Agentsim MCP Server

by agentsim Your server? Claim it

answering

Agentsim is answering right now. Last checked 11 min ago. It exposes 7 tools. Last commit 29 Sep 2026.

Control plane for agent auth walls. Connector 0 handles SMS OTP with US test numbers.

Uptime history 91 days of history · worst day 95%

91 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

422 ms

Response time

average over 24h

Stars

last commit 29 Sep 2026

What changed 9

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 27 August 2026. No other catalogue keeps this.

27 Aug 5 tool descriptions were rewritten get_messages, list_numbers, provision_number and 2 more

27 Aug 2 tools appeared open_challenge, wait_for_verdict

27 Aug 2 tools changed the parameters they ask for get_messages, release_number

What the code does

We read the source, 4 d ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command npm/bin/agentsim-mcp.js:9

    execFileSync(cmd, ['--version'], { stdio: 'ignore' });

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp --transport http https://mcp.agentsim.dev/mcp

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

https://mcp.agentsim.dev/mcp

~/.codex/config.toml

[mcp_servers.mcp]
url = "https://mcp.agentsim.dev/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.agentsim.dev/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.agentsim.dev/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.

Available tools 7

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

wait

wait_for_otp

Block until an SMS verdict arrives for this session (alias for wait_for_verdict). DEPRECATED: Use `wait_for_verdict` instead. This tool is kept for backward compatibility with existing MCP clients. Polls the AgentSIM API for up to `timeout_seconds`. Returns the OTP code when the SMS challenge resolves. If the verdict does not arrive in time, raises a ToolError with advice on retrying. Always call `release_number` after you have used the verdict.

wait_for_verdict

Block until a challenge verdict arrives for this session. Polls the AgentSIM API for up to `timeout_seconds`. Returns the structured verdict, which may include: - otp_code: the parsed OTP (for sms_otp, email_otp channels) - magic_link: the extracted HTTPS URL (for magic_link channel) - webauthn_required: true if WebAuthn/passkey was detected (detect-and-halt) - policy_denied: true if the service_url is blocked by account policy Always call `release_number` after processing the verdict.

messages

get_messages

List all SMS messages received in this session without consuming the OTP. Use this to inspect raw messages or check if an SMS arrived before calling wait_for_verdict. Does NOT mark the OTP as consumed.

numbers

list_numbers

List active challenge sessions, optionally filtered by agent_id. Use this to check for leaked sessions or inspect what is currently active.

open

open_challenge

Open an authentication challenge session. Supports multiple channels: sms_otp (programmable US number), email_otp (mock inbox), magic_link (mock inbox), and webauthn_required (detect-and-halt). Returns the challenge identifier (phone number or email address) and a session_id needed for all subsequent calls. The session is reserved for ttl_seconds. Next step: use the returned identifier on your target service to trigger the challenge, then call `wait_for_verdict` with the returned `session_id`.

provision

provision_number

Open an SMS challenge session (alias for open_challenge with channel=sms_otp). DEPRECATED: Use `open_challenge` with channel="sms_otp" instead. This tool is kept for backward compatibility with existing MCP clients. Returns the phone number (e164 format) and a session_id needed for all subsequent calls. The session is reserved for ttl_seconds. Next step: use the returned `number` on an app you own to trigger the wall, then call `wait_for_verdict` (or the `wait_for_otp` alias) with the `session_id`.

release

release_number

Close a challenge session. Always call this when you are done — even on error — so the session does not keep consuming pool capacity.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.agentsim.dev/mcp	streamable-http	needs auth	423 ms	11 min ago

Alternatives to Agentsim

same job, measured the same way

Canary

by mindstone

Mindstone-internal release-pipeline test connector; not for use. Single ping tool; no auth.

57 installs/wk local only

Browserbase

by mcparmory

Create and control browser sessions for web automation, testing, and AI agent tasks

230 installs/wk local only

Flagpost

by sathergate

Feature flags for Next.js. One file, full control with A/B testing.

47 installs/wk local only

FiveM MCP

by ziyacivan

Build, run and live-test FiveM servers with AI agents: RCON, DevCon, window control, mcpb bridge.

129 installs/wk local only

Agent Tested

by agenttested

Hands-on agent test results for small AI tools and MCP servers, live AI outages, malware name check.

14 tools answering

MCP Failure Lab

by cloudlabworks

Deliberately faulty MCP server for testing how agent clients handle tool errors and disconnects.

local only

Aether testnet wallet

by whoyoujoshin

Testnet wallet for AI agents on Aether: pay, get paid and buy from paid APIs, with spending caps.

7 tools answering

Agent Arcade

by chatgpt-cursoraikk-agent-arcade-ai

Create, test and play AI-native games through server-authoritative contracts.

49 tools answering

Agentsim — questions

Answers built from our own checks of this server.

What can Agentsim do?

It exposes 7 tools, read directly from the server on our last check. Among them: get_messages, list_numbers, open_challenge, provision_number, release_number, wait_for_otp and 1 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 →

Is Agentsim 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 422 ms. The bar chart above shows every period we have measured.

How do I connect Agentsim?

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 will need your own credentials: it refuses anonymous clients.

Does Agentsim need an API key?

Yes. Every time we knock, Agentsim answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.

How fast is Agentsim?

It answers our handshake in 422 ms on average, which is faster than 30% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Agentsim open source?

The code is open source: it is published under the MIT licence, written in Python and 1 stars on GitHub. The licence covers the code in the repository, not the hosted service at mcp.agentsim.dev, which runs on its operator's own terms.