LeashIndex Get the report

Index / other

Babelize

io-github-babelize-mcp declares 35 capabilities across 35 tools, with 2 critical issues.

85/100 exposureHigh exposure

Manifest recorded 2026-10-21 from tools/list answered by the npm package @babelize/mcp@1.3.0 (published to npm as @babelize/mcp, listed in the official MCP registry as io.github.babelize/mcp 1.3.0), run in an isolated container with no network access and placeholder 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 35 tools

35 of 35 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 35 tools

3 tools are classified as irreversible and declare no limit.

high · no-expiry · All 35 tools

35 of 35 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 35 tools

35 of 35 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 · 18 of 35 tools

18 tools can modify data and declare no limit.

low · uncapped-read · 14 of 35 tools

14 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
babelize_analyzeread declared
babelize_translatewrite assumed
babelize_checkread declared
babelize_reviewread declared
babelize_scanwrite assumed
babelize_scan_stringswrite assumed
babelize_project_listread inferred
babelize_project_getread inferred
babelize_project_createwrite inferred
babelize_babel_listread inferred
babelize_babel_getread inferred
babelize_language_listread inferred
babelize_language_codesread inferred
babelize_engine_analyzewrite assumed
babelize_tm_getread inferred
babelize_tm_setwrite inferred
babelize_tm_exportwrite assumed
babelize_glossary_deletedelete inferred
babelize_glossary_importwrite assumed
babelize_glossary_exportwrite assumed
babelize_project_language_addwrite inferred
babelize_project_language_removedelete inferred
babelize_member_listread inferred
babelize_invitation_sendsend inferred
babelize_project_syncwrite assumed
babelize_pr_raisewrite assumed
babelize_pr_updatewrite inferred
babelize_project_downloadwrite assumed
babelize_mewrite assumed
babelize_provider_tokens_listread inferred
babelize_runwrite assumed
babelize_run_and_waitwrite assumed
babelize_statusread inferred
babelize_glossary_getread inferred
babelize_glossary_setwrite inferred

Record history

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

RecordedExposureSource
2026-10-1585 tools/list answered by the npm package @babelize/mcp@1.2.0 (published to npm as @babelize/mcp, listed in the official MCP registry as io.github.babelize/mcp 1.2.0), run in an isolated container with no network access and placeholder credentials
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.