Is MCP Apps safe to use?

MCP Apps has an HVTrust score of 85.7/100 (Grade A), ranked #45 of 1283 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for MCP Apps?

MCP Apps scores 85.7/100 on HVTracker's evidence-weighted HVTrust scale. It has 2.7k GitHub stars and is categorized under Protocols & Tool Integration.

MCP Apps

modelcontextprotocol/ext-apps

Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers

Protocols & Tool Integration TypeScript Grade A Listed NOASSERTION

85.7/100

Rank #45 of 1283

Compare MCP Apps

How does it stack up against its Protocols & Tool Integration neighbours?

Pick any agent to compare →

Strong public trust posture, backed by multiple independent signals.

Open compare tool Suggest correction

Listing state

Listed

Evidence coverage

Grade B · 3/5 signals

Last push

2026-07-23 · 19d ago

Recent change

Scorecard

Is MCP Apps safe? MCP Apps scores 85.7/100 (Grade A), ranked #45 of 1283 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 5.8/10; 100% of recent commits are signed; last pushed 2026-07-23. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Protocols & Tool Integration

#2 A2A / Agent2Agent Protocol — 89.3 (A) → #3 FastMCP (TypeScript) — 86.5 (A) → #5 mcp-proxy — 79.7 (B) → #6 CLI-Anything — 79.3 (B) →

Quick Trust Read

What Would Improve It

Improve maintenance to lift the weakest part of the trust profile.

Recent Changes

2026-08-07

Scorecard Added

OSSF Scorecard: 5.8/10

2026-07-14

Newly Listed

First tracked at rank #80

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 5.8/10. Tighten the weakest checks to improve public safety evidence.

Compare with MCP Inspector Get email alerts for MCP Apps View Protocols & Tool Integration Report missing data

64.6

Activity sub-score · out of 100

In Protocols & Tool Integration

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A 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 →

Activity & Reach

Stars

2.7k

Forks

363

Last Push

2026-07-23

19 days ago

Commits (4 wk)

Downloads (7d)

1,583,234

npm

HN mentions (30d)

—

Open Issues

109

Rank Change

▼3

was #42

Analysis

HVTrust Dimensions vs Protocols & Tool Integration

85.7 / 100 · 100.0% confidence

MCP Apps Protocols & Tool Integration average (57 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits

19.8 / 25

11.2 above avg 8.6

Identity / Provenance60% listing status · 40% build provenance

18.0 / 18

6.3 above avg 11.7

Transparency50% declared license · 50% OSSF Scorecard

13.4 / 17

2.0 above avg 11.4

Maintenance60% last-push freshness · 40% commit activity

12.3 / 20

1.5 below avg 13.8

AdoptionLog-scaled stars · package downloads

16.5 / 20

6.1 above avg 10.4

Activity Inputs

64.6 / 100

StarsRepository reach

20.6 / 30

FreshnessLast push recency

22.4 / 25

ActivityRecent commits

9.7 / 25

CommunityFork signal

11.9 / 20

Supply Chain Trust

Package Provenance

Verified

npm attestation

OSSF Scorecard

5.8 / 10

OpenSSF Scorecard · scanned Aug 11, 2026

Signed Commits

100%

of last 100 commits verified

Binary-Artifacts 10

Branch-Protection 5

CI-Tests 9

CII-Best-Practices 0

Code-Review 4

Contributors 10

Dangerous-Workflow 10

Dependency-Update-Tool 10

Fuzzing 0

License 9

Maintained 10

Packaging 10

Pinned-Dependencies 3

SAST 6

Security-Policy 10

Signed-Releases 0

Token-Permissions 0

Vulnerabilities 0

Is MCP Apps safe?

Public supply-chain signals for MCP Apps are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but MCP Apps carries less obvious unverified-evidence risk than projects with thin signals.

Does MCP Apps publish package provenance?

Yes. MCP Apps's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.

Does MCP Apps have an OpenSSF Scorecard?

MCP Apps has an OpenSSF Scorecard score of 5.8/10. 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 MCP Apps actively maintained?

Maintained. Last push was 19 days ago.

What license does MCP Apps use?

MCP Apps ships under NOASSERTION. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

Are MCP Apps's commits signed?

100% of the last 100 commits to MCP Apps 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.

Compare MCP Apps head-to-head

MCP Apps vs MCP Inspector → MCP Apps vs A2A / Agent2Agent Protocol → MCP Apps vs FastMCP (TypeScript) →

AI agent surface

MCP, providers, tool surface

Scored in HVTrust

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

MCP Apps appears to expose MCP server capabilities.

Detailed evidence is not shown in the public view.

External Service Dependencies

medium confidence

1 detected

Public provider/service dependencies detected.

Anthropic

Credential signal: No explicit API-key/config marker detected.

Tool / Plugin Surface

high confidence

Declared

Declared plugin/integration surface detected.

Detailed evidence is not shown in the public view.

Package Provenance Drift

high confidence

Match

Published package metadata matches the tracked repo

Detailed evidence is not shown in the public view.

MCP signal live
External deps live
Tool / plugin surface live
Package provenance drift live

Maintain MCP Apps?

For maintainers

HVTrust scores MCP Apps 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.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history

2026-08-07

Scorecard Added

OSSF Scorecard: 5.8/10

2026-07-14

Newly Listed

First tracked at rank #80

GitHub → npm: @modelcontextprotocol/ext-apps

Embed Badge Badge guide for maintainers →

For maintainers

Markdown:
            [![HVTrust](https://hvtracker.net/badge/mcp-apps.svg)](https://hvtracker.net/agents/mcp-apps)
            
HTML:
            <a href="https://hvtracker.net/agents/mcp-apps"><img src="https://hvtracker.net/badge/mcp-apps.svg" alt="HVTrust"></a>

Other agents in Protocols & Tool Integration

Data sources
GitHub REST API (repo, commits, stars, forks, license) · npm Registry (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.3 · Raw JSON