Industry solutionsPublic source

EHR MCP Server

An Electronic Health Record integration layer for ADK-Rust Enterprise clinical agents. 25 MCP tools spanning the patient chart — demographics, encounters, problems, medications, results, notes, care gaps, quality…

Open the source Read the official guide ↗

What it gives an agent

A purpose-built capability behind one MCP connection.

The server owns its domain logic and publishes a tool contract an MCP client can discover. ADK-Rust can load that contract into an agent, normalize each schema for the chosen model provider, and keep the connection lifecycle outside the agent’s business logic.

PHI access logging — every patient-scoped read or write appends an AccessEntry (actor, patient, action, timestamp). get_access_log returns the accounting of disclosures, supporting HIPAA…

Attributable access — every tool takes an actor; nothing touches a chart anonymously.

Gated clinical writes — medication changes, clinical notes, prior auth, and denial actions require approval in production (requires_approval); reads are read_only.

Minimum necessary — patient search returns only identifying demographics, not the full chart.

FHIR-aligned model — patients, encounters, conditions, medications, allergies, observations, notes map to familiar resource shapes.

Fictitious data only — the built-in sample chart uses invented names/identifiers; no real PHI ships in the crate.

Architecture

How EHR MCP Server fits into an agent system.

The model never needs the implementation details or credentials of the system behind the server. It sees reviewed tool definitions. The MCP client handles discovery and calls, while the server keeps ownership of validation, policy, and communication with its domain system.

ADK-Rust agent

Chooses a capability from the reviewed tool catalog.

→

MCP client

Discovers schemas, sends calls, and receives typed content.

→

EHR MCP Server

Validates the request and owns 26 documented tool contracts.

→

Domain system

Keeps the API, data, credentials, and business rules behind the server.

Connection: stdio · Server framework: ADK MCP SDK + rmcp

EHR MCP Server architecture diagram from its official repository

Tool catalog

What can an agent ask EHR MCP Server to do?

Each tool has a stable name, a human-readable purpose, and a JSON input contract discovered during MCP initialization. Risk classes come from the project’s registry manifest when one is available.

26 named tools

backend_info

Report the active clinical-read backend (memory or FHIR R4); no PHI

read only

find_patients

Find patients by MRN or name (minimum-necessary demographics); logged to PHI access log

read only

get_patient

Get patient demographics and coverage (PHI read)

read only

get_encounters

List a patient's encounters (PHI read)

read only

get_conditions

Get a patient's problem list (PHI read)

read only

get_medications

Get a patient's medication list (PHI read)

read only

get_allergies

Get a patient's allergies (PHI read)

read only

get_observations

Get observations/results, optionally by category (PHI read)

read only

get_notes

Get a patient's clinical notes (PHI read)

read only

add_medication

Add a medication to the patient's list (gated clinical write)

internal write

set_medication_status

Change a medication's status (gated clinical write)

internal write

add_note

Add (and optionally sign) a clinical note (gated clinical write)

internal write

Governance

Understand the effect of every tool.

A server connection inherits the authority of its credentials and deployment environment. The declarations below come from this project’s README and MCP registry manifest; your application still decides which tools an agent receives and where approval is required.

16 read only10 internal write

Gated clinical writes — medication changes, clinical notes, prior auth, and denial actions require approval in production (requires_approval); reads are read_only.

MCP surface

What the current documentation declares.

MCP can carry tools, resources, prompts, structured results, progress, cancellation, and long-running work. This record highlights the modern protocol features explicitly mentioned by this repository.

Resources

ADK MCP SDKrmcpRegistry manifest

Install and connect

Follow the project’s documented starting point.

Install the server in the environment that owns its credentials and domain access. Add it to your MCP host, verify the discovered tools, and narrow the toolset before giving it to a production agent.

Install

cargo install mcp-ehr

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-ehr",
    ["mcp-ehr"],
).await?;

let agent = LlmAgentBuilder::new("agent")
    .tools(toolset.tools().await?)
    .build()?;

Commands and configuration are extracted from the public README. Confirm prerequisites, environment variables, and release-specific options in the official documentation before deployment.

Official documentation

Continue with the project maintainers’ source of truth.

This page provides an approachable map of the server. The repository remains authoritative for exact schemas, prerequisites, configuration, examples, tests, releases, and security updates.

Overview ↗README.md CHANGELOG ↗CHANGELOG.md Architecture ↗docs/architecture.svg Issues and support ↗github.com issues

Keep exploring

EHR MCP Server

A purpose-built capability behind one MCP connection.

How EHR MCP Server fits into an agent system.

ADK-Rust agent

MCP client

EHR MCP Server

Domain system

The server’s published architecture

What can an agent ask EHR MCP Server to do?

Understand the effect of every tool.

What the current documentation declares.

Follow the project’s documented starting point.

Continue with the project maintainers’ source of truth.

More in industry solutions.