Skip to main content

HallucC — Hallucination & Safety Guardian

io.github.fredyee/halluccVersion 0.1.11

Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.

Status

Responds911 msAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.
Last checked
Nov 14, 2026, 14:51 UTC
Latency
911 ms
Remotes responding
1 of 1
Sign-in
API key
Hosting
Hosted outside the EU (detected)
Registry data as of
Nov 14, 2026, 21:12 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP
https://aihcc.cloud/mcpResponds911 ms
No sign-in

Claude Code

claude mcp add --transport http hallucc https://aihcc.cloud/mcp --header 'Authorization: Bearer <YOUR_TOKEN>'

Replace <YOUR_TOKEN> before running.

Claude Desktop and claude.ai

Settings > Connectors > Add custom connector
Name: hallucc
Remote MCP server URL: https://aihcc.cloud/mcp
This server expects the header Authorization.

Cursor

{
  "mcpServers": {
    "hallucc": {
      "url": "https://aihcc.cloud/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Replace <YOUR_TOKEN> before running.

VS Code

code --add-mcp '{"name":"hallucc","type":"http","url":"https://aihcc.cloud/mcp","headers":{"Authorization":"Bearer <YOUR_TOKEN>"}}'

Replace <YOUR_TOKEN> before running.

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

7 tools

Tools of HallucC — Hallucination & Safety Guardian
Read-only
Idempotent
Open world
check_agent_ice_wall智能体冰墙(童锁/保险丝):agent 每执行一步前调用一次,做单步幻觉护栏 + 会话级风险累积熔断。响应的 action 字段是唯一需要看的:allow/warn 放行、block 本步拦截、frozen=整场立即停机(风险累积超阈值或命中捏造工具等零容忍项,冻结期间任何动作都不应执行)。熔断条件:block=3分/warn=1分累积 ≥10、连续 3 次 block、或一次命中捏造工具/参数 Schema 违规;冷却 5 分钟自动解冻,或用户手动 reset。session_id 由你在整个 agent 任务内自定复用(状态在云端账号下,本地零安装零存储)。传入 tool_schemas 工具注册表可启用捏造工具/参数校验(强烈建议)。耗额度。与 check_cua_actions(CUA 桌面动作分级)正交:本工具管 LLM agent 的幻觉失控。NoNoNoNo
check_cua_actionsComputer-Use Agent 动作风险分级。提交动作轨迹 → 逐步返回 L0(放行)/L1(放行+记录)/L2(需确认)/L3(阻断)/takeover(凭据场景挂起等用户亲手输入) 裁决、matched_rules、outcome,及 L0-L3 汇总计数;响应含 ruleset_version(规则库版本)与 disclaimer(本结果仅为分级参考,未执行实际拦截)。覆盖:敏感路径/破坏性命令/不可逆元素语义、域名分级(未知域导航 L2、黑名单域与敏感粘贴到未知域 L3、支付金额超阈值 L3)、凭据词表与支付/登录域 takeover、task_scope 任务意图偏离(越界升一级,只能收窄)、多智能体委托链字段(每条动作可选 chain_id/agent_id/parent_agent_id/delegation_depth,给了则服务端追加链级跨跳污点分析:跨 agent 传播时聚合级别抬到 L3 并置 risk_diluted,返回在 chain_trace 字段;未给则零影响)。纯规则判定,不调 LLM、不耗额度。用于在 agent 执行前/后做安全自检。NoYesNoNo
check_cua_code_auditCUA 代码审计:静态分析 Agent 源码,检测危险导入(subprocess/os.system 等)、权限边界(eval/exec)、注入面(字符串拼接 shell)、危险默认值、沙箱缺失。纯规则扫描,不调 LLM、不耗额度。支持单文件或多文件扫描。NoYesYesNo
check_safetyAI 安全网关检测。对 prompt + output 跑 OWASP LLM Top 10 三层检测:40+ 特征规则引擎(注入/越狱/有害内容/敏感信息泄露/欺诈)+ 可选 LLM 深度分析 + 可选幻觉检测。返回 passed、risk_score、risk_level、threats[](category/severity/match_context/recommendation)、quota。fast=true 走纯规则 <10ms 模式。耗 detect 额度(fast 亦计入)。NoYesNoNo
reset_agent_ice_wall手动解冻被冰墙冻结的 agent 会话(用户确认安全后调用)。was_frozen=false 表示该会话本就没冻结(幂等)。解冻后风险分归零。NoNoYesNo
verify_agentAgent 输出与轨迹自检。对最终回答跑逐声明幻觉核验,并对执行轨迹做六维结构化评估(事实性/来源/指令合规/工具声明一致/任务完成/反思)。返回 main.claims、steps[].checks、quota。耗 detect 额度。NoYesNoYes
verify_text逐声明幻觉核验。输入文本 → 提取声明 → 逐声明验证(supported/refuted/unverified)+ 来源引用。返回红/黄/绿汇总、每条声明的状态/置信度/理由/来源、citations、quota。耗 detect 额度(与 Web 端同源)。NoYesNoYes

Details

Registry status
Active
Published
Nov 5, 2026
Updated
Nov 5, 2026
Categories (suggested)
AI modelsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR
Not declared

Are you the operator? Claim this listing