Azure AI AgentsSAFE
Model Context Protocol Servers for Azure AI Search
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that enables Claude Desktop to search your content using Azure AI services. Choose between Azure AI Agent Service (with both document search and web search) or direct Azure AI Search integration.
Overview
This project provides two MCP server implementations to connect Claude Desktop with Azure search capabilities:
- Azure AI Agent Service Implementation (Recommended) - Uses the powerful Azure AI Agent Service to provide:
- Azure AI Search Tool - Search your indexed documents with AI-enhanced results
- Bing Web Grounding Tool - Search the web with source citations
- Direct Azure AI Search Implementation - Connects directly to Azure AI Search with three methods:
- Keyword Search - Exact lexical matches
- Vector Search - Semantic similarity using embeddings
- Hybrid Search - Combination of keyword and vector searches
Features
- AI-Enhanced Search - Azure AI Agent Service optimizes search results with intelligent processing
- Multiple Data Sources - Search both your private documents and the public web
- Source Citations - Web search results include citations to original sources
- Flexible Implementation - Choose between Azure AI Agent Service or direct Azure AI Search integration
- Seamless Claude Integration - All search capabilities accessible through Claude Desktop's interface
- Customizable - Easy to extend or modify search behavior
Quick Links
Requirements
- Python: Version 3.10 or higher
- Claude Desktop: Latest version
- Azure Resources:
- Azure AI Search service with an index containing vectorized tex
f4a866b51563OBSERVED · 2026-10-08Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
hybrid_search | read | |
keyword_search | read | |
search_index | read | |
vector_search | read | |
web_search | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
images/demo.gif
Gates applied: no_behavioural_pass.
f4a866b51563full audit observations/trust-audit/mcp-server/farzad528__azure-ai-agents.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | f4a866b51563 | SAFE | B | 89 | first audit |
Questions
What is the Azure AI Agents MCP server?
Model Context Protocol Servers for Azure AI Search
What tools does Azure AI Agents expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Azure AI Agents safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Azure AI Agents need?
It reads AZURE_SEARCH_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (f4a866b51563), read on 2026-10-08. The repository is watched and re-audited when it changes.