Medblocks

# Fix list: Medblocks

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/medblocks, the October 2026 research run, assessed 14 October 2026. Grade D, 52.7 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Medblocks: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Reliability, 28 out of 100, up to 14.4 more on the total

Why it scored 28: Read with the hosted lines and scored on the Platform API and MCP server. No status page was found. status.medblocks.com did not answer and the docs link none (0). No readable incident history (5). No request limit for the Platform API is published. The only number is manual webhook redelivery at once a minute per event (3 of 15). 429 responses carry `Retry-After`, the SDK retries 429, 502, 503 and 504 up to three times, and webhook consumers are told to dedupe by `event.id`. No idempotency keys for writes were found, and the conventions page meant to cover idempotency is a placeholder (10 of 15). No SLA found (0). Patient access and the SDK are at 1.0 with no beta label, though the backend guides are marked a work in progress and wearables as coming soon (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 2. Payments & pricing, 25 out of 100, up to 9.4 more on the total

Why it scored 25: Read with the hosted rubric. No x402, MPP or L402 (0). Plan prices are public, Free at $0 and Enterprise at $60,000 a year, with no per-unit price (10). The Free plan covers 1,000 active patients with full API access, and the docs show no card step at sign-in. The dashboard sits behind a login, so the card question was not confirmed (15 of 20). A person signs in through a browser to create the workspace, and each patient approves at their hospital. Dynamic client registration lets an MCP client register itself but still needs that sign-in (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 3. Schema & documentation, 62 out of 100, up to 6.2 more on the total

Why it scored 62: The reference pages say they are generated from `openapi/medblocks.json`, but that file is not published and the usual paths on app.medblocks.com return the web app. The MCP server's tool schemas sit behind sign-in (8 of 25). llms.txt, llms-full.txt and a Markdown version of every page (10). Guides explain which of the four surfaces fits which relationship, and the MCP page describes each tool and permission (14 of 20). Typed limits such as `limit` 1 to 100 and enumerated error codes were seen. The generated reference renders its parameter tables by script, so enums and required fields could not all be confirmed (9 of 15). Code samples throughout and an error catalogue of 36 codes with HTTP status and cause (13 of 15). A dated SDK changelog marks breaking changes, and the API takes a `Version` header, but the versioning page is an unwritten placeholder (8 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 4. Security & auth, 67 out of 100, up to 5.8 more on the total

Why it scored 67: OAuth from Medblocks' own server with dynamic client registration, PKCE, introspection, revocation and six resource scopes, and workspace API keys that owners and admins rotate and revoke, with separate Sandbox and Production prefixes. The error list includes `insufficient_scope` for keys (30). The consent screen has a tick box for managing people and deleting data that can be left off, and members cannot create keys. Confirmation before the two destructive tools is left to the assistant (15 of 20). get_health_records returns clinical text from hospital systems, and no prompt-injection guidance was found (3 of 15). Every MCP call writes an audit entry, and the dashboard shows authorisation and pull history per patient (12 of 15). The security page says public materials list HIPAA, SOC 2 Type II, ISO 27001 and GDPR, with reports in a packet on request. No security.txt, disclosure policy or bug bounty was found (7 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 5. Agent ergonomics, 72 out of 100, up to 4.6 more on the total

Why it scored 72: Ten MCP tools, short and task-shaped, and API list responses sized by `limit`. No read-only toolset beyond the consent tick boxes (22 of 25). Cursor paging on every list with `has_more` and `next_cursor`, plus `q` and `type` filters on the connections catalogue (17 of 20). One error envelope with a stable `code`, the failing `param`, a `request_id` and `retryAfter`, documented per code (19 of 20). No idempotency keys. `external_id_already_exists` (409) catches duplicates. The MCP page says every tool, lookups included, declares that it changes state because each call writes an audit entry, so no readOnlyHint is set (6 of 20). Few required parameters, and one official SDK, in TypeScript (8 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 6. Transparency & trust, 51 out of 100, up to 4.3 more on the total

Made of editorial 32, provenance 70.

Why it scored 51: Closed service. The SDK licence is proprietary and forbids redistribution and reverse engineering. The public terms cover the website and the Blue Button application, with no customer terms for the Platform API found (10 of 30). The privacy policy covers Medblocks Platform and the MCP server, deletes Medicare data within 7 days of a request, keeps automatically collected data up to 24 months and says nothing is used to train AI models. Other periods are 'a reasonable period' and it does not mention the BAA the docs require (12 of 30). The changelog calls out breaking changes, but no deprecation policy or notice period exists, and the versioning page is a placeholder (5 of 20). Data is processed in the United States per the privacy policy. No sub-processor list was found (5 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Terms of service: read, states 4 of the 7 things a reader expects, and has 3 clauses that cost points (1.4 of 10)
- Privacy policy: read, states 6 of the 8 things a reader expects (8.5 of 10)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 69 out of 100, up to 2.7 more on the total

Why it scored 69: npm shows 1.2.0-dev.5 on 10 August, dev.6 on 7 September and dev.7 on 14 September 2026, and the skills repository was last pushed on 2 October (30). Three releases in the last 90 days (20). Closed service with a dated changelog and support through a Google form. We could not test whether support answers (6 of 15). One official SDK, TypeScript, whose latest tag is still 1.0.0 while the changelog documents 1.1.0 and 1.2.0. No entry in the official MCP registry (7 of 15). The SDK has no runtime dependencies and needs Node 20 or Bun 1. The source repository is private, so CI could not be seen (6 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: the OpenAPI file `openapi/medblocks.json` named on every reference page. It is not at the obvious public paths, and the reference renders its schemas by script
- unchecked: the MCP tool definitions and annotations, which need a signed-in session. The tool list is from the docs page
- unchecked: whether workspace sign-up asks for a card, and what permissions an API key can carry. The dashboard is behind a login
- unchecked: SOC 2 Type II and ISO 27001 reports. The docs cite 'public Medblocks materials' and offer a security packet on request
- The billing page lists wearable device sync in the Free plan, while the wearables page says support is coming soon
- The founder's lead put Medblocks among health platforms. It is also a services and training company, and the graded product is Medblocks Platform, its patient-access API and MCP server

## Weaknesses

- No status page, SLA or published rate limits for the Platform API
- No idempotency keys were found, and the API conventions and versioning pages are unwritten placeholders
- The OpenAPI file the reference is generated from is not published
- Only one SDK, in TypeScript, with npm's latest tag still at 1.0.0 while the changelog documents 1.2.0
- The public terms cover the website and Blue Button app, and no sub-processor list or customer terms for the API were found

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- 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
- Ask the person before calling `disconnect_health_system` or `delete_person`. Both are permanent
- Wait for the connection webhook or check connection status before reading records. Pulls run in the background after the patient approves
- Branch on `error.code`, not the message, and wait the `Retry-After` seconds on a 429
- Use a Sandbox workspace and the Synthetic Hospital (password `demopass`) for tests. Sandbox keys cannot reach production sources

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.