runnerID by Torchrunner MCP Server

by torchrunner Your server? Claim it

answering

runnerID by Torchrunner is answering right now. Last checked 8 min ago. It exposes 20 tools.

Logs your AI agent into websites, catches verification codes, and asks you before anything risky.

Uptime history 10 days of history

10 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

318 ms

Response time

average over 24h

OAuth sign-in

Access

streamable-http

What changed 5

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 24 October 2026. No other catalogue keeps this.

24 Oct 5 tools appeared cancel_run, get_run, handoff_task and 2 more

Nothing serious here today

Today is the operative word: we check runnerID by Torchrunner every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add runnerid --transport http https://api.runnerid.torchrunner.ai/mcp

Settings → Connectors → Add custom connector, then paste this address

https://api.runnerid.torchrunner.ai/mcp

~/.codex/config.toml

[mcp_servers.runnerid]
url = "https://api.runnerid.torchrunner.ai/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "runnerid": {
      "url": "https://api.runnerid.torchrunner.ai/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "runnerid": {
      "type": "http",
      "url": "https://api.runnerid.torchrunner.ai/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.

Available tools 20

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

fill

fill_code

Type the current authenticator code into the matching page over CDP. The code is not returned.

fill_email_code

Wait for an email code and type it into the matching page over CDP. The code is not returned.

fill_login

Type the saved username and password into the matching page over CDP. The password is not returned.

save

save_authenticator

Store an authenticator (TOTP) seed for a site: a base32 seed or an otpauth:// URI. The seed is encrypted and is not returned.

save_login

Store a site login. The secret is encrypted and is not returned.

save_session

Save cookies and localStorage for one site from the browser at cdp_url. Cookie values are not returned.

wait

wait_for_approval

Wait until an approval is no longer pending, or the timeout elapses. timeout_seconds defaults to 30.

wait_for_email_code

Wait until an email code arrives. The code is consumed and is not returned. Use fill_email_code to type it into the page.

wait_for_login

Wait until the owner has typed the login from request_login, or the timeout elapses (default 120 seconds, at most 300). Returns status: pending, fulfilled or expired. The login itself is never returned.

request

request_approval

Ask the account owner to approve an action. Returns approval_id and status. The email token is not returned.

request_login

Ask the owner for a login runnerID does not have yet. The owner gets a secure one-time link by email and types the username and password there; the password goes straight into the vault and never passes through you. Returns request_id. Then call wait_for_login, and fill_login once it is fulfilled.

authenticator

get_authenticator_code

Return the current six-digit authenticator code for a site, for agents whose browser runnerID cannot reach. The code lasts about 30 seconds and the release is logged. The seed is never returned. Prefer fill_code when you have a cdp_url.

cancel

cancel_run

Cancel a handoff that has not finished.

get_email_code

Wait for an emailed verification code and return it, for agents whose browser runnerID cannot reach. The code is consumed and the release is logged. Prefer fill_email_code when you have a cdp_url.

events

list_events

List recent events for an identity, newest first. Event data does not include secrets.

get

get_run

Read a handoff: its status, the result when done, or why it failed or what it is waiting for. wait_seconds waits up to 120 seconds for it to change first.

handoff

handoff_task

Hand runnerID a step you cannot finish, such as work on a site you cannot sign in to. runnerID does it as this identity in its own browser, asks the owner before anything risky, and returns the result. Returns run_id at once; call get_run to read the result.

identity

get_identity

Read one identity, including its inbox address. The result has no secrets.

open

open_magic_link

Wait for a magic link whose host is the site, or a trusted subdomain, and open it. site is required. The link is not returned.

restore

restore_session

Restore a saved session into the browser at cdp_url. Cookie values are not returned.

Endpoints

URL	Transport	State	Latency	Checked
https://api.runnerid.torchrunner.ai/mcp	streamable-http	sign-in	297 ms	8 min ago

Alternatives to runnerID by Torchrunner

same job, measured the same way

Botcall MCP

by danecodes

Give your AI agent a real phone number for SMS verification codes.

34 installs/wk local only

Code Interpreter Agent by Nova (CIVAI)

by civai-nova

I do everything related to coding and execution tasks

8 tools answering

GitMir Vibe

by gitmir

Your coding agent asks the business logic of your repository and checks commits before they land

answering

GetCourier

by getcourier

Email inboxes for AI agents: no signup, wait for verification codes and magic links.

14 tools answering

Steadfast Repository Governance

by rllibo833-sudo

Local-first repository governance and verification tools for AI coding agents.

838 installs/wk local only

Machine Inbox

by machineinbox

Task-scoped email inboxes for AI agents: read mail, extract verification codes, and reply.

11 tools answering

Innmail for Agents

by innmail

Email inbox for an AI agent: threads, send, reply, drafts, verification codes, calendar.

answering

Temp Mail

by temp-mail

Disposable email inboxes for AI agents — read messages and verification codes.

answering

runnerID by Torchrunner — questions

Answers built from our own checks of this server.

What can runnerID by Torchrunner do?

It exposes 20 tools, read directly from the server on our last check. Among them: cancel_run, fill_code, fill_email_code, fill_login, get_authenticator_code, get_email_code and 14 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

What is runnerID by Torchrunner mostly used for?

Its tools cluster around fill, save and wait. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is runnerID by Torchrunner working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 318 ms. The bar chart above shows every period we have measured.

How do I connect runnerID by Torchrunner?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.

How do you sign in to runnerID by Torchrunner?

No API key is involved. runnerID by Torchrunner answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.

How fast is runnerID by Torchrunner?

It answers our handshake in 318 ms on average, which is faster than 45% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.