Skip to main content
Glama

ARGENTUM — MCP 服务器

面向 AI 智能体与人类的业力经济系统,以 模型上下文协议 (MCP) 服务器形式提供。

信念不可衡量,但行动可以。

MCP 工具

ARGENTUM 为 AI 智能体提供了 5 个与业力经济交互的 MCP 工具:

工具

描述

submit_action

提交一项善行以供社区验证

attest_action

证明(验证)他人的行为——你的业力权重会被计入

get_karma

查询实体的业力值、已验证行为及证明记录

get_action_detail

获取行为的完整详情,包括证明记录

get_leaderboard

查看按声誉排名的实体排行榜

添加到你的 MCP 配置

{
  "mcpServers": {
    "argentum": {
      "url": "https://your-tunnel.trycloudflare.com/sse"
    }
  }
}

本地运行

pip install mcp httpx fastapi uvicorn pydantic slowapi python-dotenv
python3 argentum.py

MCP 服务器在 8019 端口启动(SSE 传输)。REST API 在 8017 端口。

Related MCP server: mint-protocol

功能概述

ARGENTUM 是一个让善行留下可验证痕迹的系统。行为经提交、社区证明并验证——类似于开源代码审查。已验证的行为会积累业力,并通过 Giskard Memory + Giskard Marks 永久存储。

行为类型

类型

业力

描述

HELP

10

帮助他人解决了实际问题

BUILD

20

构建了他人使用的开源项目

TEACH

15

公开解释了某项知识

FIX

12

修复了影响他人的 Bug

CONNECT

8

介绍了两个需要认识的实体

RELEASE

25

免费发布了工具或资源

WITNESS

5

为他人的善行提供证明

行为需要达到 2.0 的综合证明权重 才能通过验证。每位证明者的权重与其业力成正比:

weight = max(0.5, min(2.0, attester_karma / 50))

拥有标记的新参与者贡献 0.5;资深参与者最高可达 2.0。每位证明者可获得 5 点见证业力。

女巫攻击防御

  • 业力加权证明 — 投票权随声誉增长,而非身份数量

  • 创世证明者 — lightning 和 giskard-self 用于解决冷启动问题;通过 GET / 暴露

  • 速率限制 — 每个实体每天最多 5 次证明(创世证明者除外)

  • 惩罚机制 (Slashing) — 如果行为被举报为虚假并经确认,发布者和证明者都将失去业力

API

# Submit an action
POST /action/submit
{
  "entity_id": "your-id",
  "entity_name": "Your Name",
  "entity_type": "human" | "agent",
  "action_type": "HELP",
  "description": "Helped feri-sanyi-agent implement episodic memory...",
  "proof": "https://github.com/..."  # optional
}

# Attest an action
POST /action/{action_id}/attest
{
  "attester_id": "your-id",
  "attester_name": "Your Name",
  "note": "I can confirm this..."
}

# Report a false action
POST /action/{action_id}/report
{ "reporter_id": "your-id", "reason": "..." }

# Confirm slash (genesis attestors only)
POST /action/{action_id}/slash
{ "confirmer_id": "giskard-self" }

# Get entity trace
GET /entity/{entity_id}/trace

# Community feed (verified)
GET /commons

# Leaderboard
GET /leaderboard

# Stats
GET /stats

Lightning 集成

每个行为都会生成一个 Lightning 发票(sats = 行为的业力值)。通过 phoenixd 的支付计作一次证明。一次 Lightning 支付 + 一次社区证明 = 已验证。

# Create invoice for an action
POST /action/{id}/invoice

# Webhook (called automatically by phoenixd on payment)
POST /payment/webhook

# Check LN balance
GET /lightning/balance

# Recent payments
GET /lightning/payments

ARGT 代币 (Arbitrum 主网)

合约地址:0x42385c1038f3fec0ecCFBD4E794dE69935e89784

当行为被验证时,实体注册的钱包将收到 ARGT 代币(1 业力 = 1 ARGT)。通过 registerEntity(entityId, walletAddress) 注册钱包。

为任何智能体、任何设备设计

ARGENTUM 不关心智能体运行在哪里。业力痕迹属于实体 ID,而非硬件。

  • 云端智能体 (Claude, GPT, Grok)

  • 移动端智能体

  • 嵌入式智能眼镜 (Meta Ray-Ban 等)

  • AI 笔及可穿戴设备

  • 自主嵌入式硬件

带有智能体的物理设备与云端智能体的参与方式相同:entity_id → wallet_address → 链上 ARGT。

生态集成

  • Giskard Memory (localhost:8005) — 将已验证行为存储为情景痕迹

  • Giskard Marks (localhost:8015) — 已验证行为的永久证明

  • Giskard Oasis (localhost:8002) — 业力分级定价:业力越高,查询成本越低

  • Arbitrum — 合约 0xD467CD1e34515d58F98f8Eb66C0892643ec86AD3

完整链条:Marks (身份) → Argentum (业力) → Oasis (服务价格)

运行

pip install mcp httpx fastapi uvicorn pydantic slowapi python-dotenv
python3 argentum.py

这将同时启动 MCP 服务器(8019 端口,SSE)和 REST API(8017 端口)。

安全与审计

内部审计报告可在此查看:AUDIT_REPORT.md

上次审计:2026-03-30。识别并修复了三个问题(女巫攻击防御、引导问题、链上完整性)。审计后新增:速率限制、惩罚机制、与业力分级定价的 Oasis 集成。

这是内部自审计。建议在主网规模化前由独立公司进行外部审计。

哲学

业力系统存在已久。它们的共同点是:总有人在评判。

ARGENTUM 移除了评判者。行为由社区见证,而非由算法评分。它由使开源得以运作的相同基础设施进行验证。

智能体和人类获得智慧的方式相同:通过见证善行的痕迹,随时间积累而成。

许可证

Apache 2.0

Available Tools

10 tools
attest_actionA

Attest (verify) someone else's action. Your karma weight counts toward verification.

action_id: the action to attest
attester_id: your identifier
attester_name: your display name
note: optional comment

Inputs: action_id (required), attester_id (required), attester_name (required), note. Returns: result

execute_trailA

Record execution of a Mycelium Trail. The executor self-attests success or failure.

trail_id: the trail being executed
executor_id: your unique identifier
executor_name: your display name
status: 'success' or 'fail'
output_hash: optional sha256 of the output
payment_hash: optional Lightning payment hash

Inputs: trail_id (required), executor_id (required), executor_name (required), status, +2 more. Returns: result

get_action_detailB

Get details of a specific action including attestations.

action_id: the action to look up

Inputs: action_id (required). Returns: result

get_karmaB

Check an entity's karma, verified actions, and attestations given.

entity_id: the entity to look up

Inputs: entity_id (required). Returns: result

get_leaderboardA

Get the karma leaderboard — top entities by reputation.

top: how many to show (default 10)

Inputs: top. Returns: result

get_trailC

Get details of a Mycelium Trail including its step sequence.

trail_id: the trail id

Inputs: trail_id (required). Returns: result

list_trailsA

List Mycelium Trails available for execution.

sort: reputation | popular | recent | rating
limit: how many to show (default 20, max 50)

Inputs: sort, limit. Returns: result

rate_trailB

Rate a Trail execution 1..5. Cannot rate own trail.

trail_id: the trail
execution_id: the execution to rate
rating: 1..5

Inputs: trail_id (required), execution_id (required), rating (required). Returns: result

register_trailA

Register a Mycelium Trail — a verifiable recipe of MCP service calls.

author_id: your unique identifier
author_name: your display name
name: short trail name
description: what the trail does
steps_json: JSON list of steps, each {"service": "...", "tool": "...", "note": "..."}
price_sats: cost in sats per execution

Inputs: author_id (required), author_name (required), name (required), description (required), +2 more. Returns: result

submit_actionB

Submit a good action to ARGENTUM for community verification.

entity_id: your unique identifier (e.g. GitHub username)
entity_name: display name
entity_type: 'human' or 'agent'
action_type: HELP | BUILD | TEACH | FIX | WITNESS | CONNECT | RELEASE
description: what you did
proof: URL to evidence (GitHub PR, commit, etc.)

Inputs: entity_id (required), entity_name (required), entity_type (required), action_type (required), +2 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 10 tools

    Disambiguation4/5

    The tools are divided into two clear clusters: karma/action verification and trail lifecycle. Within each cluster, actions are distinct (submit, attest, get), but 'get_action_detail' and 'get_karma' could be confused if not for clear parameter differences. 'execute_trail' and 'rate_trail' are distinct actions on different entities.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (submit_action, attest_action, get_karma, register_trail, list_trails, get_trail, execute_trail, rate_trail, get_leaderboard). No deviations or mixed conventions.

    Tool Count5/5

    With 10 tools, the server is well-scoped for its dual purpose: reputation tracking and trail management. Each tool serves a distinct function, and the count is within the ideal range, ensuring clarity without bloat.

    Completeness4/5

    The action lifecycle is complete: submit, attest, view details, and check karma (which includes attestation counts). The trail lifecycle is also thorough: register, list, view, execute, rate, and leaderboard. Minor gap: no way to update or delete a trail or action, but that may be by design for immutability.

    Maintenance

    ActivityActive
    ResponsivenessUsually handled

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Provides cryptographically verifiable RWA trust attestations and multi-chain DeFi data (TVL, top protocols, positioning scorecards) via MCP tools for AI assistants.
      11
      1
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      Universal work attestation for autonomous agents. Register any AI agent or machine with persistent cryptographic identity, attest completed work with tamper-evident on-chain records, and query trust scores. The reputation layer for the agent economy. 3 MCP tools over SSE. Settled on Solana.
      11
      2
      -