Serpdog for AI agents
Serpdog provides an API for scraping Google Search, Maps, and Scholar results plus webpage screenshots, giving developers real-time SERP data. It operates independently after merging with Scrapingdog. 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 Serpdog.
Capture a webpage screenshot
Request a screenshot of a URL to archive how a page or search result looked at a point in time.
Pull Google search results
Fetch structured Google Search results for a keyword to track rankings or monitor competitors.
Check Google Maps or Scholar data
Retrieve Maps or Scholar results for a query before compiling a research or local-listing report.
1 Serpdog actions, graded by risk.
Every Serpdog action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
1Create and change things. Allow, or ask the user first.
- serpdog.screenshot_apiScreenshot API
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Serpdog in three steps.
- 01Your users connect SerpdogThey add their Serpdog api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “screenshot API” can wait for the user to approve.
- 03Any agent can actYour agent calls Serpdog through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('serpdog', { read: 'allow', write: 'ask', // screenshot_api destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Serpdog connects.
Users add their Serpdog 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 Serpdog 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 Serpdog from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore web data and scraping apps.
Serpdog and Arc0, answered.
Can I use Serpdog with Claude, ChatGPT or Cursor?
Yes. Connect Serpdog 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 Serpdog actions you allow.
How do users connect Serpdog?
Users add their Serpdog 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 Serpdog actions can my agent take?
1 in total: 0 read, 1 write and 0 destructive, such as “screenshot API”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Serpdog?
Yes. Allow read actions and deny writes in the Serpdog policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Serpdog too?
Yes. The same Serpdog connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Serpdog into your agent.
Your users connect Serpdog once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan