MCP Agents

Why use MCP with SafeFetch?

MCP gives agents safe, structured primitives for background execution instead of direct long-running HTTP calls.

MCP server setup (Claude Desktop)

See full setup in MCP Setup. Once configured, your agent can call SafeFetch tools directly.

All 6 tools

send_action

Send an action with approval, dedupe, and idempotency.

get_action

Fetch status, results, errors, and next actions.

cancel

Cancel pending/awaiting_approval actions.

approve

Approve an action awaiting human review.

retry

Create a retry copy from failed/cancelled action.

list_actions

List/filter recent actions.

Conversation example

User: Send a charge request to the billing API for customer 42.
Agent: I'll send that for your approval first.
Agent (tool: send_action): {"url":"https://api.example.com/charge","approve":true, ...}
Agent: Action queued as act_123. Awaiting your approval before delivery.

Polling pattern for async action results

1) send_action
2) store returned action id
3) poll get_action every 2-5s
4) stop when status in [completed, failed, cancelled]

ACT_ID=$(curl -s -X POST http://localhost:3000/v1/actions ... | jq -r .id)

while true; do
  STATUS=$(curl -s http://localhost:3000/v1/actions/$ACT_ID -H "Authorization: Bearer <API_KEY>" | jq -r '.status')
  echo "status=$STATUS"
  case "$STATUS" in
    completed|failed|cancelled) break ;;
  esac
  sleep 3
done

Getting Started

CLI

Core Concepts

Guides

Templates

MCP Server

Why use MCP with SafeFetch?

MCP server setup (Claude Desktop)

All 6 tools

send_action

get_action

cancel

approve

retry

list_actions

Conversation example

Polling pattern for async action results

​Why use MCP with SafeFetch?

​MCP server setup (Claude Desktop)

​All 6 tools

send_action

get_action

cancel

approve

retry

list_actions

​Conversation example

​Polling pattern for async action results

Why use MCP with SafeFetch?

MCP server setup (Claude Desktop)

All 6 tools

Conversation example

Polling pattern for async action results