Kodey AI Salesforce MCP vs Salesforce
A side-by-side look at the Kodey AI Salesforce MCP and Salesforce MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Kodey AI Salesforce MCP for customer data platforms work as a local process; choose Salesforce for customer data platforms over a hosted endpoint. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Kodey AI Salesforce MCP when
- You need dedicated capabilities in the Customer Data Platforms domain.
- You prefer a local stdio subprocess transport.
Choose Salesforce when
- You need dedicated capabilities in the Customer Data Platforms domain.
- You prefer a remote HTTP/SSE transport.
- You have the keys it needs:
MCP_TRANSPORT, SALESFORCE_AUTH_FLOW, SALESFORCE_CLIENT_ID, SALESFORCE_CLIENT_SECRET, SALESFORCE_INSTANCE_URL, SALESFORCE_USERNAME, SALESFORCE_PASSWORD, SALESFORCE_TOKEN. - You want tools like
salesforce_search_objects, salesforce_describe_object, salesforce_query_records.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Customer Data Platforms | Customer Data Platforms |
| Quality signal | 40/100 · Fair | 51/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Remote HTTP/SSE |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | MCP_TRANSPORTSALESFORCE_AUTH_FLOWSALESFORCE_CLIENT_IDSALESFORCE_CLIENT_SECRETSALESFORCE_INSTANCE_URLSALESFORCE_USERNAMESALESFORCE_PASSWORDSALESFORCE_TOKEN |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 0 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | Not listed | 6 |
| Full listing | View Kodey AI Salesforce MCP | View Salesforce |
Tools & capabilities
Kodey AI Salesforce MCP tools
No tool names declared yet. Check the project README from the listing page.
Salesforce tools 6
salesforce_search_objectsFind standard + custom objects by partial name.salesforce_describe_objectFull schema (fields, picklists, relationships) for an object.salesforce_query_recordsExecute SOQL with relationship traversal.salesforce_aggregate_querySOQL GROUP BY / COUNT / SUM / AVG / MIN / MAX.salesforce_dml_recordsInsert / update / delete / upsert records.salesforce_search_allCross-object SOSL search.
Ready-to-paste client configs
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.
Kodey AI Salesforce MCP
{
"mcpServers": {
"kodey-ai-salesforce-mcp": {
"command": "npx",
"args": [
"-y",
"@salesforce/mcp"
]
}
}
}
Salesforce
{
"mcpServers": {
"salesforce": {
"url": "https://mcp.wyre.ai/"
}
}
}
Frequently asked questions
Kodey AI Salesforce MCP is categorized under Customer Data Platforms and uses a local stdio subprocess. Salesforce belongs to Customer Data Platforms and uses a remote HTTP/SSE transport. Pick Kodey AI Salesforce MCP for customer data platforms work and Salesforce for customer data platforms.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Kodey AI Salesforce MCP has no declared pricing — check the project's own site. Salesforce has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add kodey-ai-salesforce-mcp and salesforce as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Kodey AI Salesforce MCP has a quality signal of 40/100 (Fair) with 0 views, 0 installs and 0 GitHub stars. Salesforce has 51/100 (Good) with 0 views, 0 installs and 0 GitHub stars.