Zenserp for AI agents
Zenserp extracts Google and other search engine results in structured JSON, used by SEO and marketing teams tracking search rankings. 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 Zenserp.
Run a Google search query
Get structured search results for a keyword, a read-only search.
Check Google Trends data
Pull trend data for a search term over time.
Check API status before a batch run
Confirm the API is available before submitting a large batch of search queries.
12 Zenserp actions, graded by risk.
Every Zenserp action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- zenserp.get_statusGet API Status
- zenserp.list_batchesList Batches
- zenserp.list_countriesList Countries
- zenserp.list_languagesList Supported Languages
- zenserp.list_locationsList Locations
- zenserp.list_search_enginesList Search Engines
- zenserp.get_shopping_productGet Shopping Product Details
write
5Create and change things. Allow, or ask the user first.
- zenserp.bing_searchBing Search
- zenserp.google_searchZenserp Google Search
- zenserp.google_trendsGoogle Trends
- zenserp.yandex_searchYandex Search via Zenserp
- zenserp.google_reverse_image_searchGoogle Reverse Image Search
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Zenserp in three steps.
- 01Your users connect ZenserpThey add their Zenserp api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “bing Search” can wait for the user to approve.
- 03Any agent can actYour agent calls Zenserp through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('zenserp', { read: 'allow', write: 'ask', // bing_search destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Zenserp connects.
Users add their Zenserp 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 Zenserp 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 Zenserp from any agent.
More web data and scraping apps.
Zenserp and Arc0, answered.
Can I use Zenserp with Claude, ChatGPT or Cursor?
Yes. Connect Zenserp 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 Zenserp actions you allow.
How do users connect Zenserp?
Users add their Zenserp 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 Zenserp actions can my agent take?
12 in total: 7 read, 5 write and 0 destructive, such as “bing Search”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Zenserp?
Yes. Allow read actions and deny writes in the Zenserp policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Zenserp too?
Yes. The same Zenserp connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Zenserp into your agent.
Your users connect Zenserp once, under your brand. Your agent gets 12 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan