search_docs
Search Braintrust documentation to find relevant guides, API references, and code examples.
LABSCO SUMMARY
infer_schema before sql_query is the pairing that makes agent-written SQL work here.
Eval logs have irregular shapes — fields appear as prompts change — so a model writing SQL against them from memory will reference columns that do not exist in this project. Discovering the schema first turns that from a guess into a lookup. The pattern tools are the unusual part: an agent can not only find that a class of trace fails, but record that finding with evidence and attach it to every matching trace, so the next investigation starts where this one ended.
What it is
Braintrust's endpoint over their evaluation platform, with a separate EU address for EU organisations. Ten tools: documentation, object navigation, SQL, and a pattern log for recording what you found.
What you get
- sql_query — SELECT over experiments, datasets and logs, with an overflow path when results exceed 1MB
- infer_schema — discover fields, types and common values before writing the query
- resolve_object and list_recent_objects — turn names into IDs, parse Braintrust URLs, list what you have access to
- summarize_experiment — aggregated metrics, optionally against a baseline
- search_patterns, new_pattern and update_pattern — record a finding with evidence and attach it to matching traces
- search_docs and generate_permalink
Requirements
OAuth in most clients, or a bearer API key. EU organisations connect to api-eu.braintrust.dev instead.
Setup effort
Paste a URL, then authorize — add the endpoint to your client, then approve the OAuth consent screen
USE CASES
01
Querying an experiment properly
Infer the schema, then write SQL against the fields that actually exist.
02
Comparing a run against a baseline
Summarise the experiment with the baseline named, rather than eyeballing two dashboards.
03
Recording what you learned
File the pattern with its evidence and attach it to matching traces so it is not rediscovered.
04
Handing a result to a colleague
Generate a permalink to the object rather than describing where to click.
10 tools
Listed in project docs. Your client may show a different list.
resolve_object
Convert names to IDs (or vice versa) and parse Braintrust URLs.
list_recent_objects
List recently created projects, experiments, datasets, prompts, or functions you have access to.
infer_schema
Analyze structure/content of experiments, datasets, or logs; discovers fields, data types, common values.
search_patterns
Search existing project patterns by text, ID, status, or quality.
new_pattern
Report a new project pattern with supporting evidence (write tool).
update_pattern
Update an existing project pattern or attach evidence to matching traces (write tool).
sql_query
Query experiments, datasets, and logs with SQL (SELECT/FROM/WHERE/GROUP BY/ORDER BY/LIMIT). Results >1MB return an overflow envelope (overflow_url, byte_length, row_count, instructions).
summarize_experiment
Aggregated performance metrics for an experiment, optionally vs a baseline.
generate_permalink
Generate a direct web link to a Braintrust object.
BEFORE YOU INSTALL
What to know first
Tools you get
10 tools named in the project's documentation.
Requires
- an MCP client that can reach a remote endpoint
- OAuth 2.0 in most clients, or an Authorization: Bearer API key
INSTALLATION
Connect your client
Add the endpoint to your client, then approve the OAuth consent screen.
Server setup
ENDPOINT URL
https://api.braintrust.dev/mcpRequirements
- OAuth 2.0 in most clients, or an Authorization: Bearer API key
