Knowledge & discovery - Allium Documentation Hub

Available tools

Tool	Description
`search_schemas`	Search Allium’s table catalog, or fetch one table’s full schema by ID
`search_docs`	Semantic search across Allium’s public documentation
`browse_docs`	Navigate the documentation tree like a filesystem
`search_terminal`	Search public Terminal dashboards built by Allium’s analysts
`get_terminal_results`	Fetch a Terminal chart’s SQL or its latest precomputed rows

Check search_terminal first for common topics. An analyst-built dashboard often answers the question already, and reading its SQL costs no Explorer Units.

Search schemas

Discovery
Fetch by ID

Search by keywords, table names, tags, or a description of the data:

{
  "name": "search_schemas",
  "arguments": {
    "query": "erc20 token transfers",
    "limit": 5
  }
}

Each hit returns the table ID, database, schema, table name, description, row count, tags, and score. Hits omit the markdown body by default so the payload stays small.

Once you know the table, fetch its full schema. id is the dotted <database>.<schema>.<table> form returned in a prior hit:

{
  "name": "search_schemas",
  "arguments": {
    "id": "ethereum.raw.blocks"
  }
}

Fetch-by-ID bypasses search and always includes the full markdown body: column names, types, and descriptions.

Parameter	Default	Notes
`query`	None	Mutually exclusive with `id`
`id`	None	Dotted table ID. Always returns full content
`include_content`	`false`	Full markdown body per hit. Use a `limit` of 1 to 3 when true
`limit`	`5`	Max 20. Use 3 to 5 for discovery
`search_mode`	`basic`	`basic` is BM25 keyword ranking, sub-millisecond. `advanced` is hybrid vector + keyword with better recall on natural-language queries

advanced search mode isn’t enabled for every organization. If it returns an error, retry with search_mode: "basic" or contact [email protected].

Search and browse documentation

search_docs is semantic search over docs.allium.so. Use it for data-model questions, API usage, and querying best practices.

{
  "name": "search_docs",
  "arguments": { "query": "how to query DEX trades" }
}

browse_docs walks the same content as a filesystem. Every directory has an _index.md listing its contents with descriptions.

{
  "name": "browse_docs",
  "arguments": { "path": "historical-data/_index.md" }
}

To find a file:

Read _index.md at the root to see the top-level sections.
Read a section’s _index.md (for example historical-data/_index.md).
Drill down through subdirectory index files.
Read the specific file for table schemas, SQL examples, or API specs.

Path form	Result
`""` or `"."`	Root directories and files
`"api"`	Contents of the `api/` directory
`"api/developer/prices/token-latest-price.md"`	That file’s content

Read the _index.md in a directory before you read anything else in it: it tells you which file you want. For a semantic lookup, use search_docs.

Realtime tool descriptions include a docs_path pointing at the exact file that documents their supported chains, edge cases, and response shape. Pass it to browse_docs.

Terminal dashboards

Terminal is Allium’s library of public, analyst-built dashboards. search_terminal and get_terminal_results read existing definitions and precomputed results, so neither consumes Explorer Units.

Find a dashboard

{
  "name": "search_terminal",
  "arguments": { "query": "stablecoin supply by chain", "limit": 5 }
}

search_terminal returns ranked hits with label, description, category, status, and URL. Set include_content: true with a small limit for the full rendered dashboard markdown. It never returns raw result rows or SQL.

List its charts

Call get_terminal_results with the dashboard_id and no chart_id to get the chart manifest.

Read a chart

{
  "name": "get_terminal_results",
  "arguments": {
    "dashboard_id": "<DASHBOARD_ID>",
    "chart_id": "<CHART_ID>",
    "mode": "both",
    "max_rows": 100
  }
}

mode is queries for SQL only, results for rows only, or both.

Terminal results are precomputed. Cite result.queried_at when you report a value so your reader knows how fresh it is, and link them to the Terminal dashboard for its context and visualizations.

A typical discovery flow

Check Terminal

Run search_terminal to see whether a dashboard already covers the question. If one does, pull its SQL with get_terminal_results and start from there.

Find the tables

Search the catalog with search_schemas and a descriptive query, then fetch the top table by id for the full column detail.

Check the data model

Read the vertical’s conventions with search_docs: adjusted volume, decimals, re-org handling.

Load the SQL rules

Call get_skill(name="sql-optimization") before you write the query.

SQL & queries

Run the query once you’ve found the tables

Skills

Allium’s own guidance on writing efficient SQL

Data Catalog

The human-readable version of the schema catalog

Terminal

Browse the public dashboards yourself

​Available tools

​Search schemas

​Search and browse documentation

​Terminal dashboards

​A typical discovery flow

​Related resources

SQL & queries

Skills

Data Catalog

Terminal

Available tools

Search schemas

Search and browse documentation

Terminal dashboards

A typical discovery flow

Related resources