LeashIndex Get the report

Index / other

Compose MCP

ai-smartmemory-compose-mcp declares 51 capabilities across 51 tools, with 1 critical issue.

90/100 exposureHigh exposure

Manifest recorded 2026-10-11 from tools/list answered by the npm package @smartmemory/compose-mcp@0.7.2 (published to npm as @smartmemory/compose-mcp, listed in the official MCP registry as ai.smartmemory/compose-mcp 0.7.2), 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 51 tools

51 of 51 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.

high · no-expiry · All 51 tools

51 of 51 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 51 tools

51 of 51 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 51 tools

31 tools can modify data and declare no limit.

low · uncapped-read · 20 of 51 tools

20 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
get_vision_itemsread inferred
get_item_detailread inferred
get_phase_summaryread inferred
get_blocked_itemsread inferred
get_current_sessionread inferred
bind_sessionwrite assumed
set_workspacewrite inferred
get_workspaceread inferred
get_feature_lifecycleread inferred
kill_featurewrite assumed
complete_featurewrite assumed
start_iteration_loopwrite assumed
report_iteration_resultwrite assumed
abort_iteration_loopwrite assumed
assess_feature_artifactswrite assumed
scaffold_featurewrite inferred
approve_gatewrite inferred
get_pending_gatesread inferred
add_roadmap_entrywrite inferred
set_feature_statusread inferred
roadmap_diffread inferred
get_roadmapread inferred
validate_featureread inferred
validate_projectread inferred
roadmap_graphwrite assumed
roadmap_graph_checkwrite assumed
roadmap_xref_pushwrite inferred
propose_followupwrite assumed
link_artifactwrite assumed
link_featureswrite assumed
get_feature_artifactsread inferred
get_feature_linksread inferred
add_changelog_entrywrite inferred
get_changelog_entriesread inferred
write_journal_entrywrite inferred
get_journal_entriesread inferred
backfill_completionwrite assumed
record_completionwrite inferred
get_completionsread inferred
write_checkpointwrite inferred
compose_resumewrite assumed
judgment_position_createwrite inferred
judgment_position_amendwrite assumed
judgment_joint_addwrite inferred
judgment_transitionwrite assumed
judgment_ledger_appendwrite assumed
judgment_person_writewrite inferred
judgment_situation_writewrite inferred
judgment_goal_writewrite inferred
get_judgment_stateread inferred
get_judgment_traceread 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.