Overview
Explorer tools allow your AI agents to query Allium’s historical blockchain data using SQL queries. These tools provide access to raw and decoded data across 80+ blockchains.
| Tool Name | Description |
|---|
explorer_create_query | Create a new saved query programmatically. Returns a query_id for future use |
explorer_update_query | Update an existing saved query’s SQL, parameters, or configuration |
explorer_run_query | Run a saved Explorer query using its query_id. Supports parameterization |
explorer_run_sql | Run raw SQL directly against Allium’s production datasets |
explorer_search_schemas | Semantic search across all schema docs. Returns relevant table IDs |
explorer_browse_schemas | Browse data schema hierarchy like a filesystem to discover databases, schemas, tables |
explorer_fetch_schema | Fetch YAML schema metadata by table IDs (full table name, e.g. ethereum.raw.blocks) |
Schema IDs match full table names (e.g. ethereum.raw.token_transfers). Use search before fetching.
Create & Manage Queries
Create a New Query
Save a query programmatically for later reuse:
{
"name": "explorer_create_query",
"arguments": {
"title": "Ethereum Transactions by Date",
"sql": "SELECT * FROM ethereum.raw.transactions WHERE block_timestamp > {{start_date}} LIMIT {{limit}}",
"limit": 1000,
"parameters": {
"start_date": "2024-01-01",
"limit": "1000"
}
}
}
{
"query_id": "abc123..."
}
query_id to run or update the query later.
Update an Existing Query
Modify a saved query’s SQL or configuration:
{
"name": "explorer_update_query",
"arguments": {
"query_id": "abc123...",
"title": "Ethereum Transactions by Date (Updated)",
"sql": "SELECT block_number, hash, value FROM ethereum.raw.transactions WHERE block_timestamp > {{start_date}}",
"limit": 5000
}
}
- Optimize SQL for better performance
- Adjust row limits
- Update parameter defaults
- Change compute profiles
Run Saved Queries
Execute queries created in the Allium App or via explorer_create_query.
Get a Query ID
Create a query using explorer_create_query or save one in the Allium App to obtain its query_id.
Call the Tool
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "explorer_run_query",
"arguments": {
"query_id": "<YOUR_QUERY_ID>"
// "parameters": { "param": "value" } // optional
}
}
}
sql - Full query textdata - Result rowsmeta.columns - Column names and typesqueried_at - Execution timestamp
Run Raw SQL
Execute ad-hoc SQL queries directly:
{
"name": "explorer_run_sql",
"arguments": {
"sql": "SELECT COUNT(*) FROM ethereum.raw.transactions"
}
}
Supports up to 250,000 rows per query by default.
Explore Schemas
Search Schemas
Browse Schemas
Fetch Schema
Find relevant tables using semantic search:{
"name": "explorer_search_schemas",
"arguments": {
"query": "erc20 token transfers"
}
}
["ethereum.raw.token_transfers", "ethereum.unified.transfers", ...]
Navigate the schema hierarchy like a filesystem:{
"name": "explorer_browse_schemas",
"arguments": {
"path": "" // Empty = list all databases
}
}
"" or "." → List all databases (ethereum, solana, bitcoin, etc.)"ethereum" → List schemas in ethereum database (raw, decoded, etc.)"ethereum.raw" → List tables in ethereum.raw schema"ethereum.raw.blocks" → Get full table details with columns
Use cases:
- Discover available databases and schemas
- Explore tables within a specific schema
- Fetch complete table details for a known table
Retrieve a table’s YAML schema metadata:{
"name": "explorer_fetch_schema",
"arguments": {
"id": "ethereum.raw.token_transfers"
}
}
table: ethereum.raw.token_transfers
description: ERC20 token transfers on Ethereum mainnet
columns:
- name: transaction_hash
type: STRING
description: Transaction hash
- name: amount
type: NUMBER
description: Raw token amount (unadjusted)
...
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"content": {
"text": "{\"sql\": \"SELECT ...\", \"data\": [...], \"meta\": {\"columns\": [...]}, \"queried_at\": \"2025-07-01T00:00:00Z\"}"
}
}
}
content.text as JSON to extract:
- sql - Full query string
- data - List of result rows (objects)
- meta.columns - Each column’s name and data type
- queried_at - ISO timestamp
