Salesforce
This Salesforce MCP server, developed by tsmztech, integrates Claude AI with Salesforce CRM, enabling natural language interactions for data and metadata management. Built with TypeScript and leveraging the jsforce library, it offers tools for object searching, schema retrieval, record querying, and data manipulation. The implementation focuses on providing intuitive access to Salesforce's complex data structures and operations, making it accessible for AI models to perform tasks like creating custom objects, querying records across relationships, and managing fields. It's particularly useful for automating Salesforce administration, enhancing data analysis workflows, or integrating Salesforce capabilities into AI-driven business processes, allowing assistants to interact with Salesforce without deep API knowledge.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- productivity
- Source
- PulseMCP
- Repository
- github.com/tsmztech/mcp-server-salesforce
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Salesforce 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.