LeashIndex Get the report

Index / data

MCP Gemini

io-github-crunchtools-gemini declares 39 capabilities across 39 tools, with 2 critical issues.

84/100 exposureHigh exposure

Manifest recorded 2026-10-15 from tools/list answered by the PyPI package mcp-gemini-crunchtools==0.3.0 (published to PyPI as mcp-gemini-crunchtools, listed in the official MCP registry as io.github.crunchtools/gemini 0.3.0), run in an isolated container with no network access and no 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 39 tools

39 of 39 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 · 1 of 39 tools

1 tool is classified as irreversible and declares no limit.

high · no-expiry · All 39 tools

39 of 39 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 39 tools

39 of 39 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 · 21 of 39 tools

21 tools can modify data and declare no limit.

low · uncapped-read · 17 of 39 tools

17 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
gemini_query_toolread inferred
gemini_brainstorm_toolwrite assumed
gemini_analyze_code_toolread inferred
gemini_analyze_text_toolread inferred
gemini_summarize_toolwrite assumed
gemini_generate_image_toolwrite assumed
gemini_generate_image_with_input_toolwrite inferred
gemini_image_prompt_toolwrite assumed
gemini_imagen_generate_toolwrite assumed
gemini_start_image_edit_toolwrite inferred
gemini_continue_image_edit_toolwrite inferred
gemini_end_image_edit_toolwrite inferred
gemini_list_image_sessions_toolread inferred
gemini_analyze_image_toolread inferred
gemini_search_toolread inferred
gemini_analyze_document_toolread inferred
gemini_summarize_pdf_toolwrite assumed
gemini_extract_tables_toolwrite assumed
gemini_analyze_url_toolread inferred
gemini_compare_urls_toolread inferred
gemini_extract_from_url_toolwrite assumed
gemini_generate_video_toolwrite assumed
gemini_check_video_toolread inferred
gemini_youtube_toolread inferred
gemini_youtube_summary_toolwrite assumed
gemini_speak_toolwrite assumed
gemini_dialogue_toolwrite assumed
gemini_list_voices_toolread inferred
gemini_deep_research_toolwrite assumed
gemini_check_research_toolread inferred
gemini_research_followup_toolwrite assumed
gemini_create_cache_toolwrite inferred
gemini_query_cache_toolread inferred
gemini_list_caches_toolread inferred
gemini_delete_cache_tooldelete inferred
gemini_structured_toolread inferred
gemini_extract_toolwrite assumed
gemini_count_tokens_toolread inferred
gemini_run_code_toolwrite 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.