Skip to main content
Glama

EthersFlow — Trust Gate for AI Agents

by io.github.Ethersflow
OverviewDiscussionsAdmin

verify_agent_action

Gate and verify autonomous AI agent action decisions (e.g. trades, emails, claims, API calls) via EthersFlow Multi-Model Federated Adversarial Consensus before execution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contextNoStructured contextual evidence, metadata, or source document references.
policy_idNoOptional policy pack identifier to evaluate against.
scope_hintNoOptional domain or task scope hint (e.g. 'clinical_safety', 'financial_compliance', 'legal_citation', 'cybersecurity_auditor').
agent_countNoNumber of adversarial audit nodes (2 to 7, default 3).
scope_grantNoExplicit kernel-resolvable subject authorization or scope grant evidence (e.g. { subject_id, granted_by, consent_verified, status: 'VERIFIED' }).
agent_actionYesThe proposed action the agent intends to take.
persona_presetNo
zero_retentionNoEnforce zero data retention (ZDR).
reasoning_chainNoThe agent's internal reasoning or context leading to this decision.
grounding_enabledNoEnable hybrid fact grounding verification.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / scope_grant
      Added value: +{
+  "description": "Explicit kernel-resolvable subject authorization or scope grant evidence (e.g. { subject_id, granted_by, consent_verified, status: 'VERIFIED' }).",
+  "type": "object"
+}
  2. First observed

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It discloses the consensus mechanism and pre-execution timing, but says nothing about what a verdict looks like, whether it blocks the action on failure, latency, permissions, or retention behavior — notable gaps for a gate that sits in front of real trades and emails.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the verb leading and the mechanism trailing. Efficient, though the proprietary 'EthersFlow Multi-Model Federated Adversarial Consensus' label consumes space without adding actionable meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a 10-parameter tool with nested objects, no annotations, and no output schema, so the description must explain both behavior and result semantics. It explains neither the shape of a verification result nor the failure mode, leaving the agent under-informed for a high-stakes gating call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 90% across 10 parameters, so the schema already documents inputs well. The description adds no parameter-level detail (e.g. what agent_count or scope_grant actually do), so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb pair ('gate and verify') and resource ('autonomous AI agent action decisions'), with concrete examples (trades, emails, claims, API calls) that clarify the scope. It is clear what the tool does, though the outcome of a 'gate' decision is left implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'before execution' implies the timing condition for calling it, and the examples imply the domains where it applies. However, there is no explicit when-to-use vs. when-not guidance, no prerequisites, and no alternatives named (none exist as siblings).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All EthersFlow — Trust Gate for AI Agents toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources