LeashIndex Get the report

Index / other

Hook Detector

com-hookdetector-hookdetector declares 43 capabilities across 43 tools, with 2 critical issues.

87/100 exposureHigh exposure

Manifest recorded 2026-10-16 from tools/list on https://api.hookdetector.com/mcp, published in the official MCP registry as com.hookdetector/hookdetector 2.4.0. 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 43 tools

43 of 43 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 · 3 of 43 tools

3 tools are classified as irreversible and declare no limit.

high · no-expiry · All 43 tools

43 of 43 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 43 tools

43 of 43 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 43 tools

17 tools can modify data and declare no limit.

low · uncapped-read · 23 of 43 tools

23 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
create_accountwrite inferred
showcasewrite assumed
find_hooksread inferred
get_runread inferred
list_runsread inferred
find_long_hooksread inferred
find_packagingread inferred
get_findread inferred
keep_findread inferred
clear_find_decisionread inferred
list_findsread inferred
remix_findread inferred
list_remixesread inferred
get_remixread inferred
list_kept_findsread inferred
export_runwrite assumed
get_hookread inferred
embed_hookwrite assumed
keep_hookwrite inferred
clear_decisionwrite assumed
remix_hookwrite assumed
list_keepsread inferred
balancewrite assumed
delete_accountdelete inferred
chatwrite assumed
list_conversationsread inferred
get_conversationread inferred
usagewrite assumed
list_keysread inferred
create_keywrite inferred
revoke_keydelete inferred
request_accesswrite inferred
list_access_requestsread inferred
approve_access_requestwrite inferred
reject_access_requestwrite inferred
list_access_codesread inferred
create_access_codewrite inferred
revoke_access_codedelete inferred
admin_overviewwrite assumed
admin_list_accountsread inferred
admin_adjust_creditswrite assumed
admin_list_runsread inferred
admin_list_actionsread inferred

Record history

Earlier records for this server. A correction is added here, never written over the record it corrects.

RecordedExposureSource
2026-10-1187 tools/list on https://api.hookdetector.com/mcp, published in the official MCP registry as com.hookdetector/hookdetector 2.4.0
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.