mcpwatch

← All servers

Grade B

SilvaLabs

io.github.opensylva/silvalabs · v1.0.1 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Personal knowledge base MCP: agents read only materials you open.

Source: https://gitlab.com/silvalabs-project/silvalabs-knowledge

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 17 tool(s) to anyone, no credentials needed.
MediumMW1021 tool(s) can execute commands or delete data (delete_doc). Require confirmation before the agent calls them.

What was checked

Public tools: list_collections, get_index, get_workset, get_doc, create_doc, update_agent_md, update_doc_body, delete_doc, get_doc_section, search_docs, get_procedure, view_step, take_step, resume_step, complete_step, block_step, await_human

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/io-github-opensylva-silvalabs-e78d785b.svg)](https://www.mcpwatch.io/s/io-github-opensylva-silvalabs-e78d785b)