mcp-risk-index
Languages: English | 中文
An open risk index for common MCP servers, permissions, commands, and maintenance signals.
Status
v0.3.1 - evidence-backed catalog rendering with reviewer questions, strict review checks, and refreshed public sample metadata.
Purpose
Convert mcp-audit rule experience into a reusable public data asset without unsupported claims.
First Production Surface
Versioned data catalog with evidence-backed entries and a deterministic local CLI.
From PyPI:
python3 -m pip install xone-mcp-risk-index
mcp-risk-index init --output mcp-risk-index.catalog.yml
mcp-risk-index validate --catalog mcp-risk-index.catalog.yml --strict
mcp-risk-index render --catalog mcp-risk-index.catalog.yml --format markdown --output mcp-risk-index.md
mcp-risk-index render --catalog mcp-risk-index.catalog.yml --format json --output mcp-risk-index.json
From Homebrew:
brew install x-one-ai/tap/mcp-risk-index
mcp-risk-index --version
From a source checkout, you can also validate the bundled catalog:
mcp-risk-index validate --catalog data/catalog.yml --strict
mcp-risk-index render --catalog data/catalog.yml --format markdown --output mcp-risk-index.md
mcp-risk-index render --catalog data/catalog.yml --format json --output mcp-risk-index.json
For local development:
python3 -m pip install -e '.[dev]'
python3 -m pytest tests -q
Catalog Contract
The bundled catalog uses mcp-risk-index.catalog.v1. Each entry records identity, package, launch command, permissions, maintenance facts, review-level risk signals, evidence, and limitations. Rendered Markdown and JSON also include reviewer questions derived from the evidence-backed signals.
Review levels are prompts for human inspection:
info: useful contextreview: inspect before adoptionhigh-review: require explicit owner approval
They are not safety scores.
Strict validation requires production review governance fields such as maintenance.source_checked_at and a GitHub repository source.
Required Evidence
- server identity
- permission profile
- command/package signals
- maintenance signals
- evidence links
Non-Goals
- no subjective ranking without evidence
- no broad repo health clone
- no security claims without criteria
- no absolute safe/unsafe labels
OPT Operating Model
This project references the shared One Person Team workflow through ops/opt-overlay.md. Project-specific constraints live under ops/constraints, and evolvable local skills live under ops/skills.
Blocked Inputs
Inputs that require user or real-world data are recorded in ../x-one-skipped-inputs.md and should not block foundation work.
Real-user feedback should be classified as false-positive, false-negative, adapter-request, scenario-request, or catalog-update when it applies; portfolio-level handling is tracked in X-One portfolio health docs.
Docs
1 maintainer
Metadata
1 maintainer
Release files for xone-mcp-risk-index 0.3.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| xone_mcp_risk_index-0.3.1.tar.gz | 27.3 kB | With provenance | Details for xone_mcp_risk_index-0.3.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| xone_mcp_risk_index-0.3.1-py3-none-any.whl | Python 3 | none | any | Details for xone_mcp_risk_index-0.3.1-py3-none-any.whl |
Total release size: 37.1 kB
Release files / xone_mcp_risk_index-0.3.1.tar.gz
| Download URL | xone_mcp_risk_index-0.3.1.tar.gz |
|---|---|
| Size | 27.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5586abf1b5f346f2f18f010477916b1aab336a6d88d7e788429e3f20fbba1334
|
|
BLAKE2b-256 checksum How to use checksums |
90c02e5b455b9590df2995f8038ff5b32f2f590f331e783201f25c9e767a11c1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 14, 2026.
Transparency logRelease files / xone_mcp_risk_index-0.3.1-py3-none-any.whl
| Download URL | xone_mcp_risk_index-0.3.1-py3-none-any.whl |
|---|---|
| Size | 9.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0be64343f729db60a60d00bd2396cc0b66d53c77ec543116d61231d2ddc453d8
|
|
BLAKE2b-256 checksum How to use checksums |
2ee66e7ad48291f2c4b1d694bdbdb97419be882d131da4087416058776d808b7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 14, 2026.
Transparency logSecurity for xone-mcp-risk-index 0.3.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for xone_mcp_risk_index-0.3.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 14, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
