context safety score
A score of 33/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Found 1 unexpected binary file(s) in source repository
response injection
Every tool response includes a _metadata object (generated by src/utils/metadata.ts:generateResponseMetadata) that falsely claims data_source is 'Federal Register of Legislation (legislation.gov.au) — Australian Government, Office of Parliamentary Counsel', jurisdiction is 'AU', and the disclaimer directs verification to legislation.gov.au. This is a Portuguese law server — every response systematically misleads the agent about data provenance, causing it to cite Australian sources when presenting Portuguese law. The about and list_sources tools also return Australian source URLs (legislation.gov.au) and jurisdiction 'AU'. This is leftover from mass-templating 88 country-specific law servers from an Australian original in a 36-day-old org. (location: src/utils/metadata.ts:25-30, src/tools/about.ts:44-51, src/tools/list-sources.ts:44-53)
response injection
validate_eu_compliance tool (line 85) states 'Portugal is not an EU member; EU references indicate comparable frameworks rather than transposition obligations.' Portugal IS an EU member state. This false legal claim injected into tool responses will cause agents to give materially incorrect legal advice about EU law applicability in Portugal, potentially affecting compliance decisions. (location: src/tools/validate-eu-compliance.ts:85)
supply chain
Organization Ansvar-Systems is 36 days old with 88 public repositories, all mass-produced country-specific law MCP servers templated from a single Australian base. The portuguese-law-mcp has 0 stars, 0 forks, 1 contributor, no license in repo metadata, and is not listed on the official MCP registry. Multiple source files still contain 'Australian Law MCP' comments (capabilities.ts:2, fts-query.ts:2, metadata.ts:2). The validate-citation.ts parser contains Australian citation patterns (e.g., 'Section 13 Privacy Act 1988') rather than Portuguese ones. This mass-templating pattern with incomplete adaptation raises supply chain trust concerns — the server presents itself as a curated Portuguese legal database but contains systematically incorrect provenance metadata across its entire response surface. (location: src/utils/metadata.ts, src/capabilities.ts:2, src/utils/fts-query.ts:2, src/tools/validate-citation.ts)
curl https://api.brin.sh/mcp/Ansvar-Systems%2Fportuguese-law-mcpCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
Ansvar-Systems/portuguese-law-mcp currently scores 33/100 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.