Connect with one URL

Give your MCP client this server URL:

https://aisenseapi.com/mcp

The server is public and stateless. It works without an API key, OAuth flow or account. The same endpoint supports current MCP requests and the initialize flow used by older clients.

Use it with the OpenAI Responses API

from openai import OpenAI

client = OpenAI()

response = client.responses.create(
    model="gpt-5.6",
    tools=[
        {
            "type": "mcp",
            "server_label": "aisense",
            "server_description": "Public tools for webhooks, approvals, storage, time and IDs.",
            "server_url": "https://aisenseapi.com/mcp",
            "require_approval": "never",
        }
    ],
    input="Create a human approval request for deployment of build 42.",
)

print(response.output_text)

Change require_approval if your application should confirm tool calls. The server does not send messages, access accounts or charge money. Some tools create temporary public URLs.

Nine tools for agent workflows

Tool	Result
get_current_time	Date, time and timestamp for a timezone
generate_uuid	Random UUID version 4
shorten_url	307.fi link with 24-hour expiry
store_temporary_data	ID and URL for a stored JSON value
read_temporary_data	JSON value stored by ID
create_webhook_capture	Temporary URL for an incoming HTTP request
read_webhook_capture	Captured method, headers and body
create_human_approval	Hosted approval form and result URL
read_human_approval	Pending or answered approval result

Put a person in the loop

An agent can create a hosted approval form when it reaches a decision that needs a person. The tool returns a form URL for the reviewer and an action ID for the agent.

{
  "title": "Deploy build 42?",
  "description": "The tests passed. A person must approve production.",
  "options": ["Approve", "Reject"],
  "allow_note": true
}

The agent calls read_human_approval until the status changes from pending to answered. The form and result expire after 24 hours.

Read the Webhook Action API guide for the underlying form format.

Give an agent a webhook inbox

create_webhook_capture returns a unique update URL. Send that URL to the system that emits the webhook. The agent can then call read_webhook_capture and inspect the request.

The result includes the method, URI, headers, client IP and body. JSON stays structured. Text stays readable. Other bytes are Base64 encoded.

Read the Webhook Capture API guide for request examples.

Protocol support

The endpoint supports MCP revision 2026-07-28. It also accepts revisions 2025-11-25, 2025-06-18 and 2025-03-26 for existing clients.

The transport uses HTTP POST and JSON-RPC 2.0. The server does not issue session IDs. Each request stands on its own.

Current clients use server/discover. Older clients use initialize. Both receive the same tool list.

Limits and data

5000 requests per IP per 24 hours, shared with the REST API
256 KB maximum MCP request body
24-hour expiry for stored data, short links, captures and approval forms
Browser origins are checked against an allowlist

Temporary IDs and URLs are unguessable capability links. Send them only to the intended recipient. Do not use the public service for passwords, private keys, health data or material that needs long-term retention.

Call the protocol directly

curl -X POST https://aisenseapi.com/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "MCP-Protocol-Version: 2026-07-28" \
  -H "MCP-Method: tools/list" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/list",
    "params": {
      "_meta": {
        "io.modelcontextprotocol/protocolVersion": "2026-07-28"
      }
    }
  }'

The complete protocol notes and tool schemas are in the public GitHub documentation.

Free Public MCP Server