Skip to content
Agentmart
Submit a tool

HallucC — Hallucination & Safety Guardian

Fact-check LLM outputs with cited sources.

Connector by fredyee · GitHub account verified by the MCP Registry

IndexedMITRemote (HTTP)
Write a review

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/fredyee-hallucc

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://aihcc.cloud/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
5 read · 0 write · 0 deleteRead-only
Secrets
1 (API keys, tokens or passwords)
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 5

From the running server's own tool list (tools/list) on Oct 25, 2026.

Read 5 · Look things up without changing anything.

  • check_cua_actions
  • check_cua_code_audit
  • check_safety
  • verify_agent
  • verify_text

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • Authorization

Network hosts it talks to 1

  • aihcc.cloud · found in remote endpoint, install command

Files it touches

  • Any path the agent passes to its tools

Tools (5)

As the server listed them on Oct 25, 2026. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • check_cua_actionsClassify CUA Actionsread-only

    Computer-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。

  • check_cua_code_auditAudit CUA Coderead-only

    CUA 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。

  • check_safetyCheck Safetyread-only

    AI 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）。

  • verify_agentVerify Agentread-only

    Agent 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。

  • verify_textVerify Textread-only

    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）。

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Oct 20, 2026 (9 days ago)
Last release
Oct 16, 2026 (13 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.fredyee/hallucc
Version
0.1.10
Auth
Bearer token
License
MIT
Repository
github.com/fredyee/hallucc-mcp
Website
aihcc.cloud
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

HallucC — Hallucination & Safety Guardian MCP server. Agent Mart. https://agentmart.dev/connectors/fredyee-hallucc (last updated 2026-10-24)