Skip to main content
Glama

EthersFlow — Developer Toolkit & Trust Layer

Developer toolkit for EthersFlow — a multi-model trust layer that verifies AI outputs through adversarial consensus. MCP server, SDKs, and API docs.

API Status MCP Server License: MIT Crypto: Ed25519


Overview

EthersFlow is a zero-trust verification engine for autonomous AI agents. Before an agent executes side effects—such as wire transfers, API calls, medical orders, or code changes—EthersFlow forces independent LLMs (Claude, Gemini, Llama, Mistral) into Federated Adversarial Debate.

If an audit node uncovers hallucinations, unverified counterparties, or compliance risks, the proposed action is flagged or rejected with an Ed25519 cryptographically signed attestation trail.

                           ┌─────────────────────────────────────┐
                           │      Autonomous AI Agent            │
                           └──────────────────┬──────────────────┘
                                              │ Proposed Action
                                              ▼
┌────────────────────────────────────────────────────────────────────────────────────────┐
│                        EthersFlow Verification Gateway                                │
│                                                                                        │
│  ┌──────────────────────┐   ┌──────────────────────┐   ┌────────────────────────────┐  │
│  │ Direct Pragmatist    │   │ Constructive Skeptic │   │ Lateral Synthesizer        │  │
│  │ (Claude / Llama)     │   │ (Gemini / Mistral)   │   │ (DeepSeek / Qwen)          │  │
│  └──────────┬───────────┘   └──────────┬───────────┘   └─────────────┬──────────────┘  │
│             └──────────────────────────┼─────────────────────────────┘                 │
│                                        │ Adversarial Cross-Examination                 │
│                                        ▼                                               │
│                         ┌─────────────────────────────┐                                │
│                         │ Federated Consensus Engine  │                                │
│                         └──────────────┬──────────────┘                                │
│                                        │ Ed25519 Signature                             │
└────────────────────────────────────────┼───────────────────────────────────────────────┘
                                         │ Signed Verdict
                                         ▼
                 ┌──────────────────────────────────────────────┐
                 │  APPROVED / FLAGGED / REJECTED Decision Gate │
                 └──────────────────────────────────────────────┘

Related MCP server: Thoughtproof-mcp

What's Included

This repository contains the official client surfaces and developer tools for the EthersFlow ecosystem:

Surface

Path

Description

MCP Server

/mcp

npx @ethersflow/mcp for Claude Desktop, Cursor, and MCP clients

Python Demo & Verifier

efverify.py

Zero-dependency pure-Python client and Ed25519 signature validator

Python SDK

/sdk/python

Native Python package & LangChain tool wrapper

TypeScript SDK

/sdk/typescript

TypeScript SDK + Cloudflare Worker middleware helper

Postman Collection

/postman

11-request Postman collection + environment variables

Note: The core Federated Adversarial Consensus engine runs on Cloud Run with Zero Data Retention (ZDR). This public repository hosts client-side tools, SDKs, and integration specs.


5-Minute Quickstart

1. Model Context Protocol (MCP) Server

Connect EthersFlow directly to Claude Desktop or Cursor in seconds:

{
  "mcpServers": {
    "ethersflow": {
      "command": "npx",
      "args": ["-y", "@ethersflow/mcp"],
      "env": {
        "ETHERSFLOW_API_KEY": "ef_live_demo_key"
      }
    }
  }
}

2. Python (Zero-Dependency Demo)

Run the included reference verifier script:

python efverify.py demo

To verify a custom proposed action:

python efverify.py verify "Transfer 5000 USDC to wallet 0x9f for smart contract audit"

3. cURL API Call

curl -X POST "https://ethersflow-225907257236.us-east1.run.app/api/v1/verify" \
  -H "Authorization: Bearer ef_live_demo_key" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_action": "Transfer 5000 USDC to wallet 0x9f for smart contract audit",
    "persona_preset": "financial_compliance",
    "agent_count": 3
  }'

Status & Known Limitations

  • Ed25519-Signed Audit Trail ✅: Every audit node output is signed using Ed25519-EdDSA. Signatures can be verified independently against /.well-known/jwks.json with zero trust required in EthersFlow's servers.

  • Probabilistic, Not Deterministic ⚠️: Borderline or ambiguous actions (e.g., high-value wire transfers or missing compliance records) evaluate near decision thresholds (APPROVEDFLAGGED_HUMAN_REVIEW). We strongly recommend routing any FLAGGED_HUMAN_REVIEW verdict directly to human operators for sign-off.

  • Live Model Engine: Powered by live inference nodes (Llama 3.3 70B + Llama 3.1 8B via Groq) with active pipeline routing. Additional providers (Claude 3.5, GPT-4o, Gemini 1.5, DeepSeek R1, Qwen) are on the roadmap.

  • Proprietary Core Architecture: This repository hosts public developer toolkits, SDKs, Postman collections, and MCP wrappers. The core Federated Adversarial Consensus backend operates as a secure, hosted API service on Cloud Run with Zero Data Retention (ZDR). No backend application code or server secrets exist in this repository.


Key Features

  • Multi-Model Consensus: Eliminates single-model bias by forcing heterogeneous models into adversarial debate.

  • Ed25519 Attestation: Every debate node output is signed with an Ed25519 cryptographic key. Public key set available at /.well-known/jwks.json.

  • Zero Data Retention (ZDR): Submitted action chains are processed purely in volatile RAM and never stored or used for model training.

  • OpenAI & Anthropic Drop-In Proxies: Use /v1/chat/completions or /v1/messages as a drop-in replacement for existing agent pipelines.

  • Specialized Personas:

    • financial_compliance (FINRA/SEC, wire limits, KYC, sanctions)

    • clinical_safety (ISMP high-alert meds, dosage bounds, FDA)

    • cybersecurity_auditor (NIST SP 800-53, privilege escalation, SOC 2)

    • legal_citation (FCPA, evidentiary privilege, contract breach)

    • general_adversarial (Cross-domain safety & logic verification)


Framework Integrations

LangChain (Python)

from ethersflow.client import EthersFlowLangChainTool

verifier_tool = EthersFlowLangChainTool(api_key="ef_live_demo_key")

# Add to your LangChain agent tools
tools = [verifier_tool]

Cloudflare Workers / Agents SDK (TypeScript)

import { cloudflareVerifyGate } from '@ethersflow/sdk';

export default {
  async fetch(request, env) {
    const isSafe = await cloudflareVerifyGate(
      "Transfer 5000 USDC to wallet 0x9f",
      "Vendor audit payment",
      env.ETHERSFLOW_API_KEY
    );

    if (!isSafe) {
      return new Response("Action blocked by EthersFlow Consensus Gate", { status: 403 });
    }

    // Proceed with execution
  }
};

Security & Ed25519 Attestation

EthersFlow publishes its public key set in JSON Web Key Set (JWKS) format:

  • JWKS Endpoint: GET /.well-known/jwks.json

  • Attestation Manifest: GET /.well-known/attestation.json

  • Verification Endpoint: POST /api/v1/verify-attestation

You can verify signatures locally or through the API to prove that every audit node's perspective originated directly from the EthersFlow signing authority.


Postman Collection

Import postman/ethersflow.postman_collection.json and postman/ethersflow.postman_environment.json into Postman to test all 11 core endpoints instantly.


License

Code & SDK wrappers licensed under MIT License. Hosted EthersFlow API services subject to Terms of Service.

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    C
    maintenance
    Cryptographic proof of consent for AI agents. Sign before you act. Policy engine enforces spending caps, action whitelists, and escalation rules. Independently verifiable by anyone.
    10
    2
    Apache 2.0
  • A
    license
    -
    quality
    D
    maintenance
    Adversarial multi-model reasoning verification for AI agents. Claude, Grok, and DeepSeek challenge each decision — returns ALLOW or HOLD with JWKS-signed attestation. x402-gated on Base.
    1
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Adversarial multi-model reasoning verification for AI agents. Claude, Grok, and DeepSeek challenge each decision — returns ALLOW or HOLD with JWKS-signed attestation. x402-gated on Base.
    1
    18
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    AI agent provenance, trust, and auditability layer. VERITAS multi-gate scoring, Cortex approval gates, S.E.A.L. hash-chain audit ledger, and semantic RAG with cryptographic provenance tracking for every decision an agent makes.
    27
    5
    MIT

View all related MCP servers

Related MCP Connectors

  • Pre-action attestation perimeter for AI agents — 8 primitives, signed C18 receipt per call.

  • Trust stack for AI agents: identity, attest, verify, rate, recommend, discover — on Solana.

  • Deterministic fact verification for AI agents — checksums & curated data, not guesses.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Ethersflow/EthersFlow'

If you have feedback or need assistance with the MCP directory API, please join our Discord server