model.tools — Zero-Auth Agent Utilities
RemoteAbout model.tools — Zero-Auth Agent Utilities
model.tools is a zero-auth MCP server for agents needing email verification, state, webhook, timer, and webpage utilities. Its tools also have matching REST endpoints.
Key features
- 01Extract email codes and links
- 02Persist JSON or UTF-8 checkpoints
- 03Receive webhook events
- 04Schedule wakeup callbacks
- 05Convert webpages to Markdown
- 06Issue receipts and handoff secrets
Use cases
- 01Retrieve an inbox verification code
- 02Resume a run after container resets
- 03Receive webhooks behind NAT
- 04Wake a sleeping agent on a timer
MCP support
Provides 10 tools to MCP clients through a remote Streamable HTTP endpoint or a stdio bridge. Each tool also has a corresponding zero-auth REST endpoint.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.model.tools/mcpclaude mcp add --transport http tools-model-model-tools https://mcp.model.tools/mcp{"mcpServers":{"tools-model-model-tools":{"type":"http","url":"https://mcp.model.tools/mcp"}}}Open in Cursor{"servers":{"tools-model-model-tools":{"type":"http","url":"https://mcp.model.tools/mcp"}}}Open in VS Code{"mcpServers":{"tools-model-model-tools":{"type":"http","url":"https://mcp.model.tools/mcp"}}}{"mcpServers":{"tools-model-model-tools":{"serverUrl":"https://mcp.model.tools/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEmodel.tools MCP (model-tools-mcp)
Zero-auth utilities for autonomous agents when a workflow needs an instant email verification code, a key-value checkpoint across container restarts, an inbound webhook bin behind NAT, a delayed HTTP wakeup callback, or clean URL-to-Markdown extraction — with no signup, no API key, and no OAuth.
- Remote Streamable HTTP Endpoint:
https://mcp.model.tools/mcp - REST API Twin:
https://api.model.tools - Agent Discovery (
llms.txt):https://docs.model.tools/llms.txt - Website:
https://model.tools
Quick Connect
1. Remote Streamable HTTP (Recommended)
Add directly to Claude Desktop, Cursor, Windsurf, Cline, or any Streamable HTTP MCP client:
{
"mcpServers": {
"model-tools": {
"url": "https://mcp.model.tools/mcp"
}
}
}
2. Stdio Bridge (npx)
{
"mcpServers": {
"model-tools": {
"command": "npx",
"args": ["-y", "github:maceip/model-tools-mcp"]
}
}
}
Available Tools (10)
| Tool | Description |
|---|---|
get_email_verification_code | Read <inbox>@outbox.sh (or HTTP inbox <inbox>) and extract the latest 6-digit OTP code, verification link, or magic link. Any inbox name works on demand with zero registration. |
save_agent_checkpoint | Store or read a JSON/UTF-8 checkpoint at key id (PUT/GET https://api.model.tools/api/v1/state/:id) so multi-step runs survive container resets. |
schedule_agent_wakeup | Queue a delayed HTTP POST callback to callback_url after delay_sec (1–86400s) to wake or resume a sleeping agent loop. |
receive_webhook_events | Post or poll JSON webhook events at hook_id (https://api.model.tools/api/v1/hook/:id) when running inside a NATted or serverless sandbox. |
read_webpage_as_markdown | Fetch any public http(s) webpage and return clean Markdown stripped of scripts and layout boilerplate. |
issue_task_receipt | Issue a content-addressed task completion receipt (r_...) that downstream callers or peers can verify by URL. |
arm_tripwire_inbox | Arm a watch on an inbox or state key that fires a JSON alert to alert_url the moment another party reads it. |
ask_agent_panel | Submit a question to a 3-seat reference panel (alpha, beta, gamma) and receive individual responses plus a majority vote. |
handoff_dead_drop | Store a read-once secret or token (ttl_sec) for peer-agent handoff; reading once burns the drop (410 Gone thereafter). |
arm_deadman_watchdog | Arm a deadman timer (deadline_sec) that POSTs to alert_url if your agent stops pinging /api/v1/watchdog/:id/ping. |
Plain HTTP / curl Examples
Every MCP tool has a 1:1 zero-auth REST endpoint on https://api.model.tools:
# 1. Poll an email inbox for the latest OTP / verification link
curl -s https://api.model.tools/api/v1/inbox/my-agent-run/latest_otp
# 2. Save and read a checkpoint
curl -s -X PUT https://api.model.tools/api/v1/state/run-42 \
-H 'Content-Type: application/json' \
-d '{"step":3,"cursor":"abc"}'
curl -s https://api.model.tools/api/v1/state/run-42
# 3. Inspect or post to a webhook bin
curl -s -X POST https://api.model.tools/api/v1/hook/build-7 \
-H 'Content-Type: application/json' \
-d '{"status":"ready"}'
curl -s https://api.model.tools/api/v1/hook/build-7
# 4. Schedule a wakeup callback
curl -s -X POST https://api.model.tools/api/v1/schedule \
-H 'Content-Type: application/json' \
-d '{"callbackUrl":"https://api.model.tools/api/v1/hook/wake-test","delaySec":30,"payload":{"resume":true}}'
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.