Get started

beaconcha.in for AI agents

beaconcha.in is an explorer and analytics API for the Ethereum beacon chain, used by validators and developers to track validator performance, balances, and network health. 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.

Connect beaconcha.inSee the 37 actions ↓
AnalyticsAPI keyMCP + RESTbeaconcha.in
AUDIT LOG · BEACONCHA.INPOLICY: acme-support
09:41:07 · claude · u_8f2read
beaconcha_in.get_slot
Get Slot✓ allowed · 212ms
09:41:08 · claude · u_8f2read
beaconcha_in.get_chart
Get Chart✓ allowed · 164ms
09:41:09 · claude · u_8f2write
beaconcha_in.post_validators
Post Validators✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
beaconcha_in.get_execution_block
Get Execution Block✕ blocked · policy: deny
EVERY BEACONCHA.IN CALL, ON THE RECORD
01 · USE CASES

What agents do in beaconcha.in.

01

Check a validator's status

Get a validator's current state and balance history to confirm it's performing as expected.

02

Look up validator rewards

Get consensus and execution rewards for a validator to reconcile expected payouts for a staking operator.

03

Check network-wide performance

Get network performance and the validator queue as a read-only check before flagging a slowdown.

02 · ACTIONS

37 beaconcha.in actions, graded by risk.

Every beaconcha.in action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

35

Look things up. Allowed by default.

  • beaconcha_in.get_slot
    Get Slot
  • beaconcha_in.get_chart
    Get Chart
  • beaconcha_in.get_epoch
    Get Epoch
  • beaconcha_in.get_queues
    Get Validator Queues
  • beaconcha_in.get_validator
    Get Validator
  • beaconcha_in.get_node_health
    Get Explorer Health
  • beaconcha_in.get_latest_state
    Get Latest State
  • beaconcha_in.get_sync_committee
    Get Sync Committee
  • beaconcha_in.get_eth_store_daily
    Get ETH.Store Daily Aggregates
  • beaconcha_in.get_validators_queue
    Get Validators Queue
  • beaconcha_in.get_slot_attestations
    Get Slot Attestations
  • beaconcha_in.get_validator_deposits
    Get Validator Deposits
  • beaconcha_in.get_network_performance
    Get Network Performance
  • beaconcha_in.get_validator_proposals
    Get Validator Proposals
  • beaconcha_in.get_rocketpool_validator
    Get Rocket Pool Validator
  • beaconcha_in.get_slot_voluntary_exits
    Get Slot Voluntary Exits
+ 19 MORE

write

1

Create and change things. Allow, or ask the user first.

  • beaconcha_in.post_validators
    Post Validators

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • beaconcha_in.get_execution_block
    Get Execution Block
03 · HOW IT WORKS

beaconcha.in in three steps.

  1. 01Your users connect beaconcha.inThey add their beaconcha.in api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “post Validators” can wait for the user, and “get Execution Block” can be denied outright.
  3. 03Any agent can actYour agent calls beaconcha.in through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('beaconcha_in', {
  read: 'allow',
  write: 'ask',        // post_validators
  destructive: 'deny',  // get_execution_block
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How beaconcha.in connects.

Users add their beaconcha.in 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 beaconcha.in 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
05 · WORKS WITH

Use beaconcha.in from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More analytics apps.

Gong58 actionsSerpApi59 actionsPeople Data Labs27 actionsPostHog507 actions21risk8 actionsAkta19 actionsAlpha Vantage56 actionsAmplitude54 actions
ALL ANALYTICS APPS →
07 · FAQ

beaconcha.in and Arc0, answered.

Q01

Can I use beaconcha.in with Claude, ChatGPT or Cursor?

Yes. Connect beaconcha.in 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 beaconcha.in actions you allow.

Q02

How do users connect beaconcha.in?

Users add their beaconcha.in 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.

Q03

Which beaconcha.in actions can my agent take?

37 in total: 35 read, 1 write and 1 destructive, such as “post Validators”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in beaconcha.in?

Yes. Actions like “get Execution Block” 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.

Q05

Can my own backend call beaconcha.in too?

Yes. The same beaconcha.in connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug beaconcha.in into your agent.

Your users connect beaconcha.in once, under your brand. Your agent gets 37 actions behind your policies, with every call on the record.

Connect beaconcha.inBrowse all apps →

Free to build · MCP + REST · Audit log on every plan