sf-opensearch-logging-mcp
Enables querying ShareFile OpenSearch production logs via MCP with automatic EntraID OAuth authentication.
README
sf-opensearch-logging-mcp
Remote HTTP Streamable MCP server for ShareFile OpenSearch production logs with EntraID OAuth.
Overview
This service wraps opensearch-mcp-server-py with:
- HTTP Streamable transport at
/mcp(and SSE fallback at/sse) - EntraID OAuth with RFC 9728 Protected Resource Metadata for zero-config client discovery
- SigV4 auth to OpenSearch via IRSA (cross-account assume role)
User Setup
Add to your VS Code settings.json or .vscode/mcp.json:
{
"mcpServers": {
"sharefile-opensearch": {
"type": "http",
"url": "https://mcp.sharefile-coretools.com/mcp"
}
}
}
That's it. The MCP client handles OAuth discovery and login automatically.
Requirements: Must be on the Progress corporate network.
Architecture
VS Code MCP Client
│ HTTPS + OAuth Bearer token
▼
Internal ALB (ops-coretools)
│
▼
MCP Server Pod (this service)
│ SigV4 via IRSA
▼
OpenSearch VPC Endpoint (381491976936)
Environment Variables
| Variable | Required | Description |
|---|---|---|
AZURE_TENANT_ID |
No | EntraID tenant (default: db266a67-cbe0-4d26-ae1a-d0581fe03535) |
AZURE_CLIENT_ID |
Yes | EntraID app registration client ID |
AZURE_ALLOWED_GROUP_ID |
No | EntraID group ID for access control (empty = any authenticated user) |
MCP_BASE_URL |
No | Public base URL (default: https://mcp.sharefile-coretools.com) |
MCP_PORT |
No | Server port (default: 8080) |
OPENSEARCH_URL |
Yes | OpenSearch VPC endpoint URL |
AWS_REGION |
No | AWS region (default: us-east-1) |
Local Development
uv venv && source .venv/bin/activate
uv pip install -e ".[dev]"
# Set required env vars
export AZURE_CLIENT_ID="your-app-id"
export OPENSEARCH_URL="https://vpc-prod-us-east-1-....es.amazonaws.com"
python -m opensearch_mcp_remote
Deployment
Deployed on ops-coretools EKS cluster via ArgoCD. See the coretools repo for K8s manifests.
Endpoints
| Path | Method | Auth | Description |
|---|---|---|---|
/mcp |
POST | Bearer | MCP Streamable HTTP |
/sse |
GET | Bearer | SSE transport (fallback) |
/health |
GET | None | ALB health check |
/.well-known/oauth-protected-resource |
GET | None | OAuth discovery metadata |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.