Write a review

Head to head · Patient record retrieval · October 2026 research run

Medblocks vs Metriport Medical API

Medblocks scores 52.7 (D) on agent readiness against Metriport Medical API's 50.1 (D), and leads in 3 of 7 scored categories. Metriport Medical API leads on reliability, maintenance & community and transparency & trust. Both do patient record retrieval.

Best health record and wellness data APIs for AI agents · All 63 health comparisons

MedblocksMedblocks Inc. · HTTP API D52.7/100#773 of 1076 Metriport Medical APIMetriport Inc. · HTTP API D50.1/100#833 of 1076

Which one, for what

Medblocks D

Best for A consumer or care app, or an assistant, that needs a patient's own records from US hospitals and payers with the patient's consent, and wants an MCP route as well as REST.

Ahead on

  • Security & auth, 67 against 41
  • Payments & pricing, 25 against 5

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No status page, SLA or published rate limits for the Platform API

Metriport Medical API D

Best for US care providers and digital health companies that need a patient's network records as FHIR with webhooks.

Ahead on

  • Reliability, 45 against 28
  • Maintenance & community, 74 against 69
  • Transparency & trust, 56 against 51

Also in its favour

  • Open source

Watch for

Every API key has full access, including destructive operations, with no scopes

Score by category

CategoryWeight this runMedblocksMetriport Medical APIEdge
Reliability16%202845Metriport Medical API +17
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26265Metriport Medical API +3
Agent ergonomics13%16.27270Medblocks +2
Security & auth14%17.56741Medblocks +26
Payments & pricing10%12.5255Medblocks +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86974Metriport Medical API +5
Transparency & trust7%8.85156Metriport Medical API +5
Negative events≤1500
TotalD 52.7/100D 50.1/100

Facts side by side

FactMedblocksMetriport Medical API
KindHTTP APIHTTP API
VendorMedblocks Inc.Metriport Inc.
Hosted endpointhttps://app.medblocks.com/mcpno (local only)
TransportsHTTP, Streamable HTTPHTTP
AuthOAuth or keyAPI key
PricingFreemiumPaid
x402nono
LicenceProprietary service under Medblocks' terms. The medblocks TypeScript SDK on npm carries a proprietary licence that forbids redistribution and reverse engineering. The agent skills repository has no licence fileProprietary hosted service under Metriport's terms of use. The source in metriport/metriport is AGPLv3, with an enterprise directory under its own licence, and the @metriport/api-sdk package on npm is MIT
Tools exposed10none
Read-only variant documentednono
llms.txtyesyes
Last release2026-09-142026-09-28
Terms last updated2026-10-052024-01-01
Privacy policy last updated2026-10-052023-02-21
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesyes
Arbitration or class-action waivernot found in the textyes
Popularity36 npm/wk793 stars, 28k npm/wk

Verdicts

Medblocks

Patient-authorised record retrieval with a ten-tool remote MCP server, OAuth with per-capability consent, an audit entry for every call and a free plan for 1,000 active patients. No status page, no published rate limits and no idempotency keys were found, and the OpenAPI file behind the reference is not published.

Metriport Medical API

One network query pulls a patient's records from HIEs, pharmacies and labs and returns deduplicated FHIR, with per-operation rate limits, RFC 7807 errors and AGPLv3 source. Each API key has full access with no scopes, there are no public prices, and the sandbox opens only after Metriport approves the account.

Before you call either

Medblocks

  1. Connect with claude mcp add --transport http medblocks https://app.medblocks.com/mcp and sign in, or send a workspace API key as a Bearer token from a backend
  2. Ask the person before calling disconnect_health_system or delete_person. Both are permanent
  3. Wait for the connection webhook or check connection status before reading records. Pulls run in the background after the patient approves
  4. Branch on error.code, not the message, and wait the Retry-After seconds on a 429
  5. Use a Sandbox workspace and the Synthetic Hospital (password demopass) for tests. Sandbox keys cannot reach production sources

Metriport Medical API

  1. Check the errors array after Start Network Query. It returns 2XX even when some sources fail
  2. Wait for network-query.* webhooks or poll Get Network Query Status before reading consolidated data, which is cached from the last query
  3. Send the resource's eTag in If-Match on updates to avoid overwriting newer data
  4. Keep patient creates under 15 a minute and network queries under 20 a minute per source
  5. In sandbox, create patients whose first name matches a pre-defined persona to get example records

Questions

Which is better for AI agents, Medblocks or Metriport Medical API?

Medblocks scores 52.7 (D) on agent readiness against Metriport Medical API's 50.1 (D), and leads in 3 of 7 scored categories. Metriport Medical API leads on reliability, maintenance & community and transparency & trust.

Do Medblocks and Metriport Medical API need an API key?

Medblocks takes an API key or an OAuth sign-in. Metriport Medical API needs an API key.

Can an agent call Medblocks and Metriport Medical API without installing anything?

Medblocks has a hosted endpoint at https://app.medblocks.com/mcp. No hosted endpoint is listed for Metriport Medical API.

Are Medblocks and Metriport Medical API open source?

No open-source release is listed for Medblocks. Metriport Medical API is open source (Proprietary hosted service under Metriport's terms of use. The source in metriport/metriport is AGPLv3, with an enterprise directory under its own licence, and the @metriport/api-sdk package on npm is MIT).

Other comparisons with Medblocks or Metriport Medical API

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report