LeashIndex Get the report

Index / devtools

Scribase

com-scribase-scribase declares 97 capabilities across 97 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://api.scribase.com/mcp, published in the official MCP registry as com.scribase/scribase 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 97 tools

97 of 97 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 · 14 of 97 tools

14 tools are classified as irreversible or destructive and declare no limit. 13 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.

high · no-expiry · All 97 tools

97 of 97 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 97 tools

97 of 97 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 · 27 of 97 tools

27 tools can modify data and declare no limit.

low · uncapped-read · 56 of 97 tools

56 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
projects.listread declared
projects.createwrite inferred
keys.getread declared
sql.executedestructive declared
migrations.listread declared
migrations.applydestructive declared
tables.listread declared
tables.describeread declared
types.generateread declared
functions.listread declared
functions.deploywrite inferred
functions.logsread declared
storage.buckets.listread declared
storage.buckets.createwrite inferred
auth.config.getread declared
auth.config.setwrite inferred
capabilities.statusread declared
capabilities.addwrite inferred
extensions.listread declared
extensions.enablewrite assumed
schedule.listread declared
schedule.createwrite inferred
schedule.updatewrite inferred
schedule.deletedestructive declared
schedule.runwrite assumed
schedule.runsread declared
errors.listread declared
errors.getread declared
push.statusread declared
push.send_testsend inferred
ota.statusread declared
ota.releasesread declared
ota.rollbackdestructive declared
links.listread declared
links.createwrite inferred
logs.getread declared
branches.listread declared
branches.createwrite inferred
branches.mergewrite inferred
branches.resetdestructive declared
branches.restoredestructive declared
branches.masking.setwrite inferred
branches.deletedestructive declared
draft_x_launch_postread declared
docs.searchread declared
deploy.runread declared
analytics.summaryread declared
flags.listread declared
flags.setwrite inferred
uptime.statusread declared
ai.keysread declared
billing.productsread declared
addon.statusread declared
schema.proposeread declared
policy.simulatewrite assumed
policy.testwrite assumed
schema.applydestructive declared
sql.explainread declared
org.getread declared
org.putwrite inferred
member.putwrite inferred
project.getread declared
project.putwrite inferred
environment.listread declared
environment.getread declared
environment.createwrite inferred
environment.deletedestructive declared
environment.suspenddestructive declared
environment.resumewrite assumed
operation.getread declared
audit.listread declared
import.statusread declared
import.supabasewrite assumed
import.postgreswrite assumed
migrate.runwrite assumed
export.runread declared
org.listread declared
project.listread declared
branch.listread declared
branch.registerwrite inferred
branch.diffread declared
branch.mergedestructive declared
branch.link_pull_requestwrite inferred
database.queryread declared
database.tablesread declared
auth.usersread declared
storage.bucketsread declared
usage.getread declared
metrics.getread declared
logs.tailread declared
insights.getread declared
apikey.listread declared
apikey.revokedestructive declared
backup.listread declared
backup.getread declared
backup.createwrite inferred
backup.restoredestructive 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.