baselight avatar

Baselight

ai.baselight/baselight

Connects Claude to Baselight's catalog of 70,000+ structured datasets spanning finance, demographics, sports, and other domains. You get direct query access to verified, traceable data that grounds LLM responses in facts rather than training data. Useful when you need Claude to reason over current public data, cross-reference sources during research, or mix structured datasets into analysis workflows. The streamable HTTP transport means you can integrate it without running local infrastructure. Baselight positions itself as the antidote to hallucination by routing requests through curated tables instead of parametric memory, so responses come with source attribution baked in.

tools
9
auth
Secret needed
transport
HTTP
last updated
Apr 30, 2026

Tools

9 tools

Public tool metadata for what this MCP can expose to an agent.

baselight_pingSimple ping test to verify MCP server is responding

Simple ping test to verify MCP server is responding

No parameter schema in public metadata yet.

baselight_search_catalogSearch the catalog for datasets using a text query and filters. Datasets in Baselight have the following format: @username.dataset. Datasets can be public or private — you can search and use all public datasets as well as the user's private datasets. This is typically the firs...3 params

Search the catalog for datasets using a text query and filters. Datasets in Baselight have the following format: @username.dataset. Datasets can be public or private — you can search and use all public datasets as well as the user's private datasets. This is typically the firs...

Parameters* required
categoryarray
The dataset category to filter by
limitnumber
Maximum number of datasets to return (1-20, default 10)default: 10
querystring
The search query string, used for semantic search
baselight_search_tablesSearch for tables using a text query and filters. Tables in Baselight have the following format: @username.dataset.table. Tables are grouped into datasets which can be public or private — you can search and use all public datasets as well as the user's private datasets. Search...3 params

Search for tables using a text query and filters. Tables in Baselight have the following format: @username.dataset.table. Tables are grouped into datasets which can be public or private — you can search and use all public datasets as well as the user's private datasets. Search...

Parameters* required
categoryarray
The dataset category to filter by
limitnumber
Maximum number of tables to return (1-20, default 10)default: 10
querystring
The search query string, used for semantic search
baselight_get_dataset_metadataRetrieve detailed schema and metadata for a specific dataset using Baselight format @username.dataset. Use this after discovering datasets to understand their structure before querying. Tables within datasets follow the format @username.dataset.table (always double-quoted iden...1 params

Retrieve detailed schema and metadata for a specific dataset using Baselight format @username.dataset. Use this after discovering datasets to understand their structure before querying. Tables within datasets follow the format @username.dataset.table (always double-quoted iden...

Parameters* required
idstring
The identifier of the dataset to inspect, should be something like @user.dataset
baselight_get_dataset_tablesRetrieve a paginated list of tables from a specific dataset using Baselight format @username.dataset. Use this tool to browse datasets with many tables or to search for specific tables within a dataset. Each page returns up to 100 tables with metadata.3 params

Retrieve a paginated list of tables from a specific dataset using Baselight format @username.dataset. Use this tool to browse datasets with many tables or to search for specific tables within a dataset. Each page returns up to 100 tables with metadata.

Parameters* required
idstring
The identifier of the dataset to browse, should be something like @user.dataset
pagenumber
Page number to retrieve (starts at 1). Each page contains up to 100 tables.default: 1
querystring
Optional text search query to filter tables by name or title. If omitted, returns all tables.default:
baselight_get_table_metadataRetrieve detailed schema and metadata for a specific table using Baselight format @username.dataset.table. Use this to understand table structure, column types, and constraints before writing SQL queries. Tables must be referenced in SQL with double quotes.1 params

Retrieve detailed schema and metadata for a specific table using Baselight format @username.dataset.table. Use this to understand table structure, column types, and constraints before writing SQL queries. Tables must be referenced in SQL with double quotes.

Parameters* required
idstring
The full identifier of the table to inspect, should be something like @user.dataset.table
baselight_get_userRetrieve detailed information about a Baselight user including their profile bio, website, and public datasets. Use this to understand who owns datasets you're interested in.1 params

Retrieve detailed information about a Baselight user including their profile bio, website, and public datasets. Use this to understand who owns datasets you're interested in.

Parameters* required
usernamestring
The username of the user to inspect
baselight_sdk_query_executeExecute a SQL query on Baselight and wait for results (up to 1 minute). The query executes and returns the first 100 rows upon completion, or info about a pending query that needs more time. Use DuckDB syntax only, table format "@username.dataset.table" (double-quoted), SELECT...1 params

Execute a SQL query on Baselight and wait for results (up to 1 minute). The query executes and returns the first 100 rows upon completion, or info about a pending query that needs more time. Use DuckDB syntax only, table format "@username.dataset.table" (double-quoted), SELECT...

Parameters* required
sqlstring
The SQL query to execute. table identifiers should be wrapped in double quotes, like "@user.dataset.table". Only SELECT queries are allowed.
baselight_sdk_get_resultsRetrieve results from a previously executed SDK job using the resultId from `sdk-query-execute`. If the query is complete, returns results immediately. If still pending, polls for up to 1 more minute. Use this after `sdk-query-execute` returns PENDING status.3 params

Retrieve results from a previously executed SDK job using the resultId from `sdk-query-execute`. If the query is complete, returns results immediately. If still pending, polls for up to 1 more minute. Use this after `sdk-query-execute` returns PENDING status.

Parameters* required
jobIdstring
The result ID of the executed query (from `sdk-query-execute`).
limitnumber
Number of rows to return per page (max 100). Default is 100.default: 100
offsetnumber
Row offset for pagination. Use to fetch subsequent pages (e.g., offset=100 for page 2).default: 0

Sponsors

Details

Website
baselight.ai
Transport
HTTP
Auth
Required
Registry
MCP registry, active