Is Model Context Protocol / MCP safe?
Model Context Protocol / MCP scores 62.4/100 (Grade C), ranked #141 of 328 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types).
The public evidence: no package-provenance attestation found;
OSSF Scorecard rates its supply-chain practices 6.8/10;
78% of recent commits are signed;
last pushed 2026-07-10. Every point is earned from checkable signals — never paid placement. How scoring works →
Quick Trust Read
Verdict
Promising trust profile, but some evidence still deserves review.
62.4/100 · Grade C
Strongest Signal
Transparency
14.3/17
Weakest Signal
Safety / Integrity
12.4/25
What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-07-04
Activity Score Changed
Activity score up 5pts (85 → 90)
2026-06-29
Rank Moved
Rank rose 12 spots (#158 → #146)
2026-06-24
Rank Moved
Rank dropped 11 spots (#145 → #156)
Maintainer Checklist
Raise Scorecard signalsCurrent OSSF Scorecard is 6.8/10. Tighten the weakest checks to improve public safety evidence.
Publish provenanceAdd package provenance or release attestations so users can verify where shipped artifacts came from.
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade C reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →
Signals refreshed2026-07-11 04:00 UTC·Repo last pushed yesterday
Rank Trend
2026-07-052026-07-11
Activity & Reach
Stars
88.3k
Forks
11.2k
Last Push
2026-07-10
yesterday
Commits (4 wk)
25?
Downloads (7d)
—
HN mentions (30d)
2
Open Issues
379
Rank Change
▲1
was #142
Analysis
HVTrust Dimensions
62.4 / 100 · 100.0% confidence
Safety / IntegrityOSSF, provenance, signatures
12.4 / 25
Identity / ProvenanceListing and build link
10.8 / 18
TransparencyLicense and public checks
14.3 / 17
MaintenanceFreshness and commits
14.8 / 20
AdoptionStars and downloads
11.9 / 20
Activity Inputs
91.0 / 100
StarsRepository reach
29.7 / 30
FreshnessLast push recency
24.9 / 25
ActivityRecent commits
17.6 / 25
CommunityFork signal
18.8 / 20
Supply Chain Trust
Package Provenance
None
No package attestations found
OSSF Scorecard
6.8 / 10
OpenSSF Scorecard · scanned Jul 10, 2026
Signed Commits
78%
of last 100 commits verified
Binary-Artifacts10
Branch-Protection6
CI-Tests10
CII-Best-Practices0
Code-Review9
Contributors10
Dangerous-Workflow10
Dependency-Update-Tool10
Fuzzing0
License9
Maintained10
Packaging10
Pinned-Dependencies2
SAST5
Security-Policy10
Signed-Releases-1
Token-Permissions0
Vulnerabilities3
Is Model Context Protocol / MCP safe?
Model Context Protocol / MCP has a mixed signal profile. Some trust indicators are present, others are missing. Whether it is safe for your use case depends on which gaps matter to you — review the breakdown below before adopting in production.
Does Model Context Protocol / MCP publish package provenance?
No published build provenance is currently detected for Model Context Protocol / MCP. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does Model Context Protocol / MCP have an OpenSSF Scorecard?
Model Context Protocol / MCP has an OpenSSF Scorecard score of 6.8/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is Model Context Protocol / MCP actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does Model Context Protocol / MCP use?
Model Context Protocol / MCP ships under NOASSERTION. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Model Context Protocol / MCP's commits signed?
78% of the last 100 commits to Model Context Protocol / MCP are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.
Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.
These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →
MCP Server Support
high confidence
Implemented
Model Context Protocol / MCP appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
Credential signal:
No explicit API-key/config marker detected.
Tool / Plugin Surface
high confidence
Declared
Declared plugin/integration surface detected.
browser
code
database
filesystem
search
Detailed evidence is not shown in the public view.
Package Provenance Drift
N/A
No package source configured
Detailed evidence is not shown in the public view.
MCP signal live
External deps live
Tool / plugin surface live
Package provenance drift live
How this surface has changed
Detected changes to Model Context Protocol / MCP's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.
Detected MCP server support changed: none → implemented
Maintain Model Context Protocol / MCP?
HVTrust scores Model Context Protocol / MCP from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.
Data sources
GitHub REST API (repo, commits, stars, forks, license) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.2 · Raw JSON
