https://github.com/vinkius-labs/salesforce-mcp
Vinkius Edge enterprise Model Context Protocol (MCP) server for Salesforce CRM standard objects and SOQL.
https://github.com/vinkius-labs/salesforce-mcp
ai-agent ai-agents crm enterprise llm-tool mcp mcp-server modelcontextprotocol salesforce soql vinkius vinkius-edge
Last synced: about 1 month ago
JSON representation
Vinkius Edge enterprise Model Context Protocol (MCP) server for Salesforce CRM standard objects and SOQL.
- Host: GitHub
- URL: https://github.com/vinkius-labs/salesforce-mcp
- Owner: vinkius-labs
- Created: 2026-06-20T06:32:38.000Z (about 1 month ago)
- Default Branch: master
- Last Pushed: 2026-06-20T07:04:54.000Z (about 1 month ago)
- Last Synced: 2026-06-20T08:18:01.079Z (about 1 month ago)
- Topics: ai-agent, ai-agents, crm, enterprise, llm-tool, mcp, mcp-server, modelcontextprotocol, salesforce, soql, vinkius, vinkius-edge
- Language: TypeScript
- Homepage: https://vinkius.com/mcp/salesforce
- Size: 22.5 KB
- Stars: 3
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# ☁️ Salesforce CRM Model Context Protocol (MCP)
[](https://vinkius.com/mcp/salesforce)
[](https://hub.docker.com/r/vinkius/salesforce-mcp)
Turn your AI into a fully autonomous sales operations manager. This server provides a native Model Context Protocol bridge directly into Salesforce CRM, allowing large language models (LLMs) to natively query, mutate, and analyze your enterprise data pipeline without writing a single line of API glue code.
## Why use this integration?
Connecting ChatGPT, Claude, or any custom agent to your CRM usually involves brittle Zapier flows or custom middleware. This MCP exposes a structured, intent-driven interface. Whether you need to run complex SOQL aggregates or execute routine CRUD operations on custom objects, the agent handles it safely.
### Built for the Vinkius Edge Platform
We designed this connector specifically to be hosted on the **Vinkius Edge**. When you deploy your agentic infrastructure on Vinkius, you benefit from:
- **Zero-Trust Security**: Vinkius securely stores your Salesforce OAuth tokens. The AI never sees your underlying credentials.
- **Edge Performance**: Running on V8 isolates via Vinkius guarantees ultra-low latency, crucial when AI agents execute multi-step SOQL chain reasoning.
- **Instant Scale**: Stop managing Node.js PM2 servers. Vinkius handles the infrastructure seamlessly.
## Available Agentic Capabilities
The server registers 12 distinct tools designed for semantic consumption:
- **Data Retrieval**: Execute raw `soql_query` or use optimized `list_accounts`, `list_contacts`, and `list_opportunities` fetchers.
- **Deep Exploration**: The `global_search` tool leverages SOSL to find entities across the entire Salesforce org instantly.
- **Full Lifecycle**: Complete `get_record`, `create_record`, `update_record`, and `delete_record` support for standard and custom SObjects.
- **Analytics**: Expose your existing pipeline dashboards directly to the LLM via `list_reports` and `run_report`.
## 🚀 Deployment Guide
To get this running on the **Vinkius Edge Marketplace**:
1. Pull the repository to your environment.
2. Initialize the deployment to Vinkius:
```bash
npx mcpfusion deploy
```
Within seconds, your MCP will be globally distributed and available for connection.
🔗 **[Claim your free edge hosting for the Salesforce MCP on Vinkius](https://vinkius.com/mcp/salesforce)**
### Testing Locally
For engineers modifying the core engine using `@mcpfusion/core`:
```bash
npm install && npm run dev
```