mcpbeat

Values Firewall MCP Server

by humanified
answering

Values Firewall is answering right now. Last checked 1 min ago. It exposes 3 tools.

EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.

Uptime history 7 hours of history
7 hours agonow
100.0%
Uptime 24h
22 of 22 checks
3
Tools
read from the server
347 ms
Response time
average over 24h
open, no key
Access
streamable-http

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

run in your terminal
claude mcp add values-firewall --transport http https://vf.humanified.dk/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "values-firewall": {
      "url": "https://vf.humanified.dk/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.values-firewall]
url = "https://vf.humanified.dk/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "values-firewall": {
      "url": "https://vf.humanified.dk/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "values-firewall": {
      "url": "https://vf.humanified.dk/mcp"
    }
  }
}

Available tools 3

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

action
check_action
Kerne-gaten (to-lags evaluering): Lag A (deterministisk hard-rule/outward-match, ingen LLM) + Lag B (Sonnet vurderer mod charterets NL-principper via LiteLLM :4000, citerer principle_id + reasoning — INGEN egen alvorligheds-dom) → most-restrictive-wins aggregeret, auditerbar receipt: {action, deterministic_flags[], values_assessment[], values_assessment_unavailable, unrecognized_principle_citations, principles_evaluated, recommendation, requires_human, charter_name, scope_note}. `recommendation` ∈ {allow, flag, gate_to_human} — ALDRIG approved/denied/true/false. ADVISORY: anbefaler, blokerer/eksekverer/autoriserer ALDRIG (never-decide-for-you). FAIL-SAFE: Lag B utilgængelig -> Lag A kører stadig, values_assessment_unavailable=true, recommendation løftet til MINDST 'flag' (aldrig stille 'allow'). Read-only — skriver INTET, ingen side-effekter. PUBLIC_DEMO-mode: vurderet mod det OFFENTLIGE Art-14-demo-charter (ikke din org — se scope_note). Rate-limitet (default 5/min + 30/time, ÉN global demo-bucket). Over grænsen returneres `{error:"rate_limited", retry_after_s, scope_note}` — ALDRIG et recommendation-formet svar. Bogholderi-fejl i rate-limiteren -> deny (fail-safe). RED-TEAM-FIX (minimal-indgreb): tomt/whitespace-only `action` valideres FØR rate-limiteren forbruger en kvote-token — en ugyldig-input-loop kan ellers stille dræne demoens kvote uden at nogensinde levere en receipt (rå ValueError fra firewall.check_action's fail-loud-guard ville ellers både forbruge kvote OG propagere ubehandlet til transport-laget, hvilket bryder "check_action leverer ALTID en receipt/struktureret fejl"-disciplinen). Uden for PUBLIC_DEMO uændret: fw.check_action's egen ValueError-fail-loud gælder stadig (bindende, testet i test_values_firewall.py).
check_action_deterministic
KUN Lag A — ingen LLM-kald overhovedet (billig, ren mekanisk, spejler consistency-gates check_triple). Samme receipt-form som check_action, men values_assessment er altid tom, values_assessment_unavailable altid false, og scope_note siger eksplicit 'values_layer_consulted:false'. Read-only. PUBLIC_DEMO-mode: ÅBEN, GRATIS — ALDRIG rate-begrænset (spec §2, ingen LLM-kost). Vurderet mod det offentlige Art-14-demo-charter; scope_note får demo-disclosuren appended.
charter
list_charter
Transparens: hvilke regler/principper håndhæver DENNE firewall lige nu — navn/version/ hard_rules/outward_patterns/principles. Values-locked (arvet): firewall'en håndhæver KUN dette deklarerede charter, opfinder aldrig regler/principper udenfor det. PUBLIC_DEMO-mode: ÅBEN, GRATIS — ALDRIG rate-begrænset. Viser det OFFENTLIGE Art-14-demo- charter (6 principper, 4 hard_rules, 14 outward_patterns) — ikke noget kunde-/fleet-/ TIER-1-charter. Får et `scope_note`-felt med demo-disclosuren tilføjet (fraværende i default-mode — additiv, ingen bestående felter ændres).

Endpoints

URLTransportStateLatencyChecked
https://vf.humanified.dk/mcp streamable-http answering 328 ms 1 min ago

Alternatives to Values Firewall

same job, measured the same way
N
Glyt
by glyt

Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.

6 tools answering
Multimail
by multimail

Give your agent its own email address with graduated human oversight, from approval to autonomy.

103 installs/wk answering
N
Gate
by agenticrail

Deterministic gate for AI agents: ALLOW/DENY a step before it runs, sealed to a verifiable receipt.

2 tools answering
Consentgate MCP
by jessepetersondev

Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.

28 installs/wk local only
A
Gateway
by duvera

Governed AI actions with signed, verifiable receipts: free keyless reads, human-approved writes.

52 tools answering
Baton
by vinsenzo83

Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs.

28 installs/wk 45 tools answering
Kasbah MCP
by al-adnane

Governance layer for agentic AI — signed, verifiable receipts for every agent action.

41 installs/wk local only
Boundaryai
by boundaryai

Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.

answering

Values Firewall — questions

Answers built from our own checks of this server.

What can Values Firewall do?
It exposes 3 tools, read directly from the server on our last check. Among them: check_action, check_action_deterministic, list_charter. 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 →
Is Values Firewall working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 22 of 22 checks got a reply (100.0%), average response time 347 ms. The bar chart above shows every period we have measured.
How do I connect Values Firewall?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Values Firewall need an API key?
No. Values Firewall completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 3 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Values Firewall?
It answers our handshake in 347 ms on average, which is faster than 43% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.