LeashIndex Get the report

Index / other

ElevenLabs

io-github-mindstone-mcp-server-elevenlabs declares 32 capabilities across 32 tools, with 2 critical issues. One of them, no-revocation, is recorded for every server in the index because MCP has no field in which to declare a way to switch a tool off; a missing declaration is not evidence that the control is missing.

90/100 exposureHigh exposure

Manifest recorded 2026-10-27 from tools/list answered by the npm package @mindstone/mcp-server-elevenlabs@0.5.2 (published to npm as @mindstone/mcp-server-elevenlabs, listed in the official MCP registry as io.github.mindstone/mcp-server-elevenlabs 0.5.2), 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 · irreversible-uncapped · 8 of 32 tools

8 tools are classified as irreversible or destructive and declare no limit. 7 of them are counted only because the server annotated them destructiveHint. In MCP that annotation marks a tool that may make destructive changes rather than only additive ones; it does not say the change cannot be undone.

critical · no-revocation · All 32 tools

32 of 32 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.

high · no-expiry · All 32 tools

32 of 32 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 32 tools

32 of 32 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 · 8 of 32 tools

8 tools can modify data and declare no limit.

low · uncapped-read · 16 of 32 tools

16 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
configure_elevenlabs_api_keydestructive declared
check_subscriptionread declared
get_usage_statsread declared
list_modelsread declared
generate_musicwrite assumed
create_music_planread declared
generate_music_from_planwrite assumed
generate_speechwrite assumed
generate_speech_with_timestampswrite assumed
generate_sound_effectwrite assumed
list_voicesread declared
get_voiceread declared
search_shared_voicesread declared
transcribe_audioread declared
speech_to_speechwrite assumed
isolate_audiodelete inferred
forced_alignmentread declared
clone_voicedestructive declared
delete_voicedestructive declared
text_to_dialoguewrite assumed
design_voiceread inferred
create_voice_from_previewdestructive declared
create_dubbingwrite inferred
get_dubbingread declared
download_dubbed_audioread declared
delete_dubbingdestructive declared
list_historyread declared
get_history_item_audioread declared
list_pronunciation_dictionariesread declared
get_pronunciation_dictionaryread declared
add_pronunciation_dictionarydestructive declared
archive_pronunciation_dictionarydestructive declared
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.