mcpbeat Sign in

HallucC — Hallucination & Safety Guardian MCP Server

answering

HallucC — Hallucination & Safety Guardian is answering right now. Last checked 8 min ago. It exposes 5 tools. Last commit 20 Oct 2026.

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

Uptime history 50 days of history · worst day 95%
50 days agonow
98.9%
Uptime 24h
90 of 91 checks
5
Tools
read from the server
1297 ms
Response time
average over 24h
0
Stars
last commit 20 Oct 2026

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 15 October 2026. No other catalogue keeps this.

15 Oct a tool changed version

HallucC — Hallucination & Safety Guardian does not always answer

Over the last week it answered 99.2% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.

run in your terminal
claude mcp add hallucc --transport http https://aihcc.cloud/mcp
Settings → Connectors → Add custom connector, then paste this address
https://aihcc.cloud/mcp
~/.codex/config.toml
[mcp_servers.hallucc]
url = "https://aihcc.cloud/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "hallucc": {
      "url": "https://aihcc.cloud/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "hallucc": {
      "type": "http",
      "url": "https://aihcc.cloud/mcp"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

cua
check_cua_actions
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_audit
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。
verify
verify_agent
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_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)。
safety
check_safety
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)。

Endpoints

URLTransportStateLatencyChecked
https://aihcc.cloud/mcp streamable-http answering 900 ms 8 min ago

Alternatives to HallucC — Hallucination & Safety Guardian

same job, measured the same way
VerifyAPI — fact-check with signed receipts
by kythekitty

Fact-check any claim with live web sources. Ed25519-signed receipts. Catches hallucinations.

78 installs/wk local only
VeriGhost-Clarity
by evozim

Hallucination validator and factual grounding checker for LLM outputs.

1 tools answering
Perf MCP
by perf-ai

Fact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.

35 installs/wk local only
Claim Grounding
by truepointmarketingpartners-dotcom

Fact-check AI answers with cited sources. Pay per call in USDC on Base via x402.

4 tools answering
geo-score
by jianruntech

Free 0-100 score: can AI engines cite a site? Plus citation checks with your own API keys.

164 installs/wk local only
Arkheiaai
by arkheiaai

Detect fabrication and hallucination in any LLM output. 30+ models supported.

162 installs/wk local only
T
Trinity Research
by humanified

Fact-check claims against live web sources: verdict, consensus, cited sources, PII redaction.

4 tools answering
Agentcite
by kevinx702

Fabrication-free, DOI-backed citations for AI agents — real openAlex sources, never hallucinated.

41 installs/wk local only

HallucC — Hallucination & Safety Guardian — questions

Answers built from our own checks of this server.

What can HallucC — Hallucination & Safety Guardian do?
It exposes 5 tools, read directly from the server on our last check. Among them: check_cua_actions, check_cua_code_audit, check_safety, verify_agent, verify_text. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is HallucC — Hallucination & Safety Guardian mostly used for?
Its tools cluster around cua and verify. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is HallucC — Hallucination & Safety Guardian working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 90 of 91 checks got a reply (98.9%), average response time 1297 ms. The bar chart above shows every period we have measured.
How do I connect HallucC — Hallucination & Safety Guardian?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does HallucC — Hallucination & Safety Guardian need an API key?
No. HallucC — Hallucination & Safety Guardian completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is HallucC — Hallucination & Safety Guardian?
It answers our handshake in 1297 ms on average, which is faster than 2% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is HallucC — Hallucination & Safety Guardian open source?
The code is open source: it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at aihcc.cloud, which runs on its operator's own terms.