Apiverve for AI agents
APIVerve offers a broad set of small utility APIs, from currency conversion to airport lookups, meant to give developers quick, ready-made data endpoints instead of building each one themselves. 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 Apiverve.
Convert currency for a quote
Convert an amount from one currency to another to prepare a customer quote.
Look up airport or airline information
Get airport details by code or airline information by name for a travel itinerary.
Check current air quality for a city
Pull an air quality reading for a location before advising on travel plans.
11 Apiverve actions, graded by risk.
Every Apiverve 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
11Create and change things. Allow, or ask the user first.
- apiverve.dictionaryGet Word Definition
- apiverve.air_qualityAir Quality
- apiverve.age_calculatorAge Calculator
- apiverve.antonym_finderFind antonyms for a word
- apiverve.weather_by_cityWeather by City
- apiverve.advice_generatorAdvice Generator
- apiverve.app_store_scraperApp Store Scraper
- apiverve.currency_converterCurrency Converter
- apiverve.airline_lookup_nameGet Airline Info by Name
- apiverve.airports_lookup_icaoGet Airport Info by ICAO Code
- apiverve.airport_distance_iataGet airport distance by IATA
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Apiverve in three steps.
- 01Your users connect ApiverveThey add their Apiverve api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “get Word Definition” can wait for the user to approve.
- 03Any agent can actYour agent calls Apiverve through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('apiverve', { read: 'allow', write: 'ask', // dictionary destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Apiverve connects.
Users add their Apiverve 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 Apiverve 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 Apiverve from any agent.
Apiverve and Arc0, answered.
Can I use Apiverve with Claude, ChatGPT or Cursor?
Yes. Connect Apiverve 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 Apiverve actions you allow.
How do users connect Apiverve?
Users add their Apiverve 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 Apiverve actions can my agent take?
11 in total: 0 read, 11 write and 0 destructive, such as “get Word Definition”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Apiverve?
Yes. Allow read actions and deny writes in the Apiverve policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Apiverve too?
Yes. The same Apiverve connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Apiverve into your agent.
Your users connect Apiverve 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