LeashIndex Get the report

Index / devtools

RCA-MCP

io-github-dave1362-rca-mcp-connector declares 56 capabilities across 56 tools, with 2 critical issues.

96/100 exposureHigh exposure

Manifest recorded 2026-10-15 from tools/list answered by the PyPI package rca-mcp-connector==4.1.20 (published to PyPI as rca-mcp-connector, listed in the official MCP registry as io.github.dave1362/rca-mcp-connector 4.1.20), run in an isolated container with no network access and placeholder credentials. The date changes only when the manifest does. Not verified by a maintainer.

Issues

These describe what this server's manifest declares. A product can provide controls that MCP has no way to express — token revocation, an admin console, audit logs — and this page cannot see them. The absence of a declaration is not evidence that a control is absent.

critical · no-revocation · All 56 tools

56 of 56 tools declare no way for the customer to switch them off once granted. This applies to every tool because MCP has no field in which to declare a revocation mechanism; the product may provide one outside MCP that a manifest cannot show.

critical · irreversible-uncapped · 9 of 56 tools

9 tools are classified as irreversible and declare no limit.

high · no-expiry · All 56 tools

56 of 56 tools declare no expiry. This applies to every tool because MCP has no field in which to declare an expiry; the product may provide one outside MCP that a manifest cannot show.

high · no-audit-trail · All 56 tools

56 of 56 tools declare no record of their actions that the customer can read. This applies to every tool because MCP has no field in which to declare an audit requirement; the product may provide one outside MCP that a manifest cannot show.

high · uncapped-write · 17 of 56 tools

17 tools can modify data and declare no limit.

low · uncapped-read · 30 of 56 tools

30 tools can read data and declare no limit.

Declared capabilities

How each tool was read. declared means the server's own annotation said so — self-reported and unverified. inferred is from the tool's name. assumed means nothing indicated either way.

ToolRead asBasis
rca_auth_generate_tokenwrite assumed
rca_auth_list_keysread declared
rca_auth_rotate_keydestructive declared
rca_auth_revoke_tokendestructive declared
rca_admin_healthread declared
rca_admin_read_audit_logread declared
rca_admin_purge_namespacedestructive declared
rca_graph_createwrite inferred
rca_graph_getread declared
rca_graph_scoreread declared
rca_graph_discoverwrite assumed
rca_graph_deletedestructive declared
rca_graph_list_versionsread declared
rca_graph_restore_versiondestructive declared
rca_graph_mergewrite inferred
rca_graph_add_nodewrite inferred
rca_graph_remove_nodedestructive declared
rca_graph_add_edgewrite inferred
rca_graph_remove_edgedestructive declared
rca_graph_score_pathsread declared
rca_graph_markov_blanketread declared
rca_model_createwrite inferred
rca_model_listread declared
rca_model_update_statusread inferred
rca_model_validateread inferred
rca_model_deletedestructive declared
rca_analysis_runwrite assumed
rca_analysis_get_resultread declared
rca_analysis_list_resultsread declared
rca_analysis_query_resultsread declared
rca_analysis_compareread declared
rca_analysis_explainread declared
rca_analysis_batchwrite assumed
rca_analysis_ensemblewrite assumed
rca_pyrca_epsilon_diagnosisread declared
rca_pyrca_random_walkread declared
rca_pyrca_ht_diagnosisread declared
rca_report_generatewrite assumed
rca_report_compareread inferred
rca_provider_list_configsread declared
rca_pyrca_validate_setupread declared
rca_analysis_run_asyncwrite assumed
rca_analysis_poll_taskread declared
rca_admin_show_plan_inforead declared
rca_guide_ingestwrite assumed
rca_guide_searchread declared
rca_guide_getread declared
rca_guide_listread declared
rca_guide_deletedestructive declared
rca_dtree_startwrite assumed
rca_dtree_answerwrite assumed
rca_dtree_list_sessionsread declared
rca_guide_generate_reportread declared
rca_dtree_generate_from_fmeawrite assumed
rca_guide_pdf_previewread declared
rca_guide_ingest_pdfwrite assumed
Answering this question about your own agent? The self-serve stack report applies the same reading to your own stack or server and gives you a dated document you can hand to a customer's security review. It is generated in your browser, with nobody to wait for. Buying one does not change this page, its score or its place in the index — see Independence.
Maintain this server? If this page misreads your manifest, or your server has changed, submit its current tools/list response and it will be re-scored and dated. Corrections are published alongside the original, not in place of it.