World Model MCP
world-model-mcp is a signed audit memory server for AI coding agents, delivered as an MCP tool. Every event Ed25519-signed and Merkle-chained; offline-verifiable against pinned public keys. Hosted platform with hybrid post-quantum signing at etch.systems.
Is World Model MCP safe? Promising trust profile, but some evidence still deserves review.
Compare World Model MCP
How does it stack up against its MCP Servers neighbours?
Pick any agent to compare →In detail: World Model MCP scores 62.6/100 (Grade C), ranked #626 of 1374 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 4.3/10; 99% of recent commits are signed; no published advisory affects its latest release (world-model-mcp); last pushed 2026-09-15. Every point is earned from checkable signals — never paid placement. How scoring works →
How World Model MCP 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.
- Raise the OSSF Scorecard from 4.3 to 9.0lowest checks: Branch-Protection 0, CII-Best-Practices 0, Code-Review 0 +9.8 → 72.4 B · #192 of 778
Chain of custody
Scanners check what the code says. This traces who ships World Model MCP 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 Signed
github.com/SaravananJaichandar/world-model-mcp, MIT, last pushed 2026-09-15. 99% of the last 100 commits carry a verified signature, so changes trace to a verified account.
-
Review and release Mixed
OpenSSF Scorecard rates the repository's practices 4.3/10 (scanned Nov 4, 2026). The checks that decide who can get a change released:
- Code Review0
- Branch Protection0
- Signed Releasesn/a
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 0CI-Tests -1CII-Best-Practices 0Code-Review 0Contributors 0Dangerous-Workflow 10Dependency-Update-Tool 0Fuzzing 10License 10Maintained 4Packaging 10Pinned-Dependencies 0SAST 0Security-Policy 0Signed-Releases -1Token-Permissions 0Vulnerabilities 10 -
Published packages Partly attested
- PyPI world-model-mcp Source link isn't a GitHub repo Build provenance attested
-
What you install today No known advisories
Latest release checked: world-model-mcp 0.16.3. No published advisory affects it (OSV, checked 2026-11-09).
Changes to this chain
- 2026-09-23 Package provenance attestation detected
- 2026-08-29 OSSF Scorecard: 4.7/10
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 World Model MCP’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 World Model MCP compares in MCP Servers
- #342 Studio MCP 62.6 ±0
- #343 Chat on Steroids 62.6 ±0
- #344 World Model MCP 62.6 this agent
- #345 MCP Server For ISO27001 62.6 ±0
- #346 MCP Uptime Kuma 62.5 −0.1
Bars show each HVTrust score; the tick marks World Model MCP’s 62.6.
Where the 62.6 comes from
HVTrust dimensions vs the MCP Servers average
62.6 / 100 · 100.0% confidenceWorld Model MCP MCP Servers average (778 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
29.1 / 100Common questions about World Model MCP
Does World Model MCP publish package provenance?
Does World Model MCP have an OpenSSF Scorecard?
Is World Model MCP actively maintained?
What license does World Model MCP use?
Are World Model MCP'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
Detected changes to World Model 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.
Maintain World Model MCP?
For maintainers
HVTrust scores World Model 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.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/world-model-mcp)
<a href="https://hvtracker.net/agents/world-model-mcp"><img src="https://hvtracker.net/badge/world-model-mcp.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