Home / MCP registry index / com.rubrkit/rubrkit
com.rubrkit/rubrkit
com.rubrkit/rubrkit in the official MCP registry.
Endpoint https://www.rubrkit.com/api/v1/mcp. Source: github.com/liberat0r/react-rubrkit.
The registry describes it as: MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
We read its 41 tools on 2026-10-28. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
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 rubrkit_list_golden_cases rubrkit_add_golden_case rubrkit_retire_golden_case rubrkit_create_drift_monitor rubrkit_list_drift_monitors rubrkit_read_drift_observations rubrkit_run_drift_check rubrkit_set_drift_monitor_status rubrkit_record_outcome rubrkit_read_input_drift rubrkit_read_validity_drift
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/com-rubrkit-rubrkit)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.
Related
| Citiview Agent Market com.citiviewgroup.mcp/agent-market | 200 tools, nothing matched 2026-10-26 |
| Huggingface io.github.pipeworx-io/huggingface | 54 tools, nothing matched 2026-10-27 |
| io.github.DarthSander/agentdata-nl io.github.DarthSander/agentdata-nl | 53 tools, nothing matched 2026-10-22 |
| Gemini Crypto io.github.pipeworx-io/gemini-crypto | 52 tools, nothing matched 2026-10-27 |
| Rankwise com.tryrankwise/rankwise | 49 tools, nothing matched 2026-10-26 |
| Tensorust com.tensorust/mcp | 46 tools, nothing matched 2026-10-27 |