context safety score
A score of 23/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 1 secret pattern match(es) in repository files
supply chain
Found 3 install-script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 3 remote script pattern(s) in documentation (likely install instructions, not executable)
typosquat
Repository 'crypto-ninja/mcp-server-for-Github' closely mimics the official 'github/github-mcp-server' by GitHub. README title is simply '# GitHub MCP Server' (identical to the official project), and MCP registry name is 'io.github.crypto-ninja/github-mcp-server'. With only 4 stars, no license file, unverified personal account, this appears designed to be confused with the official GitHub MCP server. The README also displays a fake AGPL v3 license badge despite no license file existing in the repo. (location: README.md (title, line 1; MCP name metadata, lines 3 and 1223; fake license badge, line 5))
typosquat
This server 'crypto-ninja/mcp-server-for-Github' impersonates the official GitHub MCP server (github/github-mcp-server). It has 0 stars, 0 contributors, no license, is not on the MCP registry, has an unknown-age owner account, and publishes to PyPI under the identifier 'github-mcp-server' — the same name as the official package. The description '112 tools, 98% token reduction, compact responses' closely mirrors the official server's marketing. This has all hallmarks of a supply-chain impersonation attack targeting users searching for the official GitHub MCP server. (location: server.json (name, description, packages[0].identifier))
supply chain
The PyPI package identifier is 'github-mcp-server' (server.json packages[0].identifier), which directly squats on or conflicts with the official GitHub MCP server's package name. Users running 'pip install github-mcp-server' could receive this impersonation package instead of the official one, enabling arbitrary code execution via stdio transport on the user's machine. (location: server.json:14 (packages[0].identifier: 'github-mcp-server'))
curl https://api.brin.sh/mcp/crypto-ninja%2Fmcp-server-for-GithubCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
crypto-ninja/mcp-server-for-Github currently scores 23/100 with a suspicious verdict and low 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.
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.
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.
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.
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.
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.
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.
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.
integrate brin in minutes — one GET request is all it takes. query the api, browse the registry, or download the full dataset.