Astica AI for AI agents
astica ai offers cognitive AI APIs spanning computer vision, natural language processing, and voice synthesis, used by developers who need to analyze media or generate speech from text. 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 Astica AI.
Analyze an audio clip
Run audio analysis on a clip to extract information about its content.
Read text aloud with synthesized speech
Convert a block of text into spoken audio using the voice engine.
Review output before publishing
Check the analysis or generated audio result before it is used somewhere else.
2 Astica AI actions, graded by risk.
Every Astica AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- astica_ai.analyze_audioAnalyze Audio
write
1Create and change things. Allow, or ask the user first.
- astica_ai.astica_read_textASTICA_READ_TEXT
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Astica AI in three steps.
- 01Your users connect Astica AIThey add their Astica AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “aSTICA_READ_TEXT” can wait for the user to approve.
- 03Any agent can actYour agent calls Astica 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('astica_ai', { read: 'allow', write: 'ask', // astica_read_text destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Astica AI connects.
Users add their Astica 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 Astica 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 Astica AI from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Astica AI and Arc0, answered.
Can I use Astica AI with Claude, ChatGPT or Cursor?
Yes. Connect Astica 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 Astica AI actions you allow.
How do users connect Astica AI?
Users add their Astica 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 Astica AI actions can my agent take?
2 in total: 1 read, 1 write and 0 destructive, such as “aSTICA_READ_TEXT”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Astica AI?
Yes. Allow read actions and deny writes in the Astica AI policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Astica AI too?
Yes. The same Astica AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Astica AI into your agent.
Your users connect Astica AI once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan