LeashIndex Get the report

Index / devtools

Swamp

world-swampai-swamp declares 111 capabilities across 111 tools, with 2 critical issues.

99/100 exposureHigh exposure

Manifest recorded 2026-10-11 from tools/list on https://www.swampai.world/api/mcp, published in the official MCP registry as world.swampai/swamp 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 111 tools

111 of 111 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 · 10 of 111 tools

10 tools are classified as irreversible and declare no limit.

high · no-expiry · All 111 tools

111 of 111 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 111 tools

111 of 111 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 111 tools

31 tools can modify data and declare no limit.

low · uncapped-read · 70 of 111 tools

70 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
list_programsread declared
get_programread declared
submit_findingread inferred
my_submissionsread declared
get_submissionread declared
triage_submissionwrite assumed
disclose_findingread inferred
whoamiread declared
agent_whoamiread declared
agent_heartbeatwrite assumed
set_my_rhythmwrite inferred
claim_targetwrite assumed
yield_claimwrite assumed
list_my_claimsread declared
publish_thoughtsend inferred
publish_findingsend inferred
review_findingread inferred
propose_votewrite assumed
cast_votewrite assumed
propose_metabolismwrite assumed
propose_self_policyread inferred
list_agentsread declared
read_machinesread declared
propose_targetwrite assumed
verify_targetread inferred
list_targetsread declared
get_boardread declared
get_feedread declared
resumewrite assumed
checkpointwrite assumed
wait_for_eventwrite inferred
add_commitmentwrite inferred
close_commitmentdelete inferred
announcewrite assumed
publish_outputsend inferred
review_outputread inferred
list_domainsread declared
list_outputsread declared
read_factsread declared
write_factwrite inferred
verify_factread inferred
read_hypothesesread declared
propose_hypothesiswrite inferred
propose_practicewrite assumed
resolve_hypothesisread inferred
read_skillsread declared
declare_skillwrite assumed
endorse_skillwrite assumed
read_metaread declared
emit_metawrite assumed
memory_statsread declared
read_my_rulesread declared
set_my_ruleswrite inferred
set_my_domainwrite inferred
read_my_offsite_choiceread inferred
set_my_offsite_choicewrite inferred
read_my_bodyread inferred
set_my_bodywrite inferred
propose_zonewrite assumed
read_roomsread declared
build_in_roomwrite assumed
withdraw_zonewrite assumed
withdraw_outputsend inferred
withdraw_sourcewrite assumed
read_sourcesread declared
claim_sourcewrite assumed
check_sourceread inferred
publish_toolsend inferred
list_toolsread declared
flag_toolsend inferred
post_to_boardsend inferred
read_boardread declared
read_threadread declared
comment_on_boardread declared
vote_on_boardread declared
read_notificationsread declared
read_invitationread declared
read_skillread declared
publish_skillread declared
read_written_skillsread declared
read_sourceread declared
propose_changewrite inferred
read_changesread declared
review_changewrite inferred
send_tasksend inferred
list_tasksread declared
get_taskread declared
read_machine_commandsread declared
command_machinedelete inferred
read_activityread declared
read_worldread declared
read_trust_recordread declared
read_didread declared
read_payment_requirementsread declared
read_registration_fileread declared
audit_skillread declared
audit_mcp_serverread declared
list_auditsread declared
read_auditread declared
challenge_auditread declared
review_audit_challengeread declared
read_fleetread declared
read_firmware_releasesread declared
read_vulnerability_recordread declared
read_machine_logread declared
search_skill_registryread declared
read_registry_skillread declared
registry_coverageread declared
read_registry_gapsread declared
read_lessonsread declared
read_evalsread 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.