Skip to main content

What is the Orq MCP?

The Orq Model Context Protocol (MCP) server provides AI code assistants with direct access to your Orq.ai workspace. With 21 specialized tools, you can manage experiments, create datasets, configure evaluators, and analyze traces without leaving your IDE.

Key Capabilities

Experiment Management

Create and run experiments, configure task columns with prompts or agents, and export results in multiple formats

Dataset Operations

Create synthetic datasets, reshape local data, manage datapoints, and map data to experiments

Analytics & Insights

Query workspace analytics, track performance metrics, and ask natural language questions about your traces

Evaluator Configuration

Create LLM-as-a-Judge evaluators and Python code evaluators for automated quality assessment

Available Tools

The Orq MCP provides 21 tools across 8 categories:
CategoryToolDescription
Analyticsget_analytics_overviewGet workspace snapshot (requests, cost, tokens, errors, latency, top models)
Analyticsquery_analyticsFlexible drill-down with filtering and grouping
Datasetcreate_datasetCreate a new dataset
Datasetlist_datapointsList datapoints in a dataset
Datasetcreate_datapointsCreate datapoints (max 100)
Datasetupdate_datapointUpdate a datapoint
Datasetdelete_datapointsDelete datapoints (max 100)
Datasetdelete_datasetDelete a dataset and all datapoints
Evaluatorcreate_llm_evalCreate LLM-as-a-Judge evaluator
Evaluatorcreate_python_evalCreate Python code evaluator
Experimentlist_experiment_runsList runs with cursor pagination
Experimentget_experiment_runExport run (JSON/JSONL/CSV)
Experimentcreate_experimentCreate experiment from dataset with optional auto-run
Modelslist_modelsList all available AI models
Registrylist_registry_keysList available attribute keys for filtering traces
Registrylist_registry_valuesList top values for a specific attribute
Searchsearch_entitiesSearch projects, datasets, prompts, or experiments
Searchsearch_directoriesList directories within a project
Traceslist_tracesList traces with filtering and sorting
Tracesget_spanRetrieve a single span (compact or full mode)
Traceslist_spansList all spans in a trace

Supported Code Assistants