mcp-setuplisted

# MCP Setup ## Overview MCP turns AI agents into tool-using operators. The risk is that teams connect every tool, expose write access, and then wonder why the agent behaves unpredictably. Good MCP setup is not "give the agent more tools." It is tool curation, permission design, and auditability. This skill configures MCP for GTM workflows where agents research accounts, enrich records, inspect CRM, draft messaging, and route tasks without uncontrolled external side effects. ## When to Use Use this skill when the user asks to "set up MCP for sales tools", "connect our CRM to Claude/Cursor", "give my agent enrichment capabilities", "build an MCP server for GTM tools", "configure MCP permissions", "connect LeadMagic MCP", "orchestrate multiple MCP servers", or "make agent tool use safer". Do not use this for general agent architecture. Use `agent-architecture` first when the workflow itself is undefined. ## Authoritative Foundations ### Model Context Protocol Specification MCP standardizes how agents discover tools, resources, and prompts. The key design principle is clear tool descriptions and predictable tool inputs/outputs. ### Anthropic — Tool Use Design Patterns Tools should be narrowly described, unambiguous, and paired with verification steps. Agents need clear rules for when to call a tool and when to ask for confirmation. ### Least Privilege Access Control Agents should receive the minimum access needed for the current task. Read-only first, write access only