io.github.CSOAI-ORG/blockchain-ai-mcp

The material explicitly states that no keys or environment variables are required. There is no evidence that it needs API tokens, account credentials, or other sensitive authentication data, so credential leakage and abuse exposure appears low.

No remote host endpoints are declared, and the material does not describe any external API usage, telemetry, or data upload behavior. Based on the available facts, there is no clear user-data egress path.

The system flags this tool with executes-code, indicating that it runs locally as an MCP service and executes code. This is a normal capability for this class of tool and does not by itself justify a high-risk rating, but it should still be run in a constrained environment with attention to what system capabilities it actually invokes.

No README or permission details are provided, so it is unclear what local files, directories, or other resources it may read or write. As a locally running MCP tool, it may have potential access to local data, but there is no specific evidence of over-privileged access beyond its stated role.

Positive signals include listing in an official registry, an available open-source repository, and updates within the last year, all of which materially reduce supply-chain risk. However, the missing README, undeclared license, and zero-star community adoption limit auditability and maturity evidence, so a cautious rather than high-risk rating is appropriate.