Connects AI clients to Salesforce orgs for org inspection, record access, metadata deployment, retrieval, and Apex review.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Kodey AI Salesforce MCP.
kodey-ai-salesforce-mcp MCP server provides an MCP interface for working with Salesforce orgs. It is intended for agent-assisted Salesforce DX tasks, including finding authorized orgs, checking scratch-org status, viewing org records, and working with project metadata.
The documented examples also cover deploying a project to an org, retrieving metadata, reviewing Apex code for possible performance or security problems, and explaining PMD rules such as ApexCRUDViolation. The repository describes the implementation as a developer preview, so its commands, parameters, and available tools may change.
The server runs as a local stdio process. A client starts it with npx and passes startup flags that determine which Salesforce orgs it may access and which toolsets or individual tools are enabled. The example configuration uses the @salesforce/mcp package and supplies an org alias through --orgs.
Authentication is based on authorization data already stored on the user's computer by Salesforce tooling. The server uses TypeScript libraries directly instead of invoking the Salesforce CLI as a shell command. It passes usernames rather than access tokens through MCP tools and restricts access to explicitly allowed orgs.
Before configuring the server, the documented setup expects Salesforce CLI, VS Code, a Salesforce DX project, and at least one authorized Salesforce org. A scratch org can also be used.
For VS Code, add a .vscode/mcp.json file in the DX project, or configure the server globally in VS Code settings. A representative configuration starts the package over stdio and includes:
--orgs to define the authorized orgs the server can use.--toolsets to select a group of tools.--tools to select individual tools when finer control is needed.--allow-non-ga-tools when access to non-generally-available tools is required by the configuration.The README also documents installation through Smithery with the @kodey-ai/salesforce-mcp-kodey package. Agentforce for Developers includes the Salesforce DX MCP server preconfigured in its VS Code extension.
Configured capabilities support several Salesforce development workflows:
The exact tools available depend on the selected toolsets and flags. The documented examples show natural-language requests being routed to the appropriate configured tool, with the client presenting the action and its results.
kodey-ai-salesforce-mcp MCP server is marked as a developer preview. The README warns that functionality, commands, parameters, and tools can change or be deprecated without notice, and advises against implementing dependent functionality around the preview commands.
The --orgs option is required in the documented VS Code setup. Only explicitly allowlisted orgs are available to the server. This project should therefore be evaluated with those preview status and access-control requirements in mind before being used in a stable automation workflow.
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/kodey-ai-salesforce-mcp)<a href="https://allmcps.com/mcp/kodey-ai-salesforce-mcp"><img src="https://allmcps.com/api/badge/kodey-ai-salesforce-mcp?style=directory" alt="Kodey AI Salesforce MCP on AllMCPs" /></a>