Peaka for AI agents
Peaka is a data integration and query platform for connecting sources, running queries, and managing catalogs across projects. Data teams use it to unify data without building custom pipelines. 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 Peaka.
Run a query against a data source
Execute a query across connected data resources to answer a specific analytics question.
Check available data resources
List data resources read-only to see what sources are already connected before adding more.
Delete a project with approval
Remove a project and its connections only after confirming they are no longer in use.
9 Peaka actions, graded by risk.
Every Peaka action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- peaka.list_hierarchyList Hierarchy
- peaka.list_data_resourcesList Data Resources
write
5Create and change things. Allow, or ask the user first.
- peaka.create_projectCreate Project
- peaka.update_projectUpdate Project
- peaka.create_workspaceCreate Workspace
- peaka.update_workspaceUpdate Workspace
- peaka.execute_queryExecute Query
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- peaka.delete_projectDelete Project
- peaka.delete_workspaceDelete Workspace
Peaka in three steps.
- 01Your users connect PeakaThey add their Peaka api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Project” can wait for the user, and “delete Project” can be denied outright.
- 03Any agent can actYour agent calls Peaka through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('peaka', { read: 'allow', write: 'ask', // create_project destructive: 'deny', // delete_project }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Peaka connects.
Users add their Peaka 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 Peaka 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 Peaka from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore databases and spreadsheets apps.
Peaka and Arc0, answered.
Can I use Peaka with Claude, ChatGPT or Cursor?
Yes. Connect Peaka 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 Peaka actions you allow.
How do users connect Peaka?
Users add their Peaka 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 Peaka actions can my agent take?
9 in total: 2 read, 5 write and 2 destructive, such as “create Project”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Peaka?
Yes. Actions like “delete Project” 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 Peaka too?
Yes. The same Peaka connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Peaka into your agent.
Your users connect Peaka once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan