Keen.io for AI agents
Keen.io is an embedded analytics API for collecting, analyzing, and visualizing custom event data, letting developers build product usage dashboards without standing up their own analytics pipeline. 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 Keen.io.
Inspect an event collection
Inspect a single event collection's properties to understand what data has been tracked.
Run a unique count query
Run a select-unique query to count distinct users triggering an event this month.
Revoke an access key with approval
Unrevoke or revoke an access key only after an admin confirms the change is intended.
6 Keen.io actions, graded by risk.
Every Keen.io 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.
- keen_io.list_cached_datasetsList Cached Dataset Definitions
write
5Create and change things. Allow, or ask the user first.
- keen_io.select_uniqueSelect Unique
- keen_io.unrevoke_access_keyUnrevoke Access Key
- keen_io.inspect_collection_propertyInspect Collection Property
- keen_io.inspect_all_event_collectionsInspect All Event Collections
- keen_io.inspect_single_event_collectionInspect Single Event Collection
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Keen.io in three steps.
- 01Your users connect Keen.ioThey add their Keen.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “select Unique” can wait for the user to approve.
- 03Any agent can actYour agent calls Keen.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('keen_io', { read: 'allow', write: 'ask', // select_unique destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Keen.io connects.
Users add their Keen.io 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 Keen.io 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 Keen.io from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Keen.io and Arc0, answered.
Can I use Keen.io with Claude, ChatGPT or Cursor?
Yes. Connect Keen.io 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 Keen.io actions you allow.
How do users connect Keen.io?
Users add their Keen.io 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 Keen.io actions can my agent take?
6 in total: 1 read, 5 write and 0 destructive, such as “select Unique”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Keen.io?
Yes. Allow read actions and deny writes in the Keen.io policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Keen.io too?
Yes. The same Keen.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Keen.io into your agent.
Your users connect Keen.io once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan