured
- MCP server taxdome A not measured
- MCP server vertex-o A not measured
- MCP server workday-hcm A not measured
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.
- 1mo ago First seen · 26 lines scan A 3cebee893486
sharepoint is an MCP server published in the GitHub repository vivy-yi/finance-skills (42 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-30.
Other mcp servers, from other repositories
edinet
EDINET XBRL parsing library and MCP server for Japanese financial data. Runs locally from the edinet-mcp Python package. Needs 1 environment variable to run.
moxie-docs
MCP server "moxie-docs", hosted remotely at moxiedocs.com, as configured in Jackalope-Dev/Moxie-Docs-MCP.
cashflow13
13-week cash flow plan with a live Excel workbook, not just an answer in chat. Remote server at mcp.chiriba.it.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.
component-explorer
MCP server "component-explorer" as configured in microsoft/vscode. Launched with npm exec --no -- component-explorer mcp -p ./test/componentFixtures/component-ex.
reference-langchain
MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.