clearon-source-audit
Clearon Source Audit MCP
一个 MCP 服务器,用于进行与修订版本绑定的来源审查、引文匹配和发布前证据控制报告。
它旨在精确保留被审计的内容。它不发布文章、不判定真相,也不取代法律或编辑判断。
它能做什么
将每次审计绑定到精确的文章修订指纹。
记录来源分类以及主张到来源的映射。
对照检索到的来源文本验证直接引文。
标记程序性语言风险,例如将指控表述为裁判结论。
为被审计的修订生成不可变的 JSON 报告。
Related MCP server: CiteGuard
它不做什么
它不判定法律正确性或事实真伪。
它不发布或修改外部系统。
它不将检索失败视为来源虚假的证据。
它不会将已确认的警告转化为实质性支持。
要求
Node.js
20或更高版本能够启动 stdio 服务器的本地 MCP 客户端
安装
cd tools/clearon-source-audit-mcp
npm install
npm test
npm run smokeMCP 客户端设置
示例 stdio 配置:
{
"mcpServers": {
"clearon-source-audit": {
"command": "node",
"args": ["/absolute/path/to/clearon-source-audit-mcp/server.mjs"]
}
}
}如果要将审计数据放到特定位置,请在客户端环境中设置 CLEARON_SOURCE_AUDIT_ROOT。
存储
默认情况下,审计数据存储在仓库之外的用户数据目录中:
macOS:
~/Library/Application Support/clearon-source-audit-mcp/source-auditsLinux:
${XDG_DATA_HOME:-~/.local/share}/clearon-source-audit-mcp/source-auditsWindows:
%APPDATA%\\clearon-source-audit-mcp\\source-audits
使用 CLEARON_SOURCE_AUDIT_ROOT 覆盖该位置。
每次审计存储以下内容:
audit.jsonarticle.txtreports/*.json
在主机平台支持的情况下,文件以仅所有者可访问的权限写入。
推荐工作流
创建或获取要审计的精确文章文本。
计算其 SHA-256 指纹。
调用
create_source_audit。为每个来源调用
register_source。为可核查的事实性或法律性主张调用
record_claim_mapping。运行
run_mechanical_checks。修正文章中薄弱的主张、缺失的摘录、引文不匹配以及程序性警告。
如果文章文本发生变化,请为新修订创建新的审计。
调用
generate_source_report。仅当人工实际审核并接受某个警告后,才使用
acknowledge_finding。
工具
get_server_healthcreate_source_auditget_source_auditlist_source_auditsregister_sourcerecord_claim_mappingrun_mechanical_checksgenerate_source_reportacknowledge_finding
网络行为
URL 可用性检查需显式启用。run_mechanical_checks 和 generate_source_report 默认将 check_urls 设置为 false。
启用后,服务器会执行受限的 HTTP(S) 可达性检查,并且只将失败视为警告。在每次请求(包括重定向)之前,它会拒绝本地/私有 DNS 解析结果,并将连接固定到已验证的公共地址,以缩小 DNS 重绑定暴露面。这是一个便利性检查,不是信任判定,也不能替代主机级别的出口控制。
开发
npm test
npm run smoke
npm run syntax
node --check server.mjsMaintenance
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
- FlicenseNot gradedqualityNot gradedmaintenanceA 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.
- AlicenseNot gradedqualityBmaintenanceEnables per-claim citation verification for AI-generated text by fetching cited sources and judging whether they support the claim, with verdicts and evidence quotes.75MIT
- AlicenseNot gradedqualityBmaintenanceEnables defining and verifying evidence contracts for claims in READMEs, releases, or product pages using constrained verifiers and generating hash-chained receipts and reports.10MIT
- AlicenseAqualityCmaintenanceEnables scientific due diligence by grading claims against public literature, clinical trials, and filings, with explicit citations and optional attestation.4MIT
Related MCP Connectors
Deterministic cited disclosure drafts with verified GHG lineage and audit hashes.
Verify claims with verdict, confidence & cited sources; batch verify, source checks, daily brief.
Cite and independently verify Bitcoin-anchored construction-estimate audit records.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/kwgoodwin/clearon-source-audit-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server