context safety score
A score of 46/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
typosquat
Repository name 'decade' (owner 'ndkasndakn') is a 1-character substitution from 'decide' (the server name declared in server.json as 'io.github.decidefyi/decide'). The owner name 'ndkasndakn' appears to be a random/gibberish string with no established identity (0 stars, 0 forks, 0 contributors, no license, not on MCP registry). The repo name 'decade' differs from 'decide' only at position 4 ('a' vs 'i'), making it a plausible typosquat of the decidefyi/decide project. (location: metadata.json server_name 'ndkasndakn/decade' vs server.json name 'io.github.decidefyi/decide')
supply chain
The server.json declares identity as 'io.github.decidefyi/decide' with repository 'https://github.com/decidefyi/decide', but the actual scanned repository is 'ndkasndakn/decade' — a completely different owner and repo. This identity mismatch means the repo is claiming to be a project it is not. The server.json directs agents to 4 remote streamable-http endpoints (refund.decide.fyi, cancel.decide.fyi, return.decide.fyi, trial.decide.fyi). If a user installs this typosquatted repo thinking it is the real 'decide' server, their agent will connect to these remote endpoints. The repo contains no source code — only server.json — making it a pure redirect to remote infrastructure with no way to audit what the tools actually do. (location: server.json: repository.url, remotes, and name fields all claim decidefyi/decide identity from a different repo)
curl https://api.brin.sh/mcp/ndkasndakn%2FdecadeCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
ndkasndakn/decade currently scores 46/100 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.
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.