MindsHub
The unified workspace where open-source models get things done for you.
Is MindsHub safe? Promising trust profile, but some evidence still deserves review. 4 published advisories affect its latest release.
Compare MindsHub
How does it stack up against its MCP Servers neighbours?
Pick any agent to compare →In detail: MindsHub scores 63.0/100 (Grade C), ranked #576 of 1371 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 7.1/10; 57% of recent commits are signed; 4 published advisories affect its latest release (mindsdb); last pushed 2026-09-16. Every point is earned from checkable signals — never paid placement. How scoring works →
Known advisories
Published advisories (from OSV) that affect the release you'd install today: mindsdb 26.1.0. An unfixed critical advisory caps the HVTrust score at 64.9 (Grade C) and a high one at 79.9 (Grade B), until a fixed release ships; moderate, low and unrated ones are shown, not scored. Checked 2026-10-10.
- UNRATED Deserialization of untrusted data can occur in versions 23.3.2.0 and newer of the MindsDB platform, enabling a maliciously uploaded model to run arbitrary code on the server when interacted with.
- UNRATED Deserialization of untrusted data can occur in versions 23.10.2.0 and newer of the MindsDB platform, enabling a maliciously uploaded ‘inhouse’ model to run arbitrary code on the server when used for a
- UNRATED Deserialization of untrusted data can occur in versions 23.10.3.0 and newer of the MindsDB platform, enabling a maliciously uploaded ‘inhouse’ model to run arbitrary code on the server when a ‘describ
- UNRATED Deserialization of untrusted data can occur in versions 23.10.2.0 and newer of the MindsDB platform, enabling a maliciously uploaded ‘inhouse’ model to run arbitrary code on the server when using ‘fin
How MindsHub could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Publish build provenance for its packagesPyPI Trusted Publishing attestations +14.7 → 77.7 B · #105 of 781
- Raise the OSSF Scorecard from 7.1 to 9.0lowest checks: CII-Best-Practices 0, Fuzzing 0, Pinned-Dependencies 0 +4.0 → 67.0 B · #255 of 781
- Sign every commit57% signed today +2.2 → 65.2 B · #275 of 781
Chain of custody
Scanners check what the code says. This traces who ships MindsHub and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Partly signed
github.com/mindsdb/mindshub, MIT, last pushed 2026-09-16. 57% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Strong
OpenSSF Scorecard rates the repository's practices 7.1/10 (scanned Oct 10, 2026). The checks that decide who can get a change released:
- Code Review4
- Branch Protection5
- Signed Releasesn/a
- Dangerous Workflow10
- Token Permissions10
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 5CI-Tests 9CII-Best-Practices 0Code-Review 4Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 10Fuzzing 0License 10Maintained 3Packaging -1Pinned-Dependencies 0SAST 9Security-Policy 10Signed-Releases -1Token-Permissions 10Vulnerabilities 10 -
Published packages Not linked
- PyPI mindsdb Source link points to mindsdb/mindsdb, same owner No build attestation
Without a build attestation, nothing proves the published files were built from this repository.
-
What you install today 4 advisories
Latest release checked: mindsdb 26.1.0. 4 published advisories affect it (OSV, checked 2026-10-10).
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of MindsHub.
Evidence behind this score
Coverage B: 3 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions (missing)
Verify this score yourself
Every build re-issues MindsHub’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.
What this score doesn’t check
It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.
How MindsHub compares in MCP Servers
- #316 Galaxy MCP 63.2 +0.2
- #317 Prometheus MCP 63.1 +0.1
- #318 MindsHub 63.0 this agent
- #319 Cli Microsoft365 MCP Server 63.0 ±0
- #320 Webhook MCP Server 63.0 ±0
Bars show each HVTrust score; the tick marks MindsHub’s 63.0.
Where the 63.0 comes from
HVTrust dimensions vs the MCP Servers average
63.0 / 100 · 100.0% confidenceMindsHub MCP Servers average (781 agents)
Quick Trust Read
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 →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
66.9 / 100Common questions about MindsHub
Does MindsHub publish package provenance?
Does MindsHub have an OpenSSF Scorecard?
Is MindsHub actively maintained?
What license does MindsHub use?
Are MindsHub's commits signed?
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.
AI agent surface
MCP, providers, tool surface
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 signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Maintain MindsHub?
For maintainers
HVTrust scores MindsHub 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.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/mindshub)
<a href="https://hvtracker.net/agents/mindshub"><img src="https://hvtracker.net/badge/mindshub.svg" alt="HVTrust"></a>
Other agents in MCP Servers
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON