Healthclaw Guardrails vs Last EHR — Medplum
A side-by-side look at the Healthclaw Guardrails and Last EHR — Medplum MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Healthclaw Guardrails for biology & bioinformatics work over a hosted endpoint; choose Last EHR — Medplum for biology & bioinformatics as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Healthclaw Guardrails when
- You need dedicated capabilities in the Biology & Bioinformatics domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
context_get, fhir_read, fhir_search.
Choose Last EHR — Medplum when
- You need dedicated capabilities in the Biology & Bioinformatics domain.
- You prefer a local stdio subprocess transport.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Biology & Bioinformatics | Biology & Bioinformatics |
| Quality signal | 63/100 · Good | 44/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 31 | 4 |
| Directory activity | 4 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 27 | Not listed |
| Full listing | View Healthclaw Guardrails | View Last EHR — Medplum |
Tools & capabilities
Healthclaw Guardrails tools 27
context_getRetrieve a pre-built context envelope with patient-centric FHIR resources. Returns bounded, policy-stamped, time-limited context.fhir_readRead a specific FHIR resource by type and ID. Supports FHIR R4 US Core v9 stable resources and FHIR R6 ballot3 experimental resources. Returns redacted resource with PHI protection.fhir_searchSearch for FHIR resources. Supports FHIR R4 US Core v9 stable resources and FHIR R6 ballot3 experimental resources. Supports patient, code, status, _lastUpdated, _count, _sort parameters. Returns paginated, redacted Bundle.fhir_validateValidate a proposed FHIR R6 resource against structural rules. Returns OperationOutcome.questionnaire_populateSDC $populate — pre-fill a Questionnaire for a subject. Returns a QuestionnaireResponse. Read tier; mints a tenant token for non-public tenants.questionnaire_extractSDC $extract — extract FHIR resources from a completed QuestionnaireResponse into a transaction Bundle. Write tier; requires step-up authorization, including for dry_run=true previews.fhir_propose_writePropose a write — validates the resource and returns a preview. Does NOT commit. Write tier: step-up authorization is required and is supplied by the deployment as an X-Step-Up-Token header. You cannot obtain or pass it yourself. If it is absent this returns requires_step_up; tell the patient authorization is needed rather than attempting another route.fhir_commit_writeCommit a previously proposed write. Requires step-up authorization token. This is a destructive operation.fhir_statsCompute statistics (count, min, max, mean) over numeric Observation values. Standard FHIR $stats (since R4). Only supports valueQuantity. Filter by patient and/or code.fhir_interpret_labsInterpret lab Observations against reference ranges — flags each value low/normal/high/critical (HL7 v3 ObservationInterpretation) and returns clinician + consumer summaries. Decision support, not diagnosis. Read-tier. Response includes _meta.ui.resourceUri pointing to an embeddable trend timeline.care_gapsCheck which preventive-care screenings/immunizations a patient may be due for (blood pressure, cholesterol, colorectal/cervical/breast cancer screening, flu, diabetes A1c), from their own connected records. Decision support based on USPSTF/ACIP/ADA guidelines — not a diagnosis or directive. Response includes _meta.ui.resourceUri pointing to an embeddable review UI.guardrail_conformanceRun the guardrail conformance self-test on the connected HealthClaw deployment and return the graded scorecard across seven guardrail properties: PHI redaction, immutable audit, step-up auth, human-in-the-loop, tenant isolation, medical disclaimers, and error fidelity. Uses synthetic data only. Set fresh=true to force a new run instead of the cached result.- +15 more on the listing page
Last EHR — Medplum tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Healthclaw Guardrails
{
"mcpServers": {
"healthclaw-guardrails": {
"url": "https://mcp-server-production-5112.up.railway.app/mcp"
}
}
}
Last EHR — Medplum
{
"mcpServers": {
"last-ehr-medplum": {
"command": "npx",
"args": [
"-y",
"@lastehr/agent-write-conformance"
]
}
}
}
Frequently asked questions
Healthclaw Guardrails is categorized under Biology & Bioinformatics and uses a remote HTTP/SSE transport. Last EHR — Medplum belongs to Biology & Bioinformatics and uses a local stdio subprocess. Pick Healthclaw Guardrails for biology & bioinformatics work and Last EHR — Medplum for biology & bioinformatics.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Healthclaw Guardrails is listed as free. Last EHR — Medplum has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add healthclaw-guardrails and last-ehr-medplum as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Healthclaw Guardrails has a quality signal of 63/100 (Good) with 4 views, 0 installs and 31 GitHub stars. Last EHR — Medplum has 44/100 (Fair) with 4 views, 0 installs and 4 GitHub stars.