Model Context Protocol (MCP)

Salfio speaks the Model Context Protocol. If your AI assistant is MCP-aware — Claude Desktop, Claude.ai web, Cursor, the MCP Inspector — it can connect to mcp.salfio.com and use the same client/activity/dashboard data your team sees in the app.

What you can do

Once connected, an MCP client sees 10 tools mapped 1:1 to the Salfio Public API:

• List and retrieve clients
• Create, update, delete clients
• Read activities (emails + calls) on a timeline
• Read the organization summary, users, and default dashboards

Every tool is scoped to your organization. Cross-tenant reads return "not found" — the same no-leak rule the REST API enforces.

Two ways to connect

Pick based on what your client supports:

• Connect from Claude.ai web — OAuth, the recommended path for the web client.
• Connect from Claude Desktop (and other API-key clients) — paste a Salfio API key into the client config.

Rate limits and quotas

MCP shares the same rate-limit buckets as the REST API: 100 requests per minute at the organization level, 50 per minute per tool. A single team can't double its quota by splitting work across REST and MCP — the buckets are deliberately unified.

See Rate Limits for the full policy.

What about data written by AI?

MCP tools that write (create_client, update_client, delete_client) make the same changes the API would. Every mutation is subject to the usual authorization and audit trail. An org_oauth connection carries organization scope — suitable for a shared team assistant, as its scope isn't tied to any one user's role — but the granting user is still recorded as the grant's owner for audit purposes. See the Claude.ai web guide for how to pick between user-scoped and org-scoped grants.