LeashIndex Get the report

Index / messaging

Autopo

io-github-autopoiesis-ai-mcp declares 99 capabilities across 99 tools, with 3 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://autopoiesis-mcp-267405155162.us-west1.run.app/mcp, published in the official MCP registry as io.github.Autopoiesis-ai/mcp 0.6.5. 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 99 tools

99 of 99 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 · 10 of 99 tools

10 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 · uncapped-spend · 1 of 99 tools

1 tool is classified as moving money and declares no dollar limit. A cap on the number of payments does not bound their amount.

high · no-expiry · All 99 tools

99 of 99 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 99 tools

99 of 99 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 · 43 of 99 tools

43 tools can modify data and declare no limit.

low · uncapped-read · 46 of 99 tools

46 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
list_companiesread declared
whoamiread declared
founder_homeread declared
company_overviewread declared
activityread declared
list_briefingsread declared
get_briefingread declared
brief_me_nowwrite assumed
list_decisionsread declared
get_decisionread declared
decidedestructive declared
comment_on_decisionwrite assumed
list_tasksread declared
get_taskread declared
create_taskwrite inferred
update_taskwrite inferred
comment_on_taskwrite inferred
cancel_taskdestructive declared
list_agentsread declared
ask_agentread inferred
continue_chatsend inferred
read_chatread declared
list_chatsread declared
apply_chat_actionwrite assumed
list_runsread declared
get_runread declared
nudge_runwrite assumed
list_artifactsread declared
get_artifactread declared
artifact_feedbackwrite assumed
studio_overviewread declared
studio_settingswrite assumed
list_mediaread declared
get_mediaread declared
generate_mediawrite assumed
list_videosread declared
get_videoread declared
create_videowrite inferred
set_video_shotswrite inferred
upload_mediawrite inferred
attach_mediawrite assumed
update_videowrite inferred
make_video_mediawrite assumed
video_keyframeswrite assumed
critique_videowrite assumed
wait_for_videoread declared
render_videowrite assumed
design_video_cardswrite assumed
video_planread declared
import_video_planwrite assumed
export_videowrite assumed
delete_videodestructive declared
update_mediawrite inferred
convert_video_to_codewrite assumed
get_video_coderead declared
write_video_codewrite inferred
check_video_coderead inferred
video_frameswrite assumed
video_code_versionsread declared
restore_video_codewrite assumed
planread declared
change_planwrite inferred
plan_settingswrite assumed
billing_pagewrite assumed
create_artifactwrite inferred
revise_artifactwrite assumed
artifact_linksread declared
share_artifactwrite assumed
unshare_artifactdelete inferred
list_errandsread declared
get_errandread declared
draft_errandwrite inferred
start_errandwrite assumed
answer_erranddestructive declared
errand_sign_inwrite assumed
list_membersread declared
chat_coworkerswrite assumed
competitorsread declared
manage_competitorwrite assumed
shopify_storeread declared
connect_shopifywrite assumed
sync_shopifyread inferred
brand_brainread declared
social_accountsread declared
list_postsread declared
check_postsread inferred
create_postsdestructive declared
marketing_learningsread declared
budgetread declared
ledgerread declared
buy_creditspay inferred
api_requestdestructive declared
api_referenceread declared
open_in_appwrite assumed
app_decidedestructive declared
app_refresh_inboxread declared
app_videowrite assumed
app_mediawrite assumed
app_artifactwrite 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.