@modelcontextprotocol/servers Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

@modelcontextprotocol/servers is an AI agent skill, created by Model Context Protocol a Series of LF Projects, LLC. and published at modelcontextprotocol/servers. ClawSecure audited @modelcontextprotocol/servers across 73 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 50/100 (Medium Risk). The 8 findings concentrate in Supply Chain, Permissions Manifest and ReDoS, including Vulnerability in @modelcontextprotocol/server-filesystem@*:… and Vulnerability in @modelcontextprotocol/server-filesystem@*:…. 2 were rated high or critical severity.

Is @modelcontextprotocol/servers safe?

ClawSecure audited @modelcontextprotocol/servers and assigned a security score of 50/100 (Medium Risk), identifying 8 findings across Supply Chain and Permissions Manifest. Review the findings below before installing.

What did ClawSecure find in @modelcontextprotocol/servers?

ClawSecure identified 8 findings in @modelcontextprotocol/servers, concentrated in Supply Chain, Permissions Manifest and ReDoS. 2 were rated high or critical severity. The most severe include Vulnerability in @modelcontextprotocol/server-filesystem@*:… and Vulnerability in @modelcontextprotocol/server-filesystem@*:….

How was @modelcontextprotocol/servers audited?

ClawSecure ran @modelcontextprotocol/servers through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 73 files from modelcontextprotocol/servers.

What does a score of 50 mean?

ClawSecure assigned @modelcontextprotocol/servers a security score of 50/100, placing it in the Medium Risk range. This reflects 8 findings led by Supply Chain that warrant review before production use. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).

Audit Findings for @modelcontextprotocol/servers

ClawSecure detected 8 security findings in @modelcontextprotocol/servers, spanning Supply Chain, Permissions Manifest and ReDoS.

high · Vulnerability in @modelcontextprotocol/server-filesystem@*:…. Supply Chain finding detected in package.json.
high · Vulnerability in @modelcontextprotocol/server-filesystem@*:…. Supply Chain finding detected in package.json.
medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
medium · ReDoS vulnerability: Nested quantifiers (potential…. ReDoS finding detected in ADDITIONAL.md:51.
medium · Unpinned dependency:…. Supply Chain finding detected in package.json.
medium · Unpinned dependency: @modelcontextprotocol/server-memory…. Supply Chain finding detected in package.json.
medium · Unpinned dependency:…. Supply Chain finding detected in package.json.
medium · Unpinned dependency:…. Supply Chain finding detected in package.json.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for @modelcontextprotocol/servers

Update and pin dependencies

@modelcontextprotocol/servers depends on packages with supply-chain risk. Pin every dependency to an exact version, update packages with known CVEs to patched releases, and re-audit after each change. ClawSecure checks every dependency against known CVE databases.

Add a config.json permissions manifest

A config.json file declares what an agent component can access: file system, network, shell execution and more. Without it, users have no visibility into what the component can do before installing. This is the single most impactful security improvement for any AI agent skill.

Fix ReDoS-prone patterns

@modelcontextprotocol/servers contains regular expressions vulnerable to catastrophic backtracking (ReDoS). Replace vulnerable patterns, bound input length, and prefer linear-time matching so a crafted input cannot hang the agent.

Related Security Research

AI Agent Supply Chain Attacks: How Dependencies Become Weapons→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→

Related AI Agent Security Audits

gitlab-cli-skillsScore 55/100 xlsxScore 63/100 skill-creatorScore 65/100 skill-creatorScore 65/100 nginx-analyzeScore 60/100

Scanned on July 30, 2026. @modelcontextprotocol/servers is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.

Start Your Free Scan