Lumify for AI agents
Lumify provides sports schedules, live scores, odds, and statistics through a credit-metered API for betting and sports data apps needing near real-time results. 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 Lumify.
Check a game's live score
Look up the current score and stats for an in-progress game, a read-only check.
Search for a team's schedule
Search team events to find upcoming games and recent results for a matchup, a read-only sports data lookup.
Check remaining credit usage
Look up credit usage before running a batch of event or player lookups.
10 Lumify actions, graded by risk.
Every Lumify action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
9Look things up. Allowed by default.
- lumify.get_eventsGet Events
- lumify.list_eventsList Events
- lumify.search_teamsSearch Teams
- lumify.search_playersSearch Players
- lumify.get_event_scoreGet Event Score
- lumify.get_credit_usageGet Credit Usage
- lumify.get_event_analysisGet Event Analysis
- lumify.list_player_eventsList Player Events
- lumify.list_sports_or_seasonsList Sports or Seasons
write
1Create and change things. Allow, or ask the user first.
- lumify.plan_credit_costsPlan Credit Costs
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Lumify in three steps.
- 01Your users connect LumifyThey add their Lumify api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “plan Credit Costs” can wait for the user to approve.
- 03Any agent can actYour agent calls Lumify through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('lumify', { read: 'allow', write: 'ask', // plan_credit_costs destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Lumify connects.
Users add their Lumify 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 Lumify 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 Lumify from any agent.
Lumify and Arc0, answered.
Can I use Lumify with Claude, ChatGPT or Cursor?
Yes. Connect Lumify 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 Lumify actions you allow.
How do users connect Lumify?
Users add their Lumify 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 Lumify actions can my agent take?
10 in total: 9 read, 1 write and 0 destructive, such as “plan Credit Costs”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Lumify?
Yes. Allow read actions and deny writes in the Lumify policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Lumify too?
Yes. The same Lumify connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Lumify into your agent.
Your users connect Lumify once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan