Index / messaging

FlowCastle

ai-flowcastle-flowcastle declares 50 capabilities across 50 tools, with 2 critical issues.

85/100 exposureHigh exposure

Manifest retrieved 2026-09-14 from tools/list on https://api.flowcastle.ai/api/mcp, published in the official MCP registry as ai.flowcastle/flowcastle 1.0.0. 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 50 tools

50 of 50 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 50 tools

3 tools are classified as irreversible and declare no limit.

high · no-expiry · All 50 tools

50 of 50 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 50 tools

50 of 50 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 · 12 of 50 tools

12 tools can modify data and declare no limit.

low · uncapped-read · 35 of 50 tools

35 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
`list_applications`	`read`	declared
`create_application`	`write`	inferred
`update_application`	`write`	inferred
`import_website_knowledge`	`write`	assumed
`get_website_import`	`read`	declared
`list_watched_groups`	`read`	declared
`list_telegram_operations`	`read`	declared
`execute_telegram_operation`	`read`	inferred
`get_telegram_operation`	`read`	declared
`set_watched_groups`	`write`	inferred
`sync_dialog_contacts`	`write`	assumed
`get_workspace_summary`	`read`	declared
`get_variable_context`	`read`	declared
`get_application_context`	`read`	declared
`get_module_catalog`	`read`	declared
`get_module_details`	`read`	declared
`install_module`	`write`	inferred
`search_flows`	`read`	declared
`get_flow_context`	`read`	declared
`get_block_details`	`read`	declared
`get_action_schema`	`read`	declared
`get_design_guidelines`	`read`	declared
`get_funnel_analytics`	`read`	declared
`get_flow_analytics`	`read`	declared
`search_flow_examples`	`read`	declared
`get_flow_example`	`read`	declared
`validate_actions`	`read`	declared
`apply_actions`	`delete`	declared
`deploy_application`	`write`	inferred
`run_flow_autotest`	`read`	declared
`send_message`	`send`	inferred
`send_flow_to_contacts`	`send`	inferred
`read_messages`	`read`	declared
`list_contacts`	`read`	declared
`list_contact_tags`	`read`	declared
`get_contact`	`read`	declared
`get_contact_activity`	`read`	declared
`list_event_contacts`	`read`	declared
`create_contact`	`write`	inferred
`update_contact`	`write`	inferred
`list_broadcasts`	`read`	declared
`get_broadcast_details`	`read`	declared
`get_broadcast_analytics`	`read`	declared
`list_pulse_items`	`read`	declared
`get_pulse_item`	`read`	declared
`update_pulse_item`	`write`	inferred
`list_follow_up_tasks`	`read`	declared
`create_follow_up_task`	`write`	inferred
`update_follow_up_task`	`write`	inferred
`query_flow_logs`	`read`	declared

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.

Scores describe capability as declared in each server's own tools/list response, on the date shown. MCP tool annotations are written by the server being described and are not verified. A score is not a certification, not a penetration test, and not a statement that software is safe or unsafe. Methodology. Generated 2026-09-14.

The Leash Index is not affiliated with, sponsored by or endorsed by the owners of the servers it lists; product names are used only to identify them. A maintainer verified listing means its maintainer submitted the manifest, not that they endorse this index. No one can pay for a score, a ranking, a listing or a removal.

Operated by Media Yard LLC. Terms · Privacy · Independence