Salesforce Copilot MCP
Enables Microsoft 365 Copilot to interact with Salesforce through REST APIs, supporting queries, object descriptions, pipeline summaries, and anomaly detection.
README
Salesforce MCP for Microsoft 365 Copilot
This project hosts a remote MCP server for Microsoft 365 Copilot and Teams scenarios. It preserves the existing Salesforce toolset and Salesforce OAuth flow, but removes the Claude-specific OAuth broker and replaces it with Microsoft identity on Azure App Service.
Exposed tools
query_salesforcedescribe_objectget_pipeline_summarylist_recent_activitydetect_anomaliesget_schema_context
Runtime architecture
Microsoft 365 Copilot / Teams -> Federated connector -> Azure App Service hosted MCP server -> Salesforce REST APIs
Authentication model
- Microsoft identity is supplied to the app by Azure App Service Authentication.
- The app resolves the signed-in Microsoft user from App Service headers.
- That user starts Salesforce sign-in at
/auth/salesforce/start. - Salesforce OAuth tokens are stored per Microsoft user session.
- MCP requests on
/mcpexecute with that user's Salesforce session.
Key endpoints
GET /healthGET /auth/statusGET /auth/salesforce/startGET /auth/salesforce/callbackGET /auth/salesforce/disconnectPOST /mcpGET /ssePOST /message
Local development
- Copy
.env.exampleto.env. - Fill in Salesforce values.
- For local testing only, set
DEV_BYPASS_USER_IDand optionally the otherDEV_BYPASS_*values. - Run
npm install. - Run
npm run buildandnpm start. - Open
http://localhost:3000/auth/salesforce/startto connect Salesforce.
Azure deployment
See AZURE-DEPLOYMENT.md for the Azure App Service and Microsoft 365 Copilot setup.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.