LeashIndex Get the report

Index / devtools

com.light-cloud/mcp-server

com-light-cloud-mcp-server declares 110 capabilities across 110 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 2026-10-29 from tools/list answered by the npm package @light-cloud/mcp-server@1.6.2 (published to npm as @light-cloud/mcp-server, listed in the official MCP registry as com.light-cloud/mcp-server 1.6.2), 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 110 tools

110 of 110 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 · 18 of 110 tools

18 tools are classified as irreversible or destructive and declare no limit. 11 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 · 3 of 110 tools

3 tools are classified as moving money and declare no dollar limit. A cap on the number of payments does not bound their amount.

high · no-expiry · All 110 tools

110 of 110 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 110 tools

110 of 110 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 · 31 of 110 tools

31 tools can modify data and declare no limit.

low · uncapped-read · 61 of 110 tools

61 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
pingread declared
loginwrite assumed
logoutdestructive declared
connectsend inferred
connect-statusread declared
whoamiread declared
get-profileread declared
list-applicationsread declared
get-applicationread declared
get-application-statusread declared
create-applicationwrite inferred
create-application-from-uploadwrite inferred
deploy-applicationwrite inferred
delete-applicationdestructive declared
detect-frameworkread declared
list-environmentsread declared
get-environmentread declared
create-environmentwrite inferred
deploy-environmentwrite inferred
delete-environmentdestructive declared
get-environment-logsread declared
list-deploymentsread declared
get-deploymentread declared
get-github-install-urlread declared
get-github-installation-statusread declared
list-github-installationsread declared
list-repositoriesread declared
list-branchesread declared
check-repo-accessread declared
request-upload-urlwrite inferred
complete-uploadwrite inferred
get-platform-configread declared
get-cloudrun-configread declared
detect-local-frameworkread declared
detect-local-gitread declared
package-sourcedelete inferred
upload-and-deploywrite inferred
wait-for-deploymentread declared
set-password-protectionwrite inferred
get-formatted-statusread declared
get-formatted-listread declared
read-project-configread declared
write-project-configwrite inferred
get-billingread declared
list-plansread declared
choose-planwrite assumed
add-payment-methodpay inferred
payment-method-statusread inferred
list-databasesread declared
get-databaseread declared
create-databasewrite inferred
get-database-connection-stringread declared
set-environment-variableswrite inferred
get-environment-variablesread declared
set-scalingwrite inferred
add-custom-domainwrite inferred
get-custom-domain-statusread declared
update-applicationwrite inferred
update-environmentwrite inferred
rename-applicationwrite inferred
move-applicationwrite inferred
remove-custom-domaindestructive declared
retry-custom-domainwrite assumed
list-repo-directoriesread declared
get-environment-metricsread declared
get-environment-activityread declared
get-environment-runtimeread declared
get-build-logsread declared
rollback-deploymentwrite assumed
list-foldersread declared
create-folderwrite inferred
delete-folderdestructive declared
create-stackwrite inferred
update-databasewrite inferred
delete-databasedestructive declared
rotate-database-passwordwrite assumed
get-database-metricsread declared
get-database-schemaread declared
query-databasedestructive declared
dump-databaseread declared
import-databasedestructive declared
get-usageread declared
get-usage-historyread declared
list-invoicesread declared
get-invoiceread declared
get-outstanding-invoicesread declared
retry-invoicepay inferred
remove-payment-methodpay inferred
get-usage-alertsread declared
set-usage-alertswrite inferred
get-billing-detailsread declared
set-billing-detailsread inferred
create-workspacewrite inferred
list-membersread declared
invite-membersend inferred
remove-memberdestructive declared
set-member-rolewrite inferred
list-rolesread declared
update-profilewrite inferred
list-connected-devicesread declared
sign-out-devicedestructive declared
get-agent-accessread declared
connect-git-providerread declared
list-provider-repositoriesread declared
list-api-keysread declared
create-api-keywrite inferred
revoke-api-keydestructive declared
list-notificationsread declared
mark-notifications-readread inferred
contact-supportsend 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.