Skip to main content
Glama
sudo-ai-git

mcp-verify-claim

by sudo-ai-git

mcp-verify-claim

一个 Model Context Protocol (MCP) 服务器,强制实施基于证据门控、诚实分层的声明报告。智能体做出的每条声明都会被归类到某个证据层级(FACT / INFERENCE / SPECULATION / UNVERIFIED),并附上证据——正是“静默未验证声明”这一失败模式的解药(“推送成功”、“测试通过”、“API 返回了 200”——全是在从未运行命令的情况下作出的断言)。

确定性,不依赖 LLM,无网络调用。可自托管,MCP 兼容任何智能体(Claude Code、Cursor、Copilot、OpenClaw、Codex CLI)。

为什么存在

最常见的智能体失败不是推理错误,而是报告一个听起来合理、从未经过验证的结果mcp-verify-claim 设置了一道硬性闸门:任何未经验证的声明都不能作为事实来报告。

Related MCP server: Recommend Agentic Trust Layer

工具

  • tier_claim(claim, evidence, verification_kind) — 将声明分类为层级 + 判定(TRUST / REVIEW / DO-NOT-REPORT)+ 诚实的下一步行动。

  • check_claim(claim) — 对捏造/模糊化信号进行确定性扫描(无产物即宣称完成、“API 返回了”、模糊词)。

  • report_templates() — 标准的 STATUS / EVIDENCE / GAPS 完成报告结构与 6 步行为循环。

  • tier_definitions() — FACT / INFERENCE / SPECULATION / UNVERIFIED 的定义。

证据层级(核心)

层级

含义

判定

FACT

在原始工具输出中直接看到(退出码、响应体、文件回读、HTTP 状态)

TRUST

INFERENCE

从事实推导而来;展示推导链

REVIEW

SPECULATION

一种猜测;永远不要当作事实报告

REVIEW

UNVERIFIED

未产出任何证据

DO-NOT-REPORT

安装与运行

pip install mcp
# Claude Desktop / agent config:
# { "mcpServers": { "verify-claim": { "command": "python3",
#       "args": ["/absolute/path/to/mcp_server.py"] } } }
python3 mcp_server.py

示例

tier_claim("Successfully deployed", evidence="", verification_kind="")
--> tier UNVERIFIED, verdict DO-NOT-REPORT
    signals: [high] completion claim without artifact
    next: go get the evidence before reporting

tier_claim("Deploy is live", evidence="origin/main SHA==local HEAD, HTTP 200", verification_kind="read_back")
--> tier FACT, verdict TRUST

许可证与出处

MIT。由 sudo-ai-git 编写。独立的行为严谨性工具;不包含任何专有方法。是 verify-before-claim 智能体技能的 MCP 表达。

官方 MCP 注册表元数据

mcp-name: io.github.sudo-ai-git/mcp-verify-claim

A
license - permissive license
Not graded
quality - not tested
C
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

  • F
    license
    Not graded
    quality
    Not graded
    maintenance
    A bounded evidence review engine that ingests documents, extracts evidence for a given claim, detects contradictions, and produces auditable evidence packets without hallucinations or open-web research.
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables agents to verify their own output mid-task by checking every claim against provided sources, returning supported, partial, unsupported, or contradicted verdicts with exact citations.
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to record, recall, correct, and forget evidence-backed factual claims with temporal history, while explaining whether remembered information is current, historical, or contested.
    5
    Apache 2.0

View all related MCP servers

Related MCP Connectors

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/sudo-ai-git/mcp-verify-claim'

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