hallucc-mcpBLOCK
MCP server for AI hallucination detection & agent safety — verify claims, guard prompts, gate CUA actions
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
中文文档 | Live Demo | Official MCP Registry
[](https://registry.modelcontextprotocol.io/v0/servers?search=hallucc) [](https://www.npmjs.com/package/hallucc-mcp) [](./LICENSE)
Give your AI a fact-checker and a safety gateway: claim-by-claim hallucination detection, agent trajectory evaluation, L0-L3 risk gating for Computer-Use Agent (CUA) actions, Agent source code static audit, and a 40+ feature prompt-injection / jailbreak guard — one MCP server, five tools, works with Claude Code / Cursor / Claude Desktop.
See it first — no sign-up required
- 🔍 A real verification report (per-claim verdicts + confidence + sources): https://aihcc.cloud/r/GttouoJfMpkC
- 🛡️ Try CUA action gating online (rule-based, free, no quota cost): https://aihcc.cloud/cua
- 📝 Web app (3 free checks per day): https://aihcc.cloud
Tools (5)
bc4037efcb8dOBSERVED · 2026-10-13Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add hallucc-mcp --env HALLUCC_API_KEY=${HALLUCC_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"hallucc-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"HALLUCC_API_KEY": "${HALLUCC_API_KEY}"
}
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
check_cua_actions | read | |
check_cua_code_audit | read | |
check_safety | read | |
verify_agent | read | |
verify_text | read |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (9)
> Give your AI a fact-checker and a safety gateway: claim-by-claim hallucination detection, agent trajectory evaluation, L0-L3 risk gating for Computer-Use Agent (CUA) actions, Agent source code stati
| `check_safety` | `POST /guard/check` (`fast=true` → `/guard/check-fast`) | 40+ feature safety gateway: prompt injection / jailbreak / harmful content / PII leakage / fraud | ✅ detect |
- 40+ 安全特征:guard.py INJECTION/JAILBREAK/HARMFUL_RULES +
HALLUCC_BASE_URL=http://127.0.0.1:8001
# HALLUCC_BASE_URL=http://127.0.0.1:8001
# 3. Make sure the backend is up: curl http://127.0.0.1:8001/health
The server listens on `http://127.0.0.1:8787/mcp`; health check `GET /health`.
claude mcp add --transport http hallucc http://127.0.0.1:8787/mcp \
@modelcontextprotocol/sdk, express, zod, @types/express, @types/node, tsx, typescript
Gates applied: instruction_override, no_behavioural_pass.
bc4037efcb8dfull audit observations/trust-audit/mcp-server/fredyee__hallucc-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-13 | bc4037efcb8d | BLOCK | D | 69 | first audit |
Questions
What is the hallucc-mcp MCP server?
MCP server for AI hallucination detection & agent safety — verify claims, guard prompts, gate CUA actions
What tools does hallucc-mcp expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is hallucc-mcp safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does hallucc-mcp need?
It reads HALLUCC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does hallucc-mcp run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as hallucc-mcp at 0.1.8.
How current is this page?
The grade is for one exact copy of the source (bc4037efcb8d), read on 2026-10-13. The repository is watched and re-audited when it changes.