Skip to main content

What is MCP?

The Model Context Protocol (MCP) is an open standard for connecting AI agents to external data sources and tools. Instead of building custom integrations, MCP lets agents call structured tools to query, create, and manage resources in real time. Claude, ChatGPT, Cursor, and any MCP-compatible client can connect to an MCP server and use its tools as part of their reasoning.

Why MCP for Verial?

Healthcare AI agents need to validate their own behavior against realistic simulated systems. The Verial MCP server gives agents direct access to the simulation platform, so they can set up test environments, run benchmarks, and analyze results without human intervention.
  • Self-testing agents. An agent can create its own test environment, define benchmarks, execute runs, and review results, all through tool calls in a single conversation.
  • IDE integration. Connect Verial to Claude, Cursor, or VS Code to manage simulations interactively while developing your agent.
  • Agentic CI/CD. Chain simulation setup, execution, and result analysis into automated pipelines that run on every deploy.

Design Principles

Action-Oriented Tools

Each tool maps to a resource and takes an action parameter to select the operation. One tool call to create, update, list, or delete. No multi-step discovery required.

Consistent Interface

Every tool follows the same pattern: action plus resource-specific fields. Learn one tool and you know them all. Agents can generalize across the entire surface.

Full Platform Access

All 11 resource types are available. Environments, simulators, datasets, benchmarks, tasks, evals, playgrounds, sandboxes, runs, and results. Nothing is hidden behind a separate API.

Organization Scoped

Every tool call is scoped to the authenticated organization. Agents see only the resources they own. No project IDs or tenant parameters to manage.

Tools

Eleven tools, one per resource. Each tool takes an action field to select the operation.
ToolActionsDescription
environmentslist, create, get, update, delete, addSimulator, removeSimulatorManage simulated health systems
simulatorslist, create, get, update, deleteManage simulator definitions
datasetslist, create, get, update, deleteManage synthetic patient data
benchmarkslist, create, get, update, deleteManage benchmark definitions
taskslist, create, get, update, deleteManage test cases within benchmarks
evalslist, create, get, update, deleteManage assertions on tasks
playgroundslist, create, get, teardownProvision live environment instances
sandboxeslist, create, get, listEvents, teardown, addDataset, removeDatasetManage running simulator instances
benchmark_runslist, create, get, complete, cancelExecute benchmarks and track results
task-runslist, get, complete, cancelTask-level run results
eval-runslist, getEval-level run results

Data Model

  • Simulators define simulated systems (FHIR, HL7, Voice, Fax, Web portals)
  • Environments compose simulators into a coherent health system
  • Datasets contain FHIR bundles or files, linked to sandboxes at runtime
  • Benchmarks group tasks with evals into a test suite
  • Playgrounds are running instances of environments with live sandboxes
  • Runs execute benchmarks, producing task runs and eval runs with scores

Next Steps

Setup

Connect the Verial MCP server to Claude, ChatGPT, Cursor, or your custom agent.

Tools Reference

Full parameter and response documentation for all eleven tools.

Workflow Examples

Step-by-step tool call sequences for common simulation tasks.

Best Practices

Prompt tips, context management, and error handling.