Trust Agent shield iconTrust Agent
RolesAgentsSkillsHardwareEnterpriseSecurityDocsPricing
Browse roles Sign In
  • Roles
  • Dashboard
  • Saved
  • Creator
  • Profile

Trust Agent is the audited marketplace and trust layer for AI role agents, working agents, and specialist skills.

Audit-first. Provenance-aware. Enterprise-ready.

© 2026 Trust Agent · trust-agent.ai · info@trust-agent.ai

Product

RolesAgentsSkillsHardwareEnterprisePricing

Developers

API DocsQuickstartCreator GuideSDK

Company

AboutBlogContactCreator ProgrammeFoundationEnterpriseNHS and Public SectorPress

Legal

PrivacyTermsSecurityDPADownload

Agent detail

MCP Filesystem

MCP server for secure filesystem operations with sandboxed read/write access.

Audit-first trust modelProvenance awareEnterprise policy controls
VerifiedPassedLow Risk91ScoreEnterprise SafeSource VerifiedSecurity FailedScanned 29 Mar 2026

Description

What this agent does and how it is scoped.

MCP server for secure filesystem operations with sandboxed read/write access. Published and verified by TrustAgent.

audit-firstenterprise-readyfilesystemmcporchestrationsandboxedtrustagent-published

Trust Snapshot

Trust badges

Granular trust badges with evidence-driven status.

Manual Review PassedPublisher VerifiedEnterprise SafeBehavior VerifiedSandbox TestedPermission MatchedDependency Clean

Provenance

Source type

GITHUB

Publisher

TrustAgent

Source license

MIT

Commit hash

f4a8b2c6d0e5f9a3b7c1d5e9f3a7b1c5d9e3f7a1

Version hash

254fb1197783558c0552730ae2a26a4e176a4e91c5345470d7e42df33d32ad90

Audit Evidence

Version History

Hash-locked versions, source metadata, and drift context.

VersionCommitHashSourceCreated
1.0.0f4a8b2c6d0e5f9a3b7c1d5e9f3a7b1c5d9e3f7a1254fb1197783558cTrustAgent3/29/2026, 8:33:56 PM

Reviews

Brianna BuyerVerified install

Great trust signals and clear audit evidence.

91
Trust Score

Verification status

VERIFIED

Install count

3240

Risk tier

LOW

Publisher

TrustAgent

Audited and published by the TrustAgent platform.

Public trust report

MCP Filesystem completed the Trust Agent automated review pipeline for agent listings. Stage 1 configuration integrity scored 84/100 and stage 2 behaviour testing scored 85/100. The companion security scan produced 87/100 with outcome PASSED. Overall trust score: 87/100. Primary analyst watchpoints: Process execution appears under-declared, Network behavior lacks explicit egress guardrails. This public narrative excludes prompts, code, and protected configuration while preserving the buyer-facing trust rationale.

Security Scanned
Manifest Verified
Hash Locked
Source Verified

Latest trust score 87 with decision PASSED.

Open legacy reportOpen public audit reportView security report