Skip to main content
bryel exposes a remote MCP server so an agent (Claude, Cursor, or your own) can work with your data directly: explore traces, turn them into fine-tune datasets, kick off training, and run evals — all scoped to a single project, with read or write access you grant at connect time. 
https://app.bryel.ai/api/mcp

​
Connect

Add the server URL in any MCP client that supports remote servers with OAuth: 
{
  "mcpServers": {
    "bryel": { "url": "https://app.bryel.ai/api/mcp" }
  }
}
On first connect you’re sent through OAuth: sign in, pick a project, and choose read or read + write. The connection is bound to that project — the agent never names one, and every call is re-checked against your access.
Write tools (creating datasets, starting training/evals) only work if you granted write at consent. To change it, reconnect and re-consent.

​
Tools

​
Explore

​
bryel_get_schema
read
The queryable trace fields, their types/operators, and this project’s live intent labels + model names. Call it first.
​
bryel_validate_query
read
Check a BQL filter for errors (with did-you-mean) without running it.
​
bryel_query_traces
read
Run a BQL filter over the project’s traces — match count + a sample.
​
bryel_trace_stats
read
The project’s inefficiency + cost breakdown, aggregated in ClickHouse.

​
Datasets

​
bryel_list_datasets
read
List the project’s fine-tune (SFT) datasets with record counts.
​
bryel_inspect_dataset
read
A dataset’s training-data quality: intent distribution, redundancy, trajectory health.
​
bryel_create_dataset
write
Create a new empty SFT dataset.
​
bryel_add_records
write
Add {messages, tools?} trajectories to a dataset.
​
bryel_add_from_query
write
Build a dataset from real runs — every trace matching a BQL filter, reconstructed into a training record.
​
bryel_export_dataset
write
Export a dataset as fine-tune JSONL to bryel storage. Returns a jobId.
​
bryel_export_status
read
Poll an export job; once succeeded, a presigned download URL.

​
Training

​
bryel_list_presets
read
The fine-tune presets (recipes): slug, base model, loop kind, expected data shape.
​
bryel_start_training
write
Start a fine-tune from a dataset + preset. Metered — pass max_spend_usd to cap it. Returns a runId.
​
bryel_training_status
read
Poll a training run: status, progress, loss, cost, and the weights download when done.

​
Evals

​
bryel_list_eval_suites
read
The eval suites (benchmarks) in the project: slug, name, default judge model.
​
bryel_start_eval
write
Create one run per case × model for a suite. Returns each run’s sessionId + case prompt for your harness to drive (see evals).
​
bryel_eval_results
read
A suite’s leaderboard over scored runs — overall, by model, and by case.
These are the same operations as the dashboard — the MCP server just lets an agent drive them.