APIpie AI for AI agents
APIpie.ai is a unified API for accessing many AI models from different providers, plus tools for document parsing, transcription, and vector search, aimed at cost-optimizing AI workloads. 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 APIpie AI.
Transcribe an audio file to text
Convert an uploaded audio file into a text transcript using a chosen model.
Anonymize sensitive text before processing
Strip personally identifiable details out of a block of text before it is used elsewhere.
Confirm before deleting vectors
Removing vectors from a collection is destructive and should be confirmed before it runs.
13 APIpie AI actions, graded by risk.
Every APIpie AI 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.
- apipie_ai.get_stateGet state
- apipie_ai.list_modelsList AI Models
- apipie_ai.get_query_historyGet query history
- apipie_ai.get_detailed_modelsGet Detailed Models
- apipie_ai.list_vector_collectionsList Vector Collections
- apipie_ai.parse_documentParse Document
write
5Create and change things. Allow, or ask the user first.
- apipie_ai.update_stateUpdate State Settings
- apipie_ai.create_vector_collectionCreate Vector Collection
- apipie_ai.upload_fileUpload File
- apipie_ai.anonymize_textAnonymize Sensitive Text
- apipie_ai.transcribe_audioTranscribe audio to text
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- apipie_ai.delete_stateDelete state
- apipie_ai.delete_vectorsDelete Vectors
APIpie AI in three steps.
- 01Your users connect APIpie AIThey add their APIpie AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Vector Collection” can wait for the user, and “delete state” can be denied outright.
- 03Any agent can actYour agent calls APIpie AI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('apipie_ai', { read: 'allow', write: 'ask', // create_vector_collection destructive: 'deny', // delete_state }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How APIpie AI connects.
Users add their APIpie AI 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 APIpie AI 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 APIpie AI from any agent.
APIpie AI and Arc0, answered.
Can I use APIpie AI with Claude, ChatGPT or Cursor?
Yes. Connect APIpie AI 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 APIpie AI actions you allow.
How do users connect APIpie AI?
Users add their APIpie AI 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 APIpie AI actions can my agent take?
13 in total: 6 read, 5 write and 2 destructive, such as “create Vector Collection”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in APIpie AI?
Yes. Actions like “delete state” 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 APIpie AI too?
Yes. The same APIpie AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug APIpie AI into your agent.
Your users connect APIpie AI once, under your brand. Your agent gets 13 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan