Piloterr for AI agents
Piloterr offers more than fifty ready-to-use APIs for web scraping and data extraction from retailers, search engines, and directories. Businesses use it to pull structured data without building scrapers. 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 Piloterr.
Look up a product's details
Pull product information from a retailer listing to compare pricing or availability.
Run a Google search query
Retrieve structured Google search results for a keyword or research query.
Check API usage read-only
Review usage statistics before running a large batch of extraction requests.
12 Piloterr actions, graded by risk.
Every Piloterr action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
9Look things up. Allowed by default.
- piloterr.get_product_infoPiloterr Get Product Info
- piloterr.list_chewy_productsList Chewy Products
- piloterr.list_eleclerc_storesList E.Leclerc Stores
- piloterr.list_google_countriesList Google Countries
- piloterr.list_google_languagesList Google Languages
- piloterr.list_google_locationsList Google Locations
- piloterr.list_linked_in_industriesList LinkedIn Industries
- piloterr.list_leroy_merlin_productsList Leroy Merlin Products
- piloterr.searchPiloterr Google Search
write
3Create and change things. Allow, or ask the user first.
- piloterr.usage_getGet Usage
- piloterr.auchan_searchAuchan Product Search
- piloterr.auchan_productAuchan Product
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Piloterr in three steps.
- 01Your users connect PiloterrThey add their Piloterr api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “get Usage” can wait for the user to approve.
- 03Any agent can actYour agent calls Piloterr through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('piloterr', { read: 'allow', write: 'ask', // usage_get destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Piloterr connects.
Users add their Piloterr 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 Piloterr 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 Piloterr from any agent.
More web data and scraping apps.
Piloterr and Arc0, answered.
Can I use Piloterr with Claude, ChatGPT or Cursor?
Yes. Connect Piloterr 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 Piloterr actions you allow.
How do users connect Piloterr?
Users add their Piloterr 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 Piloterr actions can my agent take?
12 in total: 9 read, 3 write and 0 destructive, such as “get Usage”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Piloterr?
Yes. Allow read actions and deny writes in the Piloterr policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Piloterr too?
Yes. The same Piloterr connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Piloterr into your agent.
Your users connect Piloterr 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