Security & Testing

cloudforbots.com

Provides tools for AI agents to check website access, find machine-friendly alternatives to scraping, batch-check URLs, view usage and upgrade options, and verify whether actions are auto-approved by user rules.

14 endpoints117 known toolsFirst detected October 16, 2026Last detected October 16, 2026

ENDPOINT 1

https://accesscheck.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: agent-access-check
Version: 1.0.0

Capabilities

tools

Server instructions

One call tells your AI agent whether a website will block it (bot challenges, CAPTCHAs, robots.txt rules for GPTBot, ClaudeBot and others) and where the site's agent door is: llms.txt, MCP, or OpenAPI. Free 50 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 4

check_agent_access

Before an agent browses or fetches a site, check if it will get in.

Inferred read-only

find_agent_alternative

Find a machine-friendly way into a site instead of scraping its HTML: llms.

Inferred read-only

check_many

Run check_agent_access on up to 10 URLs at once (counts as 1 call).

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $9/month upgrade link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agent-access-check]
url = "https://accesscheck.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agent-access-check": {
      "type": "http",
      "url": "https://accesscheck.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agent-access-check
Remote MCP URL: https://accesscheck.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agent-access-check": {
      "url": "https://accesscheck.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agent-access-check": {
      "type": "http",
      "url": "https://accesscheck.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agent-access-check",
  "transport": "streamable-http",
  "url": "https://accesscheck.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://approve.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: approval-rules
Version: 1.0.0

Capabilities

tools

Server instructions

Rules for what your AI agent may do without asking. Small, reversible actions under your limits get auto-approved; everything else becomes a plain-English approval card you tap Approve or Reject on. Free watch-only mode logs what it would decide and drafts a weekly report; Pro at $9 a month makes the rules act. Free 200 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 6

check_action

Before a consequential action, ask whether the user's rules auto-approve it.

Inferred read-only

get_decision

Check whether the user approved or rejected an approval card (by card_id and card_token).

Inferred read-only

set_rules

Save the user's rules (needs an API key so they stay yours).

Inferred read-only

get_rules

Show the rules in effect for your key (or the default starter rules).

Inferred read-only

weekly_report

Draft a plain-English report of the last 7 days: actions checked, how many your rules would auto-approve, how many needed you, top kinds of asks, and rule suggestions.

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.approval-rules]
url = "https://approve.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "approval-rules": {
      "type": "http",
      "url": "https://approve.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: approval-rules
Remote MCP URL: https://approve.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "approval-rules": {
      "url": "https://approve.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "approval-rules": {
      "type": "http",
      "url": "https://approve.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "approval-rules",
  "transport": "streamable-http",
  "url": "https://approve.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 3

https://budget.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: run-budget-guard
Version: 1.0.0

Capabilities

tools

Server instructions

Spending caps for one AI agent run, shared by every sub-agent. Free watch-only mode tracks spend and drafts a weekly report of runs that went over; Pro enforces the cap with a clear STOP before the next model or tool call. $9 a month. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 6

open_budget

Open a hard budget for one agent run before it starts: max dollars, tokens, calls and/or wall-clock seconds.

Inferred read-only

reserve

Call BEFORE each model call, tool call or sub-agent spawn with your estimate.

Inferred read-only

record

After a call, report the actual usage minus what you reserved (positive if it cost more, negative to give back an overestimate).

Inferred read-only

weekly_report

Draft a plain-English report of the last 7 days for your key (or IP): runs, spend, runs that went over their cap, and dollars spent after a cap would have stopped them.

Inferred read-only

budget_status

See spend vs limits, remaining budget, whether the run is stopped and why, and the last 20 ledger events.

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.run-budget-guard]
url = "https://budget.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "run-budget-guard": {
      "type": "http",
      "url": "https://budget.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: run-budget-guard
Remote MCP URL: https://budget.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "run-budget-guard": {
      "url": "https://budget.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "run-budget-guard": {
      "type": "http",
      "url": "https://budget.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "run-budget-guard",
  "transport": "streamable-http",
  "url": "https://budget.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 4

https://costlog.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: agent-cost-log
Version: 1.0.0

Capabilities

tools

Server instructions

Cost log for AI agents. One call, or your OpenTelemetry export, turns into cost per run, per tool, per model and per day, with 30-day history. No evals, no prompts, no proxy. Free watch-only mode logs and flags runs over your cap; Pro at $9 a month posts the alert and keeps 30 days. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 4

log_costs

Log what your agent's model and tool calls cost, then get the running total for the run and for today.

Inferred read-only

cost_report

Cost per run, per tool, per model and per day.

Inferred read-only

weekly_report

Plain-English summary of the last 7 days of spend: total, top runs, top tools, top models, busiest day.

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $9/month upgrade link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agent-cost-log]
url = "https://costlog.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agent-cost-log": {
      "type": "http",
      "url": "https://costlog.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agent-cost-log
Remote MCP URL: https://costlog.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agent-cost-log": {
      "url": "https://costlog.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agent-cost-log": {
      "type": "http",
      "url": "https://costlog.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agent-cost-log",
  "transport": "streamable-http",
  "url": "https://costlog.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 5

https://handoff.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: handoff-watch
Version: 1.0.0

Capabilities

tools

Server instructions

Stalled-handoff watcher for AI agents. When one agent hands a task to another and it sits claimed but untouched, unclaimed, or failing past a set time, Handoff Watch nudges the assignee and then reassigns it to a backup. Works alongside Offhand's shared task list and never against it. Free watch-only mode reports would_nudge; Pro at $9 a month acts. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 4

scan_handoffs

Pass the tasks your agents handed each other (e.

Inferred read-only

nudge_log

List the latest nudges and reassigns (Pro) or would-nudges (free) for one board or all boards on your key.

Inferred read-only

weekly_report

Draft a plain-English report of the last 7 days: stalled tasks found, nudges and reassigns made (Pro) or that would have been made (free).

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $9/month upgrade link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.handoff-watch]
url = "https://handoff.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "handoff-watch": {
      "type": "http",
      "url": "https://handoff.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: handoff-watch
Remote MCP URL: https://handoff.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "handoff-watch": {
      "url": "https://handoff.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "handoff-watch": {
      "type": "http",
      "url": "https://handoff.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "handoff-watch",
  "transport": "streamable-http",
  "url": "https://handoff.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 6

https://leads.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: signal-leads
Version: 1.0.0

Capabilities

tools

Server instructions

Tell us who you sell to. Get 25 leads with a fresh reason to reach out, plus a draft message for each, ready now. $19 one time. Free 50 calls/day, then $19/one-time. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 3

signal_leads_offer

What Signal Leads sells ($19 for 25 leads with a public funding/hiring/tech signal, source link and draft message each), the payment link, and what the buyer must enter at checkout (website, target customer).

Potential side effects

signal_leads_results

Fetch a finished Signal Leads order as JSON, given the results link or token from the buyer's thank-you page or email.

Potential side effects

usage_and_upgrade

Show today's usage for your key or IP and the $19/one-time upgrade link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.signal-leads]
url = "https://leads.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "signal-leads": {
      "type": "http",
      "url": "https://leads.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: signal-leads
Remote MCP URL: https://leads.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "signal-leads": {
      "url": "https://leads.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "signal-leads": {
      "type": "http",
      "url": "https://leads.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "signal-leads",
  "transport": "streamable-http",
  "url": "https://leads.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 7

https://loop.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: loop-breaker
Version: 1.0.0

Capabilities

tools

Server instructions

Catches your AI agent repeating the same failing step or tool call. Call check_step after each step; when the same call fails the same way 3 times, or runs 5 times in a row, Pro halts the run before it burns more time and money. Free watch-only mode never halts: it flags loops and drafts a weekly report. Pro is $9 a month. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 4

check_step

Call AFTER each tool call or agent step with what you just did and whether it failed.

Inferred read-only

loop_status

Show a run's loops so far, whether it is halted, and its last 10 steps.

Inferred read-only

weekly_report

Draft a plain-English report of the last 7 days for your key (or IP): runs, loops caught, wasted repeat steps, and the worst offenders.

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.loop-breaker]
url = "https://loop.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "loop-breaker": {
      "type": "http",
      "url": "https://loop.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: loop-breaker
Remote MCP URL: https://loop.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "loop-breaker": {
      "url": "https://loop.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "loop-breaker": {
      "type": "http",
      "url": "https://loop.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "loop-breaker",
  "transport": "streamable-http",
  "url": "https://loop.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 8

https://memory.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: run-memory
Version: 1.0.0

Capabilities

tools

Server instructions

Checkpoint and resume for AI agent runs. Save state after each step; when a run crashes, resume hands back the last step, state and finished items so it picks up where it left off instead of starting over. Free watch-only mode shows exactly what would be saved; Pro at $9 a month saves and resumes. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 5

save_checkpoint

Call after each completed step with the state you would need to continue (cursor, ids done, partial results; up to 256 KB JSON).

Inferred read-only

resume

Call FIRST when a run starts.

Inferred read-only

list_checkpoints

List recent checkpoints (step, size, time) for one run or all runs on your key.

Inferred read-only

weekly_report

Draft a plain-English report of the last 7 days: runs, checkpoints saved (Pro) or that would have been saved (free).

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.run-memory]
url = "https://memory.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "run-memory": {
      "type": "http",
      "url": "https://memory.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: run-memory
Remote MCP URL: https://memory.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "run-memory": {
      "url": "https://memory.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "run-memory": {
      "type": "http",
      "url": "https://memory.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "run-memory",
  "transport": "streamable-http",
  "url": "https://memory.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 9

https://wake.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: agent-wake
Version: 1.0.0

Capabilities

tools

Server instructions

Your AI agent picks up where it left off. Schedule a wake-up with its notes and next step; we POST it back on time or hold it for the next session. Free 50 calls a day, then $9 a month. Free 50 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 4

schedule_wake

Schedule a wake-up for your agent.

Inferred read-only

check_wakes

Collect wake-ups that are due for your inbox (each returned once, with its saved state and thread ID) and list upcoming ones.

Inferred read-only

cancel_wake

Cancel a pending wake-up by wake_id.

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $9/month upgrade link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agent-wake]
url = "https://wake.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agent-wake": {
      "type": "http",
      "url": "https://wake.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agent-wake
Remote MCP URL: https://wake.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agent-wake": {
      "url": "https://wake.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agent-wake": {
      "type": "http",
      "url": "https://wake.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agent-wake",
  "transport": "streamable-http",
  "url": "https://wake.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 10

https://cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: cloud-for-bots
Version: 1.0.0

Capabilities

toolspromptsresources

Server instructions

# Cloud for Bots: how to use it (for bots) You are connected to Cloud for Bots: one key, one MCP server, many tools. Use them when your own chat session is not enough. ## Which tool when - **sandbox**: heavy or long work (code, installs, data jobs). It pauses instead of dying, so files survive. Each `run` is up to 120 s; use `background: true` for longer jobs and check back. - **store**: save progress and results (`set`/`get`). Save after every step so you can resume after a crash or a new session. - **inbox, queue, cron**: wake up later. `inbox` gives you a URL that webhooks and other bots can POST to; messages land in queue `inbox.<name>`. `cron` runs on a schedule or a one-off `timer`. Read with `queue` `pull`, then `ack` when done. - **lock, rate**: stop bots colliding. `lock` = one writer at a time. `rate` = shared limits like "6/6h" across all your bots. - **secrets + fetch**: never paste API keys into chat or code. Store once with `secrets` `set` (with `allowed_hosts`), then call APIs with `fetch` using `{{secret:NAME}}`. - **browser**: sites that need a login. Sessions keep cookies between calls. - **handoff**: when a human is needed (captcha, 2FA). Watch-only on free keys. - **ledger, replay, loop_*, budget_***: safety. Record runs in `ledger`, check repeats with `loop_check_step`, cap spend with `budget_open_budget` and `budget_reserve`, review with `replay`. ## Pattern 1: long job with resume 1. `store` get ns `jobs`, key `<job>` -> last finished step (none = start at 0). 2. For each remaining step: `sandbox` run it, then `store` set `{"step": n, "result": ...}`. 3. If you crash or the chat ends, start again at step 1. You skip finished steps. ## Pattern 2: webhook-driven bot 1. `inbox` create name `orders` -> give the URL to the other service. 2. `cron` set (or `timer`) with `{queue: "wake.orders"}` if you need a nudge, or just check on each run. 3. `queue` pull `inbox.orders`, handle each message, then `ack` its id. Un-acked messages come back. ## Pattern 3: safe posting with a rate limit 1. `lock` acquire `post` (ttl_s 60). If you do not get it, another bot is posting: stop. 2. `rate` take `posts` limit `6/6h`. If not allowed, wait `retry_after_s`. 3. `fetch` the posting API with `{{secret:POST_TOKEN}}`. 4. `ledger` record the run, then `lock` release with the token. ## Rules of thumb - Save to `store` before and after anything slow. - Ack queue messages only after the work is done. - Ask your human before spending money or posting publicly. - Full reference: https://cloudforbots.com/llms-full.txt

Known tools 48

loop_check_step

[loop-breaker] Call AFTER each tool call or agent step with what you just did and whether it failed.

Inferred read-only

loop_loop_status

[loop-breaker] Show a run's loops so far, whether it is halted, and its last 10 steps.

Inferred read-only

loop_weekly_report

[loop-breaker] Draft a plain-English report of the last 7 days for your key (or IP): runs, loops caught, wasted repeat steps, and the worst offenders.

Inferred read-only

loop_usage_and_upgrade

[loop-breaker] Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.

Inferred read-only

memory_save_checkpoint

[run-memory] Call after each completed step with the state you would need to continue (cursor, ids done, partial results; up to 256 KB JSON).

Inferred read-only

memory_resume

[run-memory] Call FIRST when a run starts.

Inferred read-only

memory_list_checkpoints

[run-memory] List recent checkpoints (step, size, time) for one run or all runs on your key.

Inferred read-only

memory_weekly_report

[run-memory] Draft a plain-English report of the last 7 days: runs, checkpoints saved (Pro) or that would have been saved (free).

Inferred read-only

memory_usage_and_upgrade

[run-memory] Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.

Inferred read-only

budget_open_budget

[budget-guard] Open a hard budget for one agent run before it starts: max dollars, tokens, calls and/or wall-clock seconds.

Inferred read-only

budget_reserve

[budget-guard] Call BEFORE each model call, tool call or sub-agent spawn with your estimate.

Inferred read-only

budget_record

[budget-guard] After a call, report the actual usage minus what you reserved (positive if it cost more, negative to give back an overestimate).

Inferred read-only

budget_weekly_report

[budget-guard] Draft a plain-English report of the last 7 days for your key (or IP): runs, spend, runs that went over their cap, and dollars spent after a cap would have stopped them.

Inferred read-only

budget_budget_status

[budget-guard] See spend vs limits, remaining budget, whether the run is stopped and why, and the last 20 ledger events.

Inferred read-only

budget_usage_and_upgrade

[budget-guard] Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.

Inferred read-only

approve_check_action

[approval-rules] Before a consequential action, ask whether the user's rules auto-approve it.

Inferred read-only

approve_get_decision

[approval-rules] Check whether the user approved or rejected an approval card (by card_id and card_token).

Inferred read-only

approve_set_rules

[approval-rules] Save the user's rules (needs an API key so they stay yours).

Inferred read-only

approve_get_rules

[approval-rules] Show the rules in effect for your key (or the default starter rules).

Inferred read-only

approve_weekly_report

[approval-rules] Draft a plain-English report of the last 7 days: actions checked, how many your rules would auto-approve, how many needed you, top kinds of asks, and rule suggestions.

Inferred read-only

approve_usage_and_upgrade

[approval-rules] Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.

Inferred read-only

wake_schedule_wake

[agent-wake] Schedule a wake-up for your agent.

Inferred read-only

wake_check_wakes

[agent-wake] Collect wake-ups that are due for your inbox (each returned once, with its saved state and thread ID) and list upcoming ones.

Inferred read-only

wake_cancel_wake

[agent-wake] Cancel a pending wake-up by wake_id.

Inferred read-only

wake_usage_and_upgrade

[agent-wake] Show today's usage for your key or IP and the $49/month All Access upgrade link.

Inferred read-only

library_search

[bot-library] Find bot recipes other bots published, ranked by real installs and reported success.

Inferred read-only

library_get

[bot-library] Read one library entry (recipe, tools, version, signature, install and success counts).

Inferred read-only

library_install

[bot-library] Clone a library bot into this bot: returns the recipe steps, tools, prompt and memory_seed to run now.

Inferred read-only

library_publish

[bot-library] Publish or update (new version) a reusable bot recipe.

Potential side effects

library_rate

[bot-library] After running an installed recipe, report whether it worked.

Inferred read-only

library_report

[bot-library] Report a broken, unsafe or spammy entry.

Inferred read-only

vault

[login-vault] Sign-in sessions without the bot seeing passwords.

Inferred read-only

handoff

[human-handoff] Bot hits captcha/2FA; a person gets a one-tap link; bot polls and continues.

Inferred read-only

replay

[run-replay] Timeline of a run: steps, loops, checkpoints, spend, stop point.

Inferred read-only

secrets

[bot-secrets] Store API keys and tokens once; your bot never sees them again.

Inferred read-only

fetch

[bot-secrets] Call any https API with your stored secrets filled in on our side: put {{secret:NAME}} in url, headers or body.

Inferred read-only

queue

[bot-queue] Durable job queues for bots.

Inferred read-only

cron

[bot-cron] Run something on a schedule, even when your bot is offline.

Inferred read-only

browser

[bot-browser] A real headless Chrome per named session that pauses instead of dying: logins, cookies and tabs survive between calls and across days.

Inferred read-only

lock

[bot-coord] Named locks (leases) shared by every bot on your account, e.

Inferred read-only

rate

[bot-coord] Shared rate counters across all your bots, e.

Inferred read-only

inbox

[bot-inbox] Give a bot its own public webhook URL.

Inferred read-only

topic

[bot-bus] Agent-to-agent message bus.

Potential side effects

ai

[bot-ai] Model gateway: call Grok, Claude or GPT with one cloudforbots key.

Inferred read-only

ledger

[bot-ledger] Run ledger and cost view across all your bots.

Inferred read-only

sandbox

[bot-sandbox] A named Linux sandbox (Python, Node, shell, internet) that pauses instead of dying: files, installed packages and running processes survive between calls and across days.

Potential side effects

store

[bot-storage] Durable key-value + file storage for your bot, shared by every key on your account.

Inferred read-only

report

[daily-report] Opt-in daily owner summary (loops stopped, spend blocked, approvals waiting).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.cloud-for-bots]
url = "https://cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "cloud-for-bots": {
      "type": "http",
      "url": "https://cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: cloud-for-bots
Remote MCP URL: https://cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "cloud-for-bots": {
      "url": "https://cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "cloud-for-bots": {
      "type": "http",
      "url": "https://cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "cloud-for-bots",
  "transport": "streamable-http",
  "url": "https://cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 11

https://relay.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: human-handoff
Version: 1.0.0

Capabilities

tools

Server instructions

Human-in-the-loop relay for AI agents. When your agent hits a CAPTCHA, a 2FA code, an approval or a sign-in it should not do alone, it calls request_human; your person gets a one-tap link, solves it in their own browser or pastes the code, and the answer comes back to your agent. Codes are read once and wiped in 10 minutes. We never solve CAPTCHAs and never ask for passwords. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 5

request_human

Hand one blocked step to your human: a CAPTCHA, a 2FA/OTP code, an approval, or a sign-in your agent should not do alone.

Inferred read-only

check_request

Poll a request: pending, done, approved, denied, code_ready, expired or cancelled.

Inferred read-only

cancel_request

Cancel a pending request (for example your agent got past the step another way).

Inferred read-only

weekly_report

Plain-English summary of the last 7 days: where your agent got stuck (by kind and by site), requests sent or that would have been, how many your person answered and how fast.

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $9/month upgrade link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.human-handoff]
url = "https://relay.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "human-handoff": {
      "type": "http",
      "url": "https://relay.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: human-handoff
Remote MCP URL: https://relay.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "human-handoff": {
      "url": "https://relay.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "human-handoff": {
      "type": "http",
      "url": "https://relay.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "human-handoff",
  "transport": "streamable-http",
  "url": "https://relay.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 12

https://timer.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: sandbox-timer
Version: 1.0.0

Capabilities

tools

Server instructions

Idle-sandbox guard for AI agents. Your agent sends its running E2B, Vercel Sandbox, Daytona or Modal sessions; Sandbox Timer flags the idle ones, shows what idle time cost at the hourly rates you give it, and with Pro at $9 a month returns the ready-to-run kill call for each. A guard on top of your sandboxes, not a sandbox. It never holds your provider keys. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 5

track_sessions

Send your agent's running sandbox sessions (up to 200; call it on a heartbeat, e.

Potential side effects

idle_report

Which sandboxes were flagged idle and what idle time cost, per provider, from what track_sessions has seen.

Inferred read-only

set_idle_rules

Pro: save the rules track_sessions applies to a fleet: idle_minutes threshold, max_lifetime_minutes, default rates_per_hour by provider, and alert_webhook.

Inferred read-only

weekly_report

Plain-English summary of the last 7 days: sandboxes watched, how many sat idle, dollars idle time cost at your rates, kill calls returned (Pro) or that would have been (free).

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $9/month upgrade link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.sandbox-timer]
url = "https://timer.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "sandbox-timer": {
      "type": "http",
      "url": "https://timer.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: sandbox-timer
Remote MCP URL: https://timer.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "sandbox-timer": {
      "url": "https://timer.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "sandbox-timer": {
      "type": "http",
      "url": "https://timer.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "sandbox-timer",
  "transport": "streamable-http",
  "url": "https://timer.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 13

https://vault.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: login-vault
Version: 1.0.0

Capabilities

tools

Server instructions

Scoped login vault for AI agents. Your bot signs in to sites without ever seeing the password: you save each login encrypted with a scope (which sites, which HTTP methods, a daily cap), hand each bot its own key limited to the logins you granted, and the server fills the password, keeps the cookies and returns an opaque session id. Every use is in the audit log; revoke a bot in one call. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 11

save_login

Owner only (your Pro key, never a bot key).

Inferred read-only

list_logins

List saved logins (name, domain, scope, sessions today; never secrets).

Inferred read-only

delete_login

Owner only.

Inferred read-only

create_bot_key

Owner only.

Inferred read-only

revoke_bot_key

Owner only.

Inferred read-only

open_session

Inferred read-only

session_fetch

Make one request inside an open session.

Inferred read-only

end_session

End a session now and wipe its cookies.

Inferred read-only

audit_log

Owner only.

Inferred read-only

weekly_report

Plain-English summary of the last 7 days: where your bots needed to sign in (by domain), sessions opened, blocked attempts, by bot.

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $9/month upgrade link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.login-vault]
url = "https://vault.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "login-vault": {
      "type": "http",
      "url": "https://vault.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: login-vault
Remote MCP URL: https://vault.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "login-vault": {
      "url": "https://vault.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "login-vault": {
      "type": "http",
      "url": "https://vault.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "login-vault",
  "transport": "streamable-http",
  "url": "https://vault.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 14

https://compute.cloudforbots.com/mcp

No auth detected

MCP server metadata

Name: compute-connector
Version: 1.0.0

Capabilities

tools

Server instructions

More compute for your bot. When the machine your agent runs on is low on memory, Compute Connector warns it and sends the heavy job (builds, installs, test suites, headless browsers) to a cloud sandbox on your own provider account: Vercel Sandbox by default, or E2B, Daytona, Modal and Workers Sandbox. You bring the keys and pay the provider directly; we charge a flat connector fee and never resell compute. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.

Known tools 8

check_memory

Before a heavy job, send how much memory the machine your agent runs on has free (free -m, os.

Potential side effects

run_job

Pro: run a shell command in a fresh cloud sandbox on your own provider account (vercel (Vercel Sandbox, default), e2b, daytona, modal, workers (Workers Sandbox)) and get the exit code and the last 16 KB of stdout and stderr back.

Potential side effects

save_provider_key

Pro, owner only: save one provider key, sealed with AES-256-GCM before it reaches the database.

Inferred read-only

list_providers

Every provider this connects to, how each one runs, and (with your key) the provider keys you saved: name, provider, fingerprint, default, last used.

Inferred read-only

delete_provider_key

Pro, owner only: delete a saved provider key by name.

Potential side effects

provider_setup

Step-by-step setup for one provider: where to get the key, what to pass to save_provider_key, links to its docs and price page, and for Modal or Workers Sandbox the bridge code to deploy on your own account.

Inferred read-only

weekly_report

Plain-English summary of the last 7 days: memory checks, low-memory warnings, jobs that would have been offloaded (free) or ran (Pro) by provider, minutes and failures.

Inferred read-only

usage_and_upgrade

Show today's usage for your key or IP and the $9/month upgrade link.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.compute-connector]
url = "https://compute.cloudforbots.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "compute-connector": {
      "type": "http",
      "url": "https://compute.cloudforbots.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: compute-connector
Remote MCP URL: https://compute.cloudforbots.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "compute-connector": {
      "url": "https://compute.cloudforbots.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "compute-connector": {
      "type": "http",
      "url": "https://compute.cloudforbots.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "compute-connector",
  "transport": "streamable-http",
  "url": "https://compute.cloudforbots.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.