FHIR Scorecard
PYPI · FHIR-SCORECARD
Read-only grades for publicly observable FHIR endpoints, served from the published dataset.
Available components
Last scanned (8 hours ago)
Scores higher than 76% of PyPI servers
Category Health and Science
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency71
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Cryptographically verified build provenance (signed, bound to ChelseaKR/fhir-scorecard). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 16 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability67
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 293 tokens (~58/item across 5 items; 5 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management53
- Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage80
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 40% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 2 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 1 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 31 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- 29 Oct 26 +16
- Malware scan: unverified → pass ▲ security
- 27 Oct 26 +4
- Stability: unverified → 0.23 ▲ functional
- 24 Oct 26 −6
- Source repository: pass → fail ▼ security
- Security disclosure: pass → unverified ▼ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/fhir-scorecard@0.3.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | ChelseaKR/fhir-scorecard |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/ChelseaKR/fhir-scorecard/.github/workflows/pypi-publish.yml@refs/heads/main |
| Rekor log index | 3331237024 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:fa0918f1fff2c89d884796598238cc9c20ab71b03717f0bb9d01badc8062eff6 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cited_passages ~73
For one endpoint, each finding together with the passages of the FHIR, SMART App Launch, or US Core specification page it cites, quoted verbatim from the copies retained under corpus/. No model is called; use these passages to explain a finding in the specification's own words.
| Name | Type | Req | Description |
|---|---|---|---|
| endpoint_id | string | yes | – |
No output schema declared.
No examples provided.
declared_capabilities ~86
What one endpoint's CapabilityStatement declared: every resource, interaction, search parameter, operation and profile as flat rows, with the retrieval date and the document's SHA-256. An observation of a declaration, never a test of it. The state field says when there was no readable declaration, and rows is null then, never an empty list.
| Name | Type | Req | Description |
|---|---|---|---|
| endpoint_id | string | yes | – |
No output schema declared.
No examples provided.
get_endpoint ~39
Full scorecard for one endpoint: every dimension, every finding with its spec citation, availability, and drift history.
| Name | Type | Req | Description |
|---|---|---|---|
| endpoint_id | string | yes | – |
No output schema declared.
No examples provided.
grading_method ~35
How grades are computed, what each finding code checks, and the documented limits of the dataset. Read this before characterizing any grade.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_endpoints ~60
List graded FHIR endpoints, optionally filtered by kind (payer, payer_provider_directory, provider, ehr, reference) or by grade.
| Name | Type | Req | Description |
|---|---|---|---|
| grade | string | – | Filter by letter grade A-F |
| kind | string | – | Filter by endpoint category |
No output schema declared.
No examples provided.
How do I install the FHIR Scorecard MCP server?
FHIR Scorecard runs locally as a PyPI package, launched with uvx fhir-scorecard mcp --site site. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
pypi · fhir-scorecard
claude mcp add chelseakr-fhir-scorecard -- uvx fhir-scorecard mcp --site site
What is the FHIR Scorecard MCP server?
FHIR Scorecard is an MCP server listed in the public MCP registry as io.github.ChelseaKR/fhir-scorecard. Read-only grades for publicly observable FHIR endpoints, served from the published dataset. This page covers its PyPI package (fhir-scorecard).
Is the FHIR Scorecard MCP server safe to use?
FHIR Scorecard scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the FHIR Scorecard MCP server expose?
FHIR Scorecard exposes 5 tools: list_endpoints, get_endpoint, cited_passages, declared_capabilities, grading_method. Their descriptions and schemas cost roughly 293 tokens of context every time the server is loaded.
Is the FHIR Scorecard MCP server still maintained?
FHIR Scorecard is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the FHIR Scorecard MCP server under?
FHIR Scorecard declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the FHIR Scorecard MCP server?
VerifyMCP ran 15 checks on FHIR Scorecard, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about FHIR Scorecard: Security disclosure. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.