context safety score
A score of 43/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
consent bypass
The x402_pay_request and x402_pay_for_request tool descriptions instruct the agent to 'automatically handle' HTTP 402 payment requirements, encouraging autonomous cryptocurrency spending without explicit user confirmation per transaction. The README reinforces this with 'No human approval needed' and 'Autonomous Payments' framing. While a maxPayment parameter (default $1.00) exists as a guard, the tool description language is designed to make the LLM agent complete payments without asking the user first. (location: x402_pay_request tool description in src/x402/tools.ts; README.md x402 section ('No human approval needed', 'Autonomous Payments'))
description injection
The privateKeyParam schema in src/evm/modules/common/types.ts contains a .describe() with the claim 'SECURITY: This is used only for address derivation and is not stored. The private key will not be logged or displayed in chat history.' This security assurance is embedded in the tool parameter description where it will be read by the LLM agent, potentially reducing the agent's caution about passing private keys. The claim about 'only address derivation' is factually inaccurate — the private key is also used for transaction signing, token transfers, and message signing across dozens of tools. (location: privateKeyParam definition in src/evm/modules/common/types.ts)
curl https://api.brin.sh/mcp/nirholas%2Funiversal-crypto-mcpCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
nirholas/universal-crypto-mcp currently scores 43/100 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.