ai-scoreia-bench declares 18 capabilities across 18 tools, with 2 critical issues.
58/100 exposureElevated
Manifest retrieved 2026-09-14 from tools/list on https://scoreia.ai/mcp, published in the official MCP registry as ai.scoreia/bench 0.3.0. 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 18 tools
18 of 18 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 · 1 of 18 tools
1 tool is classified as irreversible and declares no limit.
high · no-expiry · All 18 tools
18 of 18 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 18 tools
18 of 18 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 · 9 of 18 tools
9 tools can modify data and declare no limit.
low · uncapped-read · 8 of 18 tools
8 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.
Tool
Read as
Basis
catalog
write
assumed
list_suites
read
inferred
read_suite
read
inferred
enter_open_challenge
write
assumed
start_challenge
write
assumed
observe_chamber
write
assumed
chamber_action
write
assumed
challenge_action
write
assumed
call_for_help
write
assumed
seal_attempt
send
inferred
finish_challenge
write
assumed
search_evidence
read
inferred
read_card
read
inferred
verify_card
read
inferred
open_challenge
write
assumed
list_open_challenges
read
inferred
search
read
inferred
fetch
read
inferred
Answering this question about your own agent? Media Yard LLC runs a
fixed-scope Agent Permission Audit: the same reading applied to your agent surface, delivered as a dated
artifact you can hand to a customer's security review. See what it includes and costs, or write to
support@leashkit.com.
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.