SF-MCP is a Node.js server that exposes Salesforce CLI functionality through the Model Context Protocol, allowing AI assistants to interact with Salesforce orgs. Developed by Kevin Poorman, it dynamically discovers and registers all available SF CLI commands as MCP tools, supports project-specific command execution through configurable roots, and includes caching mechanisms for improved performance. The implementation handles contextual command execution within Salesforce project directories, making it particularly valuable for developers and administrators who need to perform Salesforce operations like querying data, deploying code, or managing orgs through AI assistants.
Aún no hay reseñas. ¡Sé el primero en reseñar!
Inicia sesión para unirte a la conversación
Highlight AIGet the Salesforce CLI version information.
Get help information for Salesforce CLI commands.
Clear the command discovery cache.
Refresh the command discovery cache.
Set a Salesforce project directory to use for commands. Parameters: directory (path to a directory containing a sfdx-project.json file), name (optional name for this project root), description (optional description for this project root), isDefault (optional set this root as the default for command execution).
List all configured project roots.
Attempt to detect project directory from user messages.
List Salesforce orgs. Parameters: json, verbose.
List authenticated Salesforce orgs. Parameters: json, verbose.
Display details about an org. Parameters: targetusername, json.
Open an org in the browser. Parameters: targetusername, path, urlonly.
Run anonymous Apex code. Parameters: targetusername, file, apexcode, json.
Run Apex tests. Parameters: targetusername, testnames, suitenames, classnames, json.
Execute a SOQL query. Parameters: targetusername, query, json.
List sObjects in the org. Parameters: targetusername, json.
Describe a Salesforce object. Parameters: targetusername, sobject, json.
Deploy the source to an org. Parameters: targetusername, sourcedir, json, wait.