Is MCPower-Security/mcpower-proxy safe?

suspiciousmedium confidence
48/100

context safety score

A score of 48/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.

identity
45
behavior
75
content
40
graph
60

4 threat patterns detected

high

doc injection

Repository MCPower-Security/mcpower-proxy presents itself entirely as 'Defenter' by 'Defenter-AI' throughout the README, including VS Code marketplace links to defenter.defenter-vsc and an HTML comment declaring MCP name io.github.Defenter-AI/defenter-proxy. The actual repo owner (MCPower-Security) is a different, unverified organization with only 3 stars and unknown account age. This is not a fork (fork:false, parent:null). The README impersonates another project/organization's identity, which could mislead AI agents and users into trusting this repo as the official Defenter project. (location: README.md:1-80)

medium

doc injection

HTML comment on the last line declares MCP registry metadata '<!-- mcp-name: io.github.Defenter-AI/defenter-proxy -->' referencing a GitHub org (Defenter-AI) that differs from the actual repo owner (MCPower-Security). This metadata tag could be used to register this repository in MCP registries under the Defenter-AI namespace, effectively squatting on or hijacking another organization's MCP identity. (location: README.md:80)

medium

typosquat

Repository is named 'MCPower-Security/mcpower-proxy' but server.json internally declares itself as 'io.github.Defenter-AI/defenter-proxy' pointing to a completely different GitHub organization (Defenter-AI). This identity mismatch between the repository name and the declared server identity is suspicious — the repo presents itself under one name/org while the actual package and configuration reference a different entity. Users installing from the MCPower-Security repo may not realize they are running Defenter-AI's package. The 'MCPower' name itself leverages the 'MCP' acronym to appear authoritative in the MCP ecosystem. (location: server.json (name, homepage, repository fields) vs metadata.json (full_name: MCPower-Security/mcpower-proxy))

high

cross server attack

The server is architecturally designed as a man-in-the-middle proxy that intercepts ALL MCP communication between an AI agent and its downstream tools. The instructions in server.json explicitly state it will 'Intercept all MCP communication' and perform 'cloud analysis' — meaning all tool calls, tool responses, and any sensitive data flowing through MCP (including code, credentials in context, system prompts, and user conversations) are captured and sent to an external cloud service (defenter.ai). Combined with very low trust signals (3 stars, unverified org, not on MCP registry, unknown account age), this represents a significant data exfiltration risk. A user wrapping their MCP servers with this proxy grants it full visibility into every interaction. (location: server.json instructions field: '--wrapped-config' pattern and description 'Redact secrets/PII locally before cloud analysis')

API

curl https://api.brin.sh/mcp/MCPower-Security%2Fmcpower-proxy

FAQ: how to interpret this assessment

Common questions teams ask before deciding whether to use this mcp server in agent workflows.

Is MCPower-Security/mcpower-proxy safe for AI agents to use?

MCPower-Security/mcpower-proxy currently scores 48/100 with a suspicious verdict and medium confidence. The goal is to protect agents from high-risk context before they act on it. Treat this as a decision signal: higher scores suggest lower observed risk, while lower scores mean you should add review or block this mcp server.

How should I interpret the score and verdict?

Use the score as a policy threshold: 80–100 is safe, 50–79 is caution, 20–49 is suspicious, and 0–19 is dangerous. Teams often auto-allow safe, require human review for caution/suspicious, and block dangerous.

How does brin compute this mcp server score?

brin evaluates four dimensions: identity (source trust), behavior (runtime patterns), content (malicious instructions), and graph (relationship risk). Analysis runs in tiers: static signals, deterministic pattern checks, then AI semantic analysis when needed.

What do identity, behavior, content, and graph mean for this mcp server?

Identity checks source trust, behavior checks unusual runtime patterns, content checks for malicious instructions, and graph checks risky relationships to other entities. Looking at sub-scores helps you understand why an entity passed or failed.

Why does brin scan packages, repos, skills, MCP servers, pages, and commits?

brin performs risk assessments on external context before it reaches an AI agent. It scores that context for threats like prompt injection, hijacking, credential harvesting, and supply chain attacks, so teams can decide whether to block, review, or proceed safely.

Can I rely on a safe verdict as a full security guarantee?

No. A safe verdict means no significant risk signals were detected in this scan. It is not a formal guarantee; assessments are automated and point-in-time, so combine scores with your own controls and periodic re-checks.

When should I re-check before using an entity?

Re-check before high-impact actions such as installs, upgrades, connecting MCP servers, executing remote code, or granting secrets. Use the API in CI or runtime gates so decisions are based on the latest scan.

Learn more in threat detection docs, how scoring works, and the API overview.

Last Scanned

February 27, 2026

Verdict Scale

safe80–100
caution50–79
suspicious20–49
dangerous0–19

Disclaimer

Assessments are automated and may contain errors. Findings are risk indicators, not confirmed threats. This is a point-in-time assessment; security posture can change.

start scoring agent dependencies.

integrate brin in minutes — one GET request is all it takes. query the api, browse the registry, or download the full dataset.