Skip to content

HallucC — Hallucination & Safety Guardian MCP server

io.github.fredyee/halluccfredyeestreamable-httpv0.1.12Scanned

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

7 tools: 1 do something that can't be undone and 6 change things.

Tools: 0 delete, 1 irreversible, 6 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 0
  • 4 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the HallucC — Hallucination & Safety Guardian MCP server can do

The HallucC — Hallucination & Safety Guardian MCP server is published by the GitHub account fredyee. It has 7 tools. It can do things that cannot be undone, such as sending, paying or publishing (check_cua_actions) and create or change data (6 tools: verify_text, verify_agent, check_cua_code_audit, check_safety and 2 more), but cannot delete data. None of its tools only reads.

2 tools bring in text other people can write (verify_text and verify_agent).

The fixed checks matched 4 findings (tool-shadowing, credentials-mention and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 17, 2026, version 0.1.12.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

7 tools

Can't be undone 1Claude Code: ask
  • check_cua_actionsComputer-Use Agent action risk grading.2 findings

    Why it is in this group

    • The description says "irreversible".
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...on) / L3 (block) / takeover (suspend in credential scenarios and wait for the user to type..."

      What this check looks for
    • Warn

      The server marks "check_cua_actions" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description says "irreversible".

      What this check looks for
    Description, as the server wrote it
    Computer-Use Agent action risk grading. Submit an action trajectory and receive a step-by-step verdict of L0 (allow) / L1 (allow + log) / L2 (require confirmation) / L3 (block) / takeover (suspend in credential scenarios and wait for the user to type manually), together with matched_rules, outcome and L0-L3 tallies. The response includes ruleset_version and a disclaimer (results are grading guidance only; no enforcement is performed). Coverage: sensitive paths, destructive commands, irreversible element semantics; domain grading (unknown-domain navigation -> L2, blocklisted domains and sensitive pastes into unknown domains -> L3, payment amounts above threshold -> L3); credential vocabularies and takeover on payment/login domains; task_scope intent deviation (out of scope escalates one level and can only narrow); multi-agent delegation chain fields (each action may carry chain_id/agent_id/parent_agent_id/delegation_depth; when provided the server adds chain-level cross-hop taint analysis, raising the aggregate level to L3 and setting risk_diluted on cross-agent propagation, returned in the chain_trace field; omitted means no effect). Pure rule-based: no LLM calls, no quota consumed. Use it for safety self-checks before and after agent execution.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Changes things 6Claude Code: ask
  • check_agent_ice_wallAgent ice wall (child lock / fuse).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Agent ice wall (child lock / fuse). Call it once before every agent step for per-step hallucination guardrails plus session-level cumulative risk fusing. The response's action field is the only one you need to read: allow/warn = proceed, block = this step is intercepted, frozen = halt the entire run immediately (the risk score passed the threshold, or a zero-tolerance condition such as a fabricated tool was hit; no action should be executed while frozen). Fuse conditions: block = 3 points, warn = 1 point, accumulated >= 10; three consecutive blocks; or a single fabricated-tool / parameter-schema violation. It auto-unfreezes after a 5-minute cooldown, or the user can reset it manually. session_id is caller-defined and must be reused for the whole agent task (state lives in your cloud account, zero local install and zero local storage). Pass tool_schemas as a tool registry to enable fabricated-tool and parameter validation (strongly recommended). Consumes quota. Orthogonal to check_cua_actions (CUA desktop action grading): this tool governs an LLM agent's own loss of control.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • check_cua_code_auditCUA code audit: static analysis of agent source code that detects dangerous imports (subprocess, os.system, and similar), privilege boundaries (eval/exec), injection surface (strin…1 finding

    Why it is in this group

    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "check_cua_code_audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.code), which can change anything it can reach.

      What this check looks for
    Description, as the server wrote it
    CUA code audit: static analysis of agent source code that detects dangerous imports (subprocess, os.system, and similar), privilege boundaries (eval/exec), injection surface (string-concatenated shell commands), dangerous defaults, and missing sandboxing. Pure rule-based scanning: no LLM calls, no quota consumed. Supports single-file and multi-file scans.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_safetyAI safety gateway detection.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    AI safety gateway detection. Runs three-layer OWASP LLM Top 10 detection on prompt + output: a 40+ signature rule engine (injection, jailbreak, harmful content, sensitive data leakage, fraud) plus optional LLM deep analysis and optional hallucination detection. Returns passed, risk_score, risk_level, threats[] (category/severity/match_context/recommendation) and quota. fast=true uses the rule-only sub-10ms mode. Consumes detect quota (fast calls count too).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • reset_agent_ice_wallManually unfreeze an agent session frozen by the ice wall (call after the user confirms it is safe).No findings

    Why it is in this group

    • The name "reset_agent_ice_wall" says "reset": a word for a change.
    Description, as the server wrote it
    Manually unfreeze an agent session frozen by the ice wall (call after the user confirms it is safe). was_frozen=false means the session was not frozen in the first place (idempotent). The risk score resets to zero after unfreezing.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • verify_agentAgent output and trajectory self-check.Reads text others write1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The input schema at properties.steps.items.properties.tool.description names a tool "in" that this server does not list.

      Matched text

      inputSchema.properties.steps.items.properties.tool.description: "Tool called in this step"

      What this check looks for
    Description, as the server wrote it
    Agent output and trajectory self-check. Runs claim-by-claim hallucination verification on the final answer and a six-dimension structured evaluation of the execution trajectory (factuality, sourcing, instruction compliance, tool-claim consistency, task completion, reflection). Returns main.claims, steps[].checks and quota. Consumes detect quota.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • verify_textClaim-by-claim hallucination verification.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Claim-by-claim hallucination verification. Input text is split into claims, and each claim is verified (supported / refuted / unverified) with source citations. Returns a red/yellow/green summary plus each claim's status, confidence, reason and sources, along with citations and quota. Consumes detect quota (shared with the web dashboard).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:05 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
7
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 7 tools that change things (1 irreversible, 6 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://aihcc.cloud/mcp: tools/list returned 7 tools to an anonymous client, including check_cua_actions (irreversible), verify_text (write), verify_agent (write), check_cua_code_audit (write), check_safety (write) and 2 more

    What this check looks for

Posture changes

  1. Nov 6, 2026
    • Tools that change things, listed without credentials: 5 to 7

Findings

Matches of fixed checks, with the text they matched.

3 warn1 info
  • The input schema at properties.steps.items.properties.tool.description names a tool "in" that this server does not list.

    Matched text

    inputSchema.properties.steps.items.properties.tool.description: "Tool called in this step"

    What this check looks for
  • The server marks "check_cua_actions" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description says "irreversible".

    What this check looks for
  • The server marks "check_cua_code_audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.code), which can change anything it can reach.

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "...on) / L3 (block) / takeover (suspend in credential scenarios and wait for the user to type..."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools7 changed.~7 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 7.View diff
    • Tools that change things, listed without credentials: 5 to 7
  3. Tools2 added.+2 addedView diff

Install

Pinned to version 0.1.12. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__hallucc__verify_text",
      "mcp__hallucc__verify_agent",
      "mcp__hallucc__check_cua_actions",
      "mcp__hallucc__check_cua_code_audit",
      "mcp__hallucc__check_safety",
      "mcp__hallucc__check_agent_ice_wall",
      "mcp__hallucc__reset_agent_ice_wall"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as hallucc. Review it before you use it.

Capability tags behind 2 rules
  • mcp__hallucc__verify_text untrusted-input
  • mcp__hallucc__verify_agent untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.fredyee/hallucc/verify?hash=ca2ee912debbb27b1bdc121e679612a0e168e05f0ccf2a5179c8204886dc456a" | jq -e '.changed == false'

Pinned hash ca2ee912debb, from Nov 17, 2026, 07:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.fredyee/hallucc/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.fredyee/hallucc
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.fredyee/hallucc.svg)](https://radar.anlyon.com/servers/io.github.fredyee/hallucc)

Source: MCP Registry · repository. Synced Nov 17, 2026, 07:17 UTC.

HallucC — Hallucination & Safety Guardian MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the HallucC — Hallucination & Safety Guardian MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 7 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the HallucC — Hallucination & Safety Guardian MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the HallucC — Hallucination & Safety Guardian MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: check_cua_actions.

What tools does the HallucC — Hallucination & Safety Guardian MCP server have?

7 tools: 1 irreversible, 6 write. check_cua_actions, verify_text, verify_agent, check_cua_code_audit, check_safety, check_agent_ice_wall and reset_agent_ice_wall.

Does the HallucC — Hallucination & Safety Guardian MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the HallucC — Hallucination & Safety Guardian MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the HallucC — Hallucination & Safety Guardian MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.