Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Mirobody

PYPI · MIROBODY

Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.

Available components

+18 this week 80 Trust /100

Last scanned (20 hours ago)

Scores higher than 78% of PyPI servers

Category Health and Science

Trust breakdown (7 categories)

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 Security94
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Declares code that runs automatically (its declared build backend, an in-tree build backend, build-time code we could not rule out (a Hatch, PDM or setuptools build hook, a dynamic version we could not read statically, shipped VCS metadata or a stray root module)) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does. View diagnostics → Partial
  • 0 of 1 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 1 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability80
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 935 tokens (~116/item across 8 items; 6 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage83
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 50% 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

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 →

Changelog

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.

  • 21 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 20 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 19 Nov 26 +1
    • Package version: 1.6.1 → 1.6.2 functional
  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
  • 14 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 13 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
  • 11 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
Diagnostics

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 21 Nov 2026 · Analysed pypi/mirobody@1.6.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 3 scripts
Hook Tier Command
build_backend Not reviewed build_backend
backend_path Not reviewed <in-tree backend, unreviewed>
build_hook Not reviewed tool.setuptools.dynamic attr

Background: Why install scripts are a supply-chain risk →

Dependencies 1 package
Packages resolved 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~766 tokens

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 →

Tool Tokens
convert_unit ~109

Convert one value between units, offline, before comparing readings recorded differently. Crossing mass and substance concentration (mg/dL and mmol/L) needs the reading's LOINC code for the molar mass. A null `converted` is an answer: the units measure different things, so report the readings separately.

NameTypeReqDescription
from_unitstringyes–
loinc_codestring–Needed only between mass and substance concentration.
to_unitstringyes–
valuenumberyes–

No output schema declared.

No examples provided.

normalize_unit ~71

Normalize units as printed (mg/dL, 毫摩尔每升, 次/分) to canonical UCUM and their LOINC property family, offline. An empty `ucum` means unrecognized. The family does not decide convertibility; convert_unit does.

NameTypeReqDescription
unitsarrayyes–

No output schema declared.

No examples provided.

resolve_indicator ~98

Resolve indicator names to LOINC codes, offline. Same code from two names means the same test. Unresolved is an honest no: report it unmatched, never invent a code. A panel name answers with the panel's code (blood pressure gives 85354-9); a family of tests (血脂, lipid panel) is refused. Prefer standardize_reading when a value and unit are known.

NameTypeReqDescription
namesarrayyes–

No output schema declared.

No examples provided.

standardize_complaint ~140

Classify a complaint or a diagnosis in a person's own words (头疼, sore throat, 高血压) on ICPC-3, offline. kind=symptom for what someone feels, kind=condition for a named diagnosis; the two use different ICPC-3 components and must not be mixed. The words stay in `code.text`; without a `coding` the vocabulary could not place them, and the coding-decision extension's `reason` says why. The ICPC-3 display names are English.

NameTypeReqDescription
kindstring––
textstringyesThe complaint or diagnosis as the person wrote it.

No output schema declared.

No examples provided.

standardize_reading ~224

Turn lab or vital-sign readings as printed (any language) into FHIR Observations with their LOINC code and UCUM unit, offline and without a key. The unit takes part in choosing the code (cholesterol in mmol/L and in mg/dL are different codes), so pass it. An Observation without `coding` means no code was chosen, and the coding-decision extension's `rejectedReason` says why when a code was set aside. A blood pressure such as 120/80 mmHg is two readings (systolic, diastolic). Pass one reading (name, value, unit) or up to 200 as `readings`.

NameTypeReqDescription
namestring–The test name exactly as printed, any language.
readingsarray––
unitstring–The unit as printed: g/dL, mmol/L, 次/分. Omit when none.
valuestring|number–The result as printed: 13.5, <5, 阴性, Positive.

No output schema declared.

No examples provided.

standardize_report ~124

Read a lab report (PDF, image, spreadsheet, text) and return every reading as a FHIR Observation with its LOINC code. Reading the document takes a model: this sends it to the model provider configured on this machine, and needs `pip install 'mirobody[parse]'` and one model key. Coding is local. Pass `path` for a local file or `text` for report text.

NameTypeReqDescription
pathstring–A local file path readable by this server.
textstring–Report text, instead of a file.

No output schema declared.

No examples provided.

Install

How do I install the Mirobody MCP server?

Mirobody runs locally as a PyPI package, launched with uvx --python 3.12 mirobody mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

pypi · mirobody

# add to Claude Code
claude mcp add ai-thetahealth-mirobody -- uvx --python 3.12 mirobody mcp
Common questions

What is the Mirobody MCP server?

Mirobody is an MCP server listed in the public MCP registry as ai.thetahealth/mirobody. Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key. This page covers its PyPI package (mirobody).

Is the Mirobody MCP server safe to use?

Mirobody scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 Mirobody MCP server expose?

Mirobody exposes 6 tools: standardize_reading, standardize_complaint, standardize_report, resolve_indicator, normalize_unit, convert_unit. Their descriptions and schemas cost roughly 766 tokens of context every time the server is loaded.

Is the Mirobody MCP server still maintained?

Mirobody is still listed as active in the MCP registry. We last reached this channel on 21 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 Mirobody MCP server under?

Mirobody 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 Mirobody MCP server?

VerifyMCP ran 16 checks on Mirobody, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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.