Agent Decoy Gateway
Related Servers
Alternatives to Agent Decoy Gateway
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables transparent MCP proxying with a hash-chained effect ledger, classifying agent actions by reversibility, enforcing approval gates, and dry-run previews of sessions.MIT

Tarmac MCPofficial
AlicenseAqualityBmaintenanceEnables MCP agents such as Claude and Cursor to start runs on a live Robinhood Chain fork, read balances and quotes, request swaps under policy checks, and review verdicts and traces without holding a key.8MIT- AlicenseAqualityBmaintenanceFree seven-tool proof loop for MCP agents: scoped sessions, bounded authorization, typed outcomes, evidence-bound claims, and tamper-evident local closure. Upgrade to Complete Local for durable memory, recovery, signed traces, release verification, and multi-agent workflows.7Apache 2.0

alethia-mcpofficial
AlicenseAqualityAmaintenanceMCP bridge that lets any MCP client drive the Alethia runtime for agent-native E2E testing. It provides a per-step policy gate that blocks destructive actions with a cryptographic audit trail.1522 npm2MIT- AlicenseNot gradedqualityBmaintenanceEnables agents to propose policy-gated treasury payments and swaps, check pending human approvals, read transaction receipts, and locally verify their integrity through MCP tools.MIT
- AlicenseAqualityBmaintenanceEnables MCP-capable assistants to run read-only AI governance inventory checks, assemble Decision Packs, and validate signed Agent Trust Passports against pinned upstream tooling, returning every result as non-authorizing with authority_effect NONE.3Apache 2.0
TDQS
Scored across 2 tools
The two tools have clearly distinct roles: one opens/creates a synthetic settlement-reference trail, while the other follows an existing reference handle. The descriptions make the sequence and action boundaries explicit, so an agent should not confuse them.
Both names follow a consistent verb_noun pattern: lookup_settlement_reference and follow_settlement_reference. The shared object name reinforces the relationship without creating naming ambiguity.
Two tools is thin for a gateway surface, even if the intended workflow is deliberately minimal. The set is not bloated, but it sits at the borderline where more lifecycle operations may be expected.
The basic open-and-follow workflow is covered, but there is no visible way to list trails, inspect status, close/reset a trail, or handle errors beyond the hard step limit. These are notable gaps for a stateful reference-trail domain, though agents may work around them.