Botster for AI agents
Botster is a web scraping platform that businesses use to run configured bots against target sites and manage the resulting jobs and data. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Botster.
Check a job's run results
Read-only lookup of a bot run's structured results before deciding what to do with the data.
Launch a scraping bot
Launch a configured bot to run a new scraping job after the user confirms the target and cost.
Require approval before deleting a run
Flag deleting a job or run as destructive since it removes collected scraping results.
11 Botster actions, graded by risk.
Every Botster action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- botster.get_jobGet Job
- botster.list_botsList Bots
- botster.list_jobsList Jobs
- botster.get_creditsGet Credit Balance
- botster.get_run_resultsGet Run Results
- botster.calculate_bot_costCalculate Bot Cost
write
3Create and change things. Allow, or ask the user first.
- botster.launch_botLaunch Bot
- botster.restart_jobRestart Job
- botster.set_job_archivedSet Job Archived
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- botster.delete_jobDelete Job
- botster.delete_runDelete Run
Botster in three steps.
- 01Your users connect BotsterThey add their Botster api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “launch Bot” can wait for the user, and “delete Job” can be denied outright.
- 03Any agent can actYour agent calls Botster through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('botster', { read: 'allow', write: 'ask', // launch_bot destructive: 'deny', // delete_job }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Botster connects.
Users add their Botster api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Botster connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Botster from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore web data and scraping apps.
Botster and Arc0, answered.
Can I use Botster with Claude, ChatGPT or Cursor?
Yes. Connect Botster to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Botster actions you allow.
How do users connect Botster?
Users add their Botster api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Botster actions can my agent take?
11 in total: 6 read, 3 write and 2 destructive, such as “launch Bot”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Botster?
Yes. Actions like “delete Job” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Botster too?
Yes. The same Botster connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Botster into your agent.
Your users connect Botster once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan