Salesforce CLI
Official Salesforce MCP server implementation that provides AI assistants with direct access to Salesforce development and code analysis tools through a modular provider architecture. Built by Salesforce using TypeScript and the MCP SDK, it features three core provider packages: dx-core for Salesforce org management (scratch org creation, metadata deployment, SOQL queries, permission sets), code-analyzer for static code analysis using PMD, ESLint, and other engines, and a provider API framework for extensibility. The implementation includes comprehensive toolset organization, telemetry integration, rate limiting, authentication handling, and supports both GA and non-GA tool states with dynamic tool enabling/disabling capabilities. Designed for Salesforce developers, architects, and AI-assisted development workflows, it enables use cases like automated org setup, code quality enforcement, metadata management, and development lifecycle automation without requiring manual CLI interaction.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/salesforcecli/mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Salesforce CLI from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.