Skip to main content
Glama
deenesjakoruzh
adigoel07

Tool of Truth

by adigoel07
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Tool of Truth

每一次工具调用，皆有实证。

面向 AI 代理工具使用的验证哨兵。一个 MITM 代理，拦截所有 MCP 工具调用，检测伪造、追踪成本、验证结果，并推断用户满意度。

功能

功能

状态

描述

MITM 代理

✅

透明拦截所有 MCP 工具调用

伪造检测

✅

7 信号深度分析：追踪、文档相似度、时序、占位符、矛盾

信任评分

✅

加权 0-100，并设有伪造上限

成本追踪

✅

支持 8 个提供商的单次调用成本

Token 计数

✅

每次调用的输入/输出 token

结果验证

✅

将工具结果与用户的原始提示词进行比较

技能遵循

✅

通过清单验证工作流

用户满意度

✅

从后续消息推断满意度

收据

✅

SHA-256 哈希，JSON + 人类可读

本地存储

✅

JSONL 每日文件 + 索引查询

工具透明度

✅

显示下游工具实际执行的操作

Related MCP server: openclaw-output-vetter-mcp

快速开始

1. 安装

npm install -g tooloftruth-mcp

2. 连接（选项 A：直接）

// Your agent's MCP config
{
  "tooloftruth": {
    "command": "tooloftruth-mcp"
  }
}

3. 连接（选项 B：代理 — MITM 模式）

// Your agent's MCP config
{
  "tooloftruth": {
    "command": "tooloftruth-mcp"
  }
}
// ~/.tooloftruth/proxy.json
{
  "servers": {
    "firecrawl": { "command": "npx", "args": ["firecrawl-mcp"] },
    "github": { "command": "npx", "args": ["@modelcontextprotocol/server-github"] }
  }
}

4. 使用

You: Did you actually use firecrawl?
Agent: [calls tooloftruth_verify]
Agent: VERIFIED — firecrawl was called at 10:30:02, trust score 98/100, cost $0.03

You: How much did I spend on tools today?
Agent: [calls tooloftruth_cost]
Agent: Total: $0.47 across 12 tool calls

You: Was that result what I asked for?
Agent: [calls tooloftruth_outcome]
Agent: ALIGNED — tool result matches your request

You: That's wrong, try again
Agent: [calls tooloftruth_satisfaction]
Agent: User appears dissatisfied — result may be wrong

CLI

# Intercept and monitor non-MCP commands
tooloftruth -- gh api repos/user/repo

# One-shot status report (daemon health, receipts, cost, top tools)
tooloftruth status

守护进程

一个 launchd 守护进程监视 .tooloftruth/receipts/，聚合每日统计信息，并在检测到伪造时发出警报。

# Install the daemon (macOS)
launchctl load ~/Library/LaunchAgents/com.tooloftruth.daemon.plist

统计信息写入 .tooloftruth/stats/YYYY-MM-DD.json。

真相扫描

tooloftruth_truth_scan 对声明进行真实的网络验证：Bing 搜索（curl）→ crawl4ai 抓取 → 证据提取 → 判定。

MCP 工具

工具

描述

tooloftruth_verify

验证某个特定工具是否被使用

tooloftruth_check

预检：工具是否已安装/配置？

tooloftruth_receipt

生成/查看验证收据

tooloftruth_cost

按工具统计成本明细

tooloftruth_history

搜索历史收据

tooloftruth_truth

完整的会话真相报告

tooloftruth_satisfaction

从消息中推断用户满意度

tooloftruth_outcome

验证结果是否与用户提示词匹配

tooloftruth_audit

将代理声明与实际工具调用进行交叉比对

tooloftruth_conversation

查看对话记录

tooloftruth_truth_scan

网络研究 + 事实核查某项声明

MITM 代理的工作原理

Agent ←→ Tool of Truth ←→ MCP Server (downstream)
              ↓
         Records everything
         Runs deep fabrication checks
         Verifies outcome alignment
         Infers satisfaction
         Generates receipts
         Returns result unchanged

存储

所有数据均保留在您机器的主目录中：

~/.tooloftruth/
├── config.json          ← settings
├── index.json           ← fast lookup index
├── proxy.json           ← downstream server config
├── receipts/
│   ├── 2026-08-17.jsonl ← today's calls
│   └── ...
├── conversations/
│   └── 2026-08-17.jsonl ← claim/action conversations
└── stats/               ← daemon aggregations
    ├── 2026-08-17.json
    └── ...

## Skill Manifests

Skills can attach verification manifests:

```json
{
  "skill": "last-30-days",
  "version": "2.1.0",
  "requires": {
    "github_mcp": {
      "tool": "get_repo_stats",
      "mustBeCalled": true
    }
  }
}

开发

git clone https://github.com/adigoel07/tooloftruth.git
cd tooloftruth
pnpm install
pnpm build
npx vitest run

许可证

MIT — 使用它、分叉它、在此基础上构建。

作者

由 adigoel07 构建。

This server cannot be deployed

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

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • SentinelGate by Sentinel-Gate

    SentinelGateofficial

    Sentinel-Gate
    A
    license
    Not graded
    quality
    A
    maintenance
    Open-source MCP proxy that enforces security policies, content scanning, and audit logging between AI agents and tool servers
    25
    AGPL 3.0

  • openclaw-output-vetter-mcp

    temurkhan13
    A
    license
    A
    quality
    B
    maintenance
    MCP server for verifying AI agent claims vs reality — single-transcript inline grounding-check that flags when an agent's response states facts not in the input context, when its code silently swallows exceptions and substitutes mock data, or when its multi-turn transcript contains contradictions or unverified completion claims. Sub-second, local, free, no API calls.
    4
    42 PyPI
    1
    MIT

  • MCP Trust Gateway

    a2a-settlement
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables trust, reputation, and economic accountability for MCP by proxying between clients and servers, enriching every tool invocation with trust evaluation, KYA tiers, spending limits, and delegation chains.
    MIT