mcp-verify-claim
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: footnote
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
This server cannot be deployed
Maintenance
Related MCP Connectors
Agent memory that refuses to guess: evidence-gated recall, exact-source reads, verifiable deletion.
Deterministic decision layer for autonomous agents: reproducible PROCEED/REVIEW/SKIP verdicts.
Deterministic fact verification for AI agents — checksums & curated data, not guesses.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables agents to verify claims with evidence-based truth scores and confidence levels by running a deterministic pipeline of evidence lanes and adversarial checks.26MIT
- AlicenseNot gradedqualityBmaintenanceEnables 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
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to verify claims deterministically by computing arithmetic, ratios, and dates and matching statements against provided sources, returning a confidence ladder of certain, source-backed, or unverifiable.MIT
- AlicenseBqualityCmaintenanceEnables AI agents to verify technical claims against supplied evidence, identify unsupported assumptions and contradictions, and recommend the smallest next check before acting.5MIT