A side-by-side look at the FirstSales MCP and Kodey AI Salesforce MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose FirstSales MCP for customer data platforms work over a hosted endpoint; choose Kodey AI Salesforce MCP for customer data platforms as a local process. You can also run both side by side in one mcpServers block.
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Customer Data Platforms | Customer Data Platforms |
| Quality signal | 50/100 · Good | 40/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | OAuth 2.0 | Not declared |
| Pricing | Paid service | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | — | 0 |
| Directory activity | 1 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | Not listed | Not listed |
| Full listing | View FirstSales MCP | View Kodey AI Salesforce MCP |
No tool names declared yet. Check the project README from the listing page.
No tool names declared yet. Check the project README from the listing page.
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"firstsales-mcp": {
"url": "https://api.app.firstsales.io/mcp"
}
}
}
{
"mcpServers": {
"kodey-ai-salesforce-mcp": {
"command": "npx",
"args": [
"-y",
"@salesforce/mcp"
]
}
}
}