llm-wiki-mcp

The materials explicitly state that no keys or environment variables are required, and there is no request for API tokens, account credentials, or other sensitive authentication data; based on the available facts, credential exposure and abuse risk appears low.

No remote endpoints are declared, and the materials do not list external APIs or third-party service destinations; based on the current facts, there is no explicit data egress path. However, the missing README prevents full verification of runtime network behavior.

The objective system checks show executes-code capability, meaning it can run code or processes on the local machine. This is a normal high-privilege capability for MCP tools and warrants caution; the current materials do not show requests for system permissions clearly beyond the stated function.

The description says it supports querying and ingesting wiki knowledge bases built from documents, so it likely accesses user-provided documents or knowledge-base data; however, the materials do not specify exact read/write scope, persistence behavior, or whether it can access paths outside the workspace, so the data access boundary is unclear and warrants caution.

A positive factor is the presence of a public open-source repository, which is in principle auditable; however, the source is a third-party registry, the license is undeclared, community adoption is 0 stars, maintenance status is unknown, and the README is essentially missing, limiting verifiability and supply-chain confidence. No explicit red flags justify a high-risk rating from the provided facts alone.