LeashIndex Get the report

Index / storage

CutClip.one

one-cutclip-cutclip declares 111 capabilities across 111 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.

100/100 exposureHigh exposure

Manifest recorded 2026-11-08 from tools/list on https://cutclip.one/api/mcp, published in the official MCP registry as one.cutclip/cutclip 1.0.0. 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 111 tools

111 of 111 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 · 17 of 111 tools

17 tools are classified as irreversible and declare no limit.

high · no-expiry · All 111 tools

111 of 111 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 111 tools

111 of 111 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 · 62 of 111 tools

62 tools can modify data and declare no limit.

low · uncapped-read · 32 of 111 tools

32 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
project.createwrite inferred
project.list_for_ownerread inferred
project.updatewrite inferred
project.deletedelete inferred
project.get_stateread inferred
project.get_summaryread inferred
project.exportwrite assumed
project.importwrite inferred
track.createwrite inferred
track.updatewrite inferred
track.deletedelete inferred
track.reorderwrite inferred
scene.createwrite inferred
scene.updatewrite inferred
scene.reorderwrite inferred
scene.deletedelete inferred
timeline.add_placeholderwrite inferred
timeline.move_itemwrite inferred
timeline.duplicate_itemwrite assumed
timeline.trim_itemwrite assumed
timeline.set_speedwrite inferred
timeline.set_volumewrite inferred
timeline.set_transformwrite inferred
timeline.split_itemwrite assumed
timeline.delete_itemdelete inferred
timeline.close_gapdelete inferred
timeline.batchwrite inferred
timeline.close_gapsdelete inferred
timeline.add_transitionwrite inferred
timeline.add_transitionswrite inferred
timeline.remove_transitionsdelete inferred
timeline.remove_transitiondelete inferred
timeline.update_transition_durationwrite inferred
asset.replace_placeholderwrite inferred
asset.getread inferred
asset.listread inferred
scenario.createwrite inferred
scenario.getread inferred
scenario.updatewrite inferred
scenario.deletedelete inferred
scenario.apply_to_timelinewrite assumed
storyline.getread inferred
storyline.set_premisewrite inferred
storyline.set_candidateswrite inferred
storyline.pickwrite assumed
storyline.update_scenewrite inferred
storyline.rewindwrite assumed
storyline.applywrite assumed
prompt.attachwrite assumed
prompt.updatewrite inferred
prompt.getread inferred
prompt.list_for_sceneread inferred
prompt.list_revisionsread inferred
project.undowrite assumed
render.previewread inferred
render.finalwrite assumed
credits.get_balanceread inferred
credits.list_historyread inferred
render.statusread inferred
render.get_resultread inferred
render.list_for_projectread inferred
render.deletedelete inferred
asset.uploadwrite inferred
asset.capture_framewrite assumed
prompt.draftwrite assumed
shot.draftread inferred
storyline.suggestwrite assumed
film.get_lookread inferred
film.update_lookwrite inferred
generation.list_modelsread inferred
character.listread inferred
character.getread inferred
character.createwrite inferred
character.updatewrite inferred
character.set_primarywrite inferred
character.deletedelete inferred
character.add_referencewrite inferred
character.remove_referencedelete inferred
character.generate_sheetwrite assumed
character.generate_viewread inferred
location.listread inferred
location.getread inferred
location.createwrite inferred
location.updatewrite inferred
location.deletedelete inferred
location.add_referencewrite inferred
location.remove_referencedelete inferred
location.generate_plateswrite assumed
shot.listread inferred
shot.getread inferred
shot.createwrite inferred
shot.updatewrite inferred
shot.deletedelete inferred
shot.reorderwrite inferred
shot.compile_promptread inferred
shot.generate_keyframewrite assumed
shot.select_keyframewrite assumed
shot.generate_videowrite assumed
shot.select_takewrite assumed
shot.add_stillwrite inferred
shot.remove_keyframedelete inferred
music.compile_promptread inferred
music.generatewrite assumed
voice.listread inferred
voice.compileread inferred
voice.generatewrite assumed
shot.lipsyncwrite assumed
shot.revoicewrite assumed
generation.listread inferred
generation.statusread inferred
generation.canceldelete inferred
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.