MCP For Claude Marketplace
Filesystem Sandbox Boundary Enforcer

Filesystem Sandbox Boundary Enforcer MCP Connector for Claude

A+

Enforces strict path boundaries and prevents traversal attacks.

3 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

This MCP server provides a security engine to prevent path traversal and unauthorized file system access. It uses deterministic string manipulation to resolve paths, expanding .. segments and removing redundant slashes. Use validate_path_access to check if a requested path is permitted within your allowed roots, or use preview_path_expansion to see how a complex path will be normalized before validation.

sandboxpath-traversalsecurity-enforcementpath-normalizationaccess-control

3 tools expose this connector's capabilities to your AI agent.

validate_path_access

Returns permission status, resolved path, and violation reason if denied. Determines if a specific file system request is safe and permitted under current security policies

analyze_root_integrity

Audits a list of potentially allowed directories to ensure the configuration itself does not contain forbidden zones

preview_path_expansion

segments and redundant slashes in the input path. Demonstrates how a messy or complex path will be cleaned and resolved before any permission checks are applied

See how to talk to your AI agent using Filesystem Sandbox Boundary Enforcer.

Is the path '/var/www/html/../etc/passwd' allowed if my root is '/var/www/html'?

No, the resolved path is `/etc/passwd`, which triggers a blocklist violation.

Show me how the path '///home//user/./docs/../config' will look after expansion.

/home/user/config

Check if '/mnt/data' is a safe root directory.

The directory `/mnt/data` is safe and does not match any forbidden patterns in the blocklist.

The server resolves all `..` segments and redundant slashes using deterministic string manipulation before checking if the resulting path starts with an allowed root or matches a forbidden blocklist.

Related Connectors

claude-task-completion-verifier

claude-task-completion-verifier MCP

3 tools Official

A deterministic verification engine that validates task fulfillment by checking files, content, and command execution.

A+ View details →
Compliance Governance Prover

Compliance Governance Prover MCP

1 tools Official

An AI said 'comply with GDPR' without naming a single article. It said 'we have controls' without mapping any to a regulation. It said 'low risk' without measuring severity or fine exposure. The auditor found 4 critical gaps. That is not compliance — that is compliance theater. This tool forces five audit-grade axes: specific regulation naming, control mapping, evidence documentation, gap quantification, and named accountability.

A+ View details →
Guardrail Violation Detector

Guardrail Violation Detector MCP

3 tools Official

Analyzes AI agent outputs for safety and compliance violations.

A+ View details →
Dependency Resolution Engine

Dependency Resolution Engine MCP

3 tools Official

Deterministic dependency resolution for agent tool and plugin loading.

A+ View details →