Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.seamless.ai/llms.txt

Use this file to discover all available pages before exploring further.

Every MCP tool is annotated with a risk tier so agents and humans can reason about side effects before a call runs.
TierDescriptionExamples
readRead-only; no data changessearch_contacts, get_credits, list_campaigns
writeCreates or modifies dataresearch_contacts, create_campaign, send_email
destructivePermanent deletiondelete_campaign, delete_list, delete_saved_search

​
MCP client hints

Tools also expose MCP SDK hints derived from the tier:
  • readOnlyHint: true for read tools
  • destructiveHint: true for destructive tools
  • openWorldHint: true when the tool touches unbounded external data (e.g. global search graph, sending email to the public internet)
Enable human confirmation for write and destructive tools in your MCP client. Read tools are safe to run autonomously for most workflows.
destructive operations cannot be undone. Require explicit approval before delete_campaign, delete_list, or similar tools.

​
Tool reference

Each tool domain page lists tools with their risk tier. See Access control for which domains your account can use.