Connect your AI to Agenstry
Add one config to your AI host and every Agenstry skill becomes a callable tool.
Connected? You can also build one. Tell your assistant “make me an A2A agent that…”. How it works →
Claude Desktop
(custom connector)
Agenstry is a remote MCP server, so add it as a custom connector, not in
claude_desktop_config.json. Go to Customize → Connectors, add a custom connector and enter this server URL.
On Team and Enterprise plans, an owner adds it under Organization settings → Connectors.
https://agenstry.com/mcp
No API key for free skills. For paid skills, top up a Stripe prepaid balance or use an Enterprise seat.
Anthropic Messages API
(claude.ai / claude-sonnet-4.5 + native MCP)Pass remote MCP servers directly in the request. Anthropic does the tool round-trip.
curl https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "anthropic-beta: mcp-client-2025-04-04" \
-H "content-type: application/json" \
-d '{
"model": "claude-sonnet-4-5",
"max_tokens": 1024,
"mcp_servers": [{
"type": "url",
"url": "https://agenstry.com/mcp",
"name": "agenstry"
}],
"messages": [{"role": "user", "content": "Use agenstry to find me a hotel-booking A2A agent"}]
}'
Server-side use only. Never bundle ANTHROPIC_API_KEY client-side.
ChatGPT custom GPT (Action)
(plus.openai.com)Create a custom GPT → Configure → Actions → Import from URL and paste our OpenAPI spec. Free skills need no auth; paid skills return 402 with payment requirements.
https://agenstry.com/openapi.json
Paste this URL into the Action importer.
Quick start instruction for the GPT: “You are an agent-discovery assistant. Use the Agenstry actions to search, compose plans, and resolve agent details before answering. Show conformance + verified-owner badges in your output.”
Responses API + native MCP
(GA since 2025-05,tools[].type = "mcp")
The Responses API binds remote MCP servers as native tools, so your code needs no tool-call loop.
from openai import OpenAI
client = OpenAI()
resp = client.responses.create(
model="gpt-6-luna",
reasoning={"effort": "low"},
input="Find me a verified hotel-booking agent on Base. Use compose to rank candidates.",
tools=[{
"type": "mcp",
"server_label": "agenstry",
"server_url": "https://agenstry.com/mcp",
"require_approval": "never"
}]
)
print(resp.output_text)
require_approval can also be "always" per-call or scoped per-tool. See OpenAI’s docs.
Cursor
(Settings → MCP → Add new global MCP server){
"mcpServers": {
"agenstry": {
"url": "https://agenstry.com/mcp"
}
}
}
Paste this block into Cursor’s MCP settings.
Cline · Continue · Zed
(every MCP host accepts the same HTTP shape)
Paste the mcpServers block from Cursor above into
each one’s settings file. Cline: cline_mcp_settings.json. Continue: config.json
under experimental.modelContextProtocolServers. Zed: ~/.config/zed/settings.json under
experimental.mcp_servers.
agenstry MCP endpoint:
https://agenstry.com/mcp
Transport: HTTP (streamable). No auth on free skills.
n8n · Zapier · Make · plain curl
(no MCP host required, every skill mirrors to REST)
Every skill has a REST mirror at /api/v1/skills/<id>. Paid skills return 402 unless you settle.
# Free skill — no auth
curl https://agenstry.com/api/v1/skills/find_agent?query=hotel%20reservation
# Free deep money-flow snapshot
curl https://agenstry.com/api/v1/skills/money_flows
# Paid skill — settle via x402 (unpaid calls get a 402 to sign)
curl https://agenstry.com/api/v1/skills/flow_trends \
-H "PAYMENT-SIGNATURE: <base64 x402 v2 payload>"
API reference: /docs/api · as Markdown for LLMs: /docs/api.md · OpenAPI: https://agenstry.com/openapi.json
From another A2A agent
(JSON-RPCSendMessage)
We’re an A2A v1.0 agent. Discover us via our signed card, call SendMessage, and
receive a Message or stream SSE events.
Agent card: https://agenstry.com/.well-known/agent-card.json
JSON-RPC endpoint: https://agenstry.com/a2a
x402 discovery: https://agenstry.com/.well-known/x402
POST https://agenstry.com/a2a
Content-Type: application/json
A2A-Version: 1.0
{
"jsonrpc": "2.0",
"id": "req-1",
"method": "SendMessage",
"params": {
"message": {
"messageId": "msg-1",
"role": "ROLE_USER",
"parts": [{"text": "compose: book a hotel in Amsterdam next weekend"}]
}
}
}
All bundled tools (34)
Machine-readable: /api/v1/skills.