mcpwatch

← All servers

Grade B

com.rubrkit/rubrkit

com.rubrkit/rubrkit · v1.0.0 · 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

MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.

Source: https://github.com/liberat0r/react-rubrkit

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 41 tool(s) to anyone, no credentials needed.
MediumMW1023 tool(s) can execute commands or delete data (rubrkit_delete_artifact_bundle, rubrkit_hard_delete_artifact_bundle, rubrkit_read_eval). Require confirmation before the agent calls them.

What was checked

Public tools: rubrkit_search_api_docs, rubrkit_read_api_doc, rubrkit_read_openapi_contract, rubrkit_create_artifact_bundle, rubrkit_list_artifact_bundles, rubrkit_read_artifact_bundle, rubrkit_delete_artifact_bundle, rubrkit_hard_delete_artifact_bundle, rubrkit_upload_artifact_files, rubrkit_list_artifact_files, rubrkit_read_artifact_file, rubrkit_update_artifact_file, rubrkit_compact_artifact_file, rubrkit_estimate_deep_compaction, rubrkit_apply_deep_compaction, rubrkit_start_audit, rubrkit_list_audits, rubrkit_read_audit, rubrkit_apply_audit_rewrite, rubrkit_poll_job, rubrkit_list_job_events, rubrkit_list_artifact_bundle_versions, rubrkit_restore_artifact_bundle_version, rubrkit_list_file_versions, rubrkit_restore_file_version, rubrkit_run_evals, rubrkit_list_evals, rubrkit_read_eval, rubrkit_export_proof_report, rubrkit_read_proof_report

Maintainer? Add the badge

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

[![mcpwatch](https://www.mcpwatch.io/badge/com-rubrkit-rubrkit-f47f00ec.svg)](https://www.mcpwatch.io/s/com-rubrkit-rubrkit-f47f00ec)