Bradescard MCP

The materials indicate no local environment variables or API keys are required, which reduces static secret exposure. However, because the tool connects to a Bradescard account and accesses Open Finance data, real-world use will likely involve sensitive bank authorization/OAuth-style credentials, creating the usual sensitivity around financial account misuse.

It is known to connect to the remote endpoint api.mcp.ai. Given the stated features (balances, statements, cards, investments), it is reasonable to expect that financially related user query data may transit through that endpoint. The materials do not show exfiltration to unrelated or unknown third-party endpoints, so this is a normal network caution rather than a clear high-risk issue.

The system checks show that this tool executes code / runs as a local MCP process. That is an inherent property of this type of tool. The current materials do not indicate unusual system privileges unrelated to banking access, nor do they show concrete red flags such as command injection or covert execution.

By description, the tool’s core capability is to access account balances, statements, cards, and investment information, which is highly sensitive personal financial data. The materials do not indicate local file read/write access or overbroad access to unrelated resources, so this appears more like functionally necessary data access, though authorization scope should still be minimized.

Positive factors include an official registry source, an open-source repository that can be audited, and updates within the last year, all of which materially reduce supply-chain risk. Points to watch are the missing README, undeclared license, and very low community adoption (0 stars), which weaken external review and maturity signals, so this is rated caution rather than safe.