MCP Server - Microsoft 365 File Search (SharePoint & OneDrive)

Created By
godwin3737a year ago
Overview

MCP Server is a Model Context Protocol server implementation that provides advanced file search capabilities within Microsoft 365, specifically for SharePoint and OneDrive. It enables efficient file discovery and metadata analysis, integrating seamlessly with business workflows.

How to use MCP Server?

To use the MCP Server, you need to register an application in the Azure Portal, configure your environment variables, and integrate it with Claude Desktop by updating the configuration file. You can perform file searches and retrieve file content using the provided tools.

Key features of MCP Server?

  • Advanced file search within Microsoft 365 environment.
  • Metadata analysis for efficient file discovery.
  • Local caching for improved performance and reduced API calls.

Use cases of MCP Server?

  1. Searching for specific files in SharePoint or OneDrive.
  2. Analyzing file metadata for business insights.
  3. Integrating file search capabilities into business workflows.

FAQ from MCP Server?

  • What permissions are required to use MCP Server?

You need to grant permissions such as Sites.Read.All and Files.Read.All in the Azure Portal.

  • Is there a caching mechanism?

Yes, the server caches downloaded files locally to improve performance.

  • What programming language is used for this project?

The MCP Server is implemented in Python.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
godwin3737
Star
0
Language
Python
License
-

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

16 hours ago
Voyei

6 hours ago