LeashIndex Get the report

Index / devtools

io.github.Harflow-Dev/harflow-mcp

io-github-harflow-dev-harflow-mcp declares 48 capabilities across 48 tools, with 2 critical issues.

94/100 exposureHigh exposure

Manifest recorded 2026-10-22 from tools/list answered by the PyPI package harflow-mcp==0.0.1 (published to PyPI as harflow-mcp, listed in the official MCP registry as io.github.Harflow-Dev/harflow-mcp 0.0.1), 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 48 tools

48 of 48 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 · 8 of 48 tools

8 tools are classified as irreversible and declare no limit.

high · no-expiry · All 48 tools

48 of 48 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 48 tools

48 of 48 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 48 tools

18 tools can modify data and declare no limit.

low · uncapped-read · 22 of 48 tools

22 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_backendsread inferred
start_tasksend inferred
list_approval_requestsread inferred
get_approval_requestread inferred
respond_approval_requestwrite inferred
preview_task_permissionsread inferred
subscribewrite assumed
get_task_notificationsread inferred
unsubscribewrite assumed
get_task_statusread inferred
wait_for_taskwrite assumed
wait_for_taskswrite assumed
continue_taskwrite assumed
resume_taskwrite assumed
list_tasksread inferred
list_task_pageread inferred
cancel_taskdelete inferred
get_task_eventsread inferred
get_task_event_pageread inferred
send_messagesend inferred
cancel_queued_messagedelete inferred
list_workflowsread inferred
get_workflowread inferred
save_workflowread inferred
delete_workflowdelete inferred
workflow_builderwrite assumed
followup_workflow_buildersend inferred
apply_workflow_draftsend inferred
preview_workflow_runread inferred
start_workflowwrite assumed
subscribe_workflowwrite assumed
unsubscribe_workflowwrite assumed
get_workflow_notificationsread inferred
revise_workflow_goalwrite assumed
list_workflow_runsread inferred
list_workflow_run_pageread inferred
get_workflow_statusread inferred
wait_for_workflowwrite assumed
get_workflow_run_detailread inferred
pause_workflowwrite assumed
resume_workflowwrite assumed
read_workflow_assigned_inputread inferred
inspect_workflow_nodewrite assumed
recover_workflowwrite assumed
cancel_workflowdelete inferred
register_artifactwrite assumed
get_task_artifactsread inferred
get_workflow_artifactsread 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.