Fetchpet MCP server
{
"mcpServers": {
"pulsemcp-fetchpet": {
"command": "npx",
"args": [
"-y",
"fetchpet-mcp-server@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "https://...",
"FLY_IO_API_TOKEN": "<fly_io_api_token>"
}
}
}
}{
"mcpServers": {
"pulsemcp-fetchpet": {
"command": "npx",
"args": [
"-y",
"fetchpet-mcp-server@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "https://...",
"FLY_IO_API_TOKEN": "<fly_io_api_token>"
}
}
}
}{
"mcpServers": {
"pulsemcp-fetchpet": {
"command": "npx",
"args": [
"-y",
"fetchpet-mcp-server@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "https://...",
"FLY_IO_API_TOKEN": "<fly_io_api_token>"
}
}
}
}{
"servers": {
"pulsemcp-fetchpet": {
"command": "npx",
"args": [
"-y",
"fetchpet-mcp-server@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "${input:agent_orchestrator_base_url}",
"FLY_IO_API_TOKEN": "${input:fly_io_api_token}"
}
}
},
"inputs": [
{
"id": "agent_orchestrator_base_url",
"type": "promptString",
"description": "Agent orchestrator base url",
"password": true
},
{
"id": "fly_io_api_token",
"type": "promptString",
"description": "Fly io api token",
"password": true
}
]
}{
"mcpServers": {
"pulsemcp-fetchpet": {
"command": "npx",
"args": [
"-y",
"fetchpet-mcp-server@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "https://...",
"FLY_IO_API_TOKEN": "<fly_io_api_token>"
}
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsoninstall npx -y fetchpet-mcp-serverversion 0.1.8
What it does
MCP server for automating Fetch Pet insurance claims management using Playwright browser automation. Designed for workflows that need to interact with Fetch Pet's systems programmatically.
- Automate submission and tracking of pet insurance claims through the Fetch Pet platform.
- Extract claim status and documentation requirements from Fetch Pet accounts.
- Retrieve claim history and related policy information for pet insurance management.
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.