# Apex Dev

> Apex Dev is a paid MCP server for agent tooling. Pre-execution spend and security gate for AI agents, with signed policy receipts. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API, Web
- **Website:** https://apexfaucet.xyz/firewall/
- **MCP Registry name:** xyz.apexfaucet/apex-dev
- **Categories:** [agent tooling](https://ai-powered.com/categories/agent-tooling)
- **Listing updated:** 2026-11-20

## About

The README and product page describe an API gate that an agent calls before it spends money or invokes an external tool. The check enforces per-transaction and daily USD caps, allowlists, prompt-injection and secret-leak blocking, and URL phishing checks, then returns an Ed25519-signed ALLOW, HOLD_FOR_HUMAN or DENY receipt that can be verified offline against the published JWKS.

The same vendor site lists a wide set of other endpoints, including page rendering, token lookups, CVE and npm/PyPI checks, and an MCP entry point at /api/mcp/dev.

The product is aimed at developers building orchestrators with MCP clients, LangGraph, the OpenAI Agents SDK or x402 wallets who need a policy layer before payments or tool calls. Access is per call over x402 or with an API key; the pricing page lists a $0.005 price for the firewall endpoint and a $5 card key option.

## Features

- **Spend caps and allowlists:** Enforces per-transaction and daily USD limits, a human-approval threshold, and payee or URL allowlists before an agent moves money.
- **Prompt-injection and PII blocking:** Optional checks that block prompt-injection attempts and personal data leaking out of an agent's request.
- **Signed policy receipts:** Returns an Ed25519-signed ALLOW, HOLD_FOR_HUMAN or DENY decision that can be stored in an audit log and verified offline.
- **URL phishing checks:** Screens target URLs for phishing before the agent calls them.
- **Live firewall simulator:** A browser simulator lets users test policy decisions, with 10 free evaluations per day.

## Good for

- Capping autonomous agent payments to a daily USD limit
- Routing high-value agent payments to a human for approval
- Blocking prompt-injection or secret exfiltration in agent tool calls
- Keeping a signed audit trail of every agent spend decision

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http apex-dev https://apexfaucet.xyz/api/mcp/dev
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://apexfaucet.xyz/api/mcp/dev
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "apex-dev": {
      "url": "https://apexfaucet.xyz/api/mcp/dev"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "apex-dev": {
      "type": "http",
      "url": "https://apexfaucet.xyz/api/mcp/dev"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "apex-dev": {
      "serverUrl": "https://apexfaucet.xyz/api/mcp/dev"
    }
  }
}
```

### Grok Bot (Grok Bot desktop app → Connect apps → Add a custom connector)

```sh
https://apexfaucet.xyz/api/mcp/dev
```

Enter a Name (for example "Apex Dev"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "apex-dev": {
      "type": "http",
      "url": "https://apexfaucet.xyz/api/mcp/dev"
    }
  }
}
```

## Tools

31 of 32 tools say they're read-only. 1 tool doesn't say. From the server's own tool annotations; not verified by us.

- `work_commons` (says read-only): APEX Synapse Deduplicated Work Commons: before spending $0.05+ and 15s computing an LLM, research, security audit, or quant analysis task from scratch, check the verified Proof-of-Work Commons for an instant (<5ms) Ed25519-graded deliverable (saving 90%+ cost & crediting an 80% royalty to the creator agent). Free explorer: https://apexfaucet.xyz/synapse/ . $0.002 per lookup over x402 or X-API-Key.
- `work_mint` (says read-only): Mint a verified AI agent work deliverable into the APEX Synapse Proof-of-Work Royalty Commons (https://apexfaucet.xyz/synapse/). Auto-grades quality via work-grade, issues an Ed25519 WorkAssetCertificate, and registers your agent for an 80% royalty share ($0.0016/lookup) every time another agent reuses your work via work_commons. $0.005 per mint over x402 or X-API-Key.
- `agent_memory` (says read-only): Agent memory. Persistent Cloud KV Memory & Inter-Agent Dead-Drop Blackboard: store, retrieve, list, or delete persistent JSON/text state across namespaces (op=set|get|list|delete, up to 30d TTL) with secret/PII leak protection, an Ed25519 storage receipt, and a free public read permalink (/api/memory/read/:ns/:key). Free playground: https://apexfaucet.xyz/memory/ . $0.001 per call over x402 or X-A
- `deep_research` (says read-only): Deep research. 1-Call Deep Web Research & Verified Citation Engine: queries Wikipedia, HackerNews, and ArXiv in parallel and synthesizes an executive brief, bulleted key facts, numbered URL citations [1..N], and an Ed25519 provenance receipt. Free playground: https://apexfaucet.xyz/memory/ . $0.003 per call over x402 or X-API-Key.
- `agent_spotlight` (says read-only): Pin your AI agent, MCP server, x402 API, or micro-bounty on the live APEX Global Agent Spotlight Wire (https://apexfaucet.xyz/memory/ + GET /api/spotlight/feed) for 24 hours. Auto-verifies HTTPS/anti-phishing safety via url-threat-check, issues an Ed25519 SpotlightCertificate, and announces on Telegram. $0.01 per 24h pin over x402 or X-API-Key.
- `ai_infra_status` (says read-only): Live outage & latency status radar across 9 AI + crypto backbone providers (OpenAI, Anthropic, Cloudflare, GitHub, Stripe, Coinbase, Base, Solana, Hyperliquid). 60s cached (<5ms) for high-frequency agent pre-flight checks. Free live board: https://apexfaucet.xyz/pulse/ . $0.001 per call over x402 or X-API-Key.
- `agent_firewall` (says read-only): Unified orchestrator access-control & pre-payment firewall for autonomous AI agents: enforces per-tx/daily USD spend caps, human-approval threshold, allowlists/denylists, HTTPS/phishing URL check, prompt-injection scan, and secret/PII exfiltration guard, returning an Ed25519-signed ALLOW / HOLD_FOR_HUMAN / DENY attestation verifiable offline via /.well-known/jwks.json. Free interactive tester (10/
- `work_grade` (says read-only): Grade any AI agent work deliverable before releasing escrow (ERC-8183 / G2 Jobs / MCP): checks JSON/schema validity, anti-refusal/stub quality, embedded indirect prompt injection, secret/PII leakage, and task alignment, returning an Ed25519-signed PASS_RELEASE / REVISE / REJECT_REFUND attestation verifiable offline via /.well-known/jwks.json. Free interactive tester (10/day): https://apexfaucet.xy
- `veritas_notary` (says read-only): Hash-chained Proof-of-Execution Notary for autonomous AI agents: links any workflow step to an optional parentReceiptHash, runs deterministic security/integrity checks (prompt injection, secret/PII leak, JSON validity), returns an Ed25519-signed VeritasReceipt with a free public verification URL (/veritas/?r=<hash>), and compounds the agent Machine Credit Score. Free 10/day demo: https://apexfauce
- `agent_credit` (says read-only): Machine Credit Bureau (300-950 autonomous AI agent credit & trust score): fuses Veritas Proof-of-Execution history and live domain hygiene to return an Ed25519-signed AgentCreditReport with directly pluggable agent-firewall spend limits (maxTxUsd, dailyCapUsd, humanApproveOverUsd, escrowCollateralPct). Free explorer: https://apexfaucet.xyz/veritas/ . $0.005 per call over x402 or X-API-Key.
- `agent_launch_audit` (says read-only): Comprehensive 1-call production launch readiness audit for any AI agent, MCP server, or x402 API domain: fuses A2A/MCP/x402/JWKS/llms.txt discovery grading, HTTPS/phishing threat checks, tech-stack detection, and optional live x402 delivery probe, returning prioritized revenue/discovery fixes and an Ed25519-signed LaunchReadinessCertificate verifiable offline via /.well-known/jwks.json. $0.02 per 
- `html_sanitize` (says read-only): Sanitize untrusted HTML before feeding to an LLM or UI: strips XSS scripts/iframes/on* handlers/javascript: URIs, detects & removes hidden CSS prompt-injection blocks, and returns safeHtml, clean Markdown, plainText & securityReport. $0.001 per call over x402 or X-API-Key. Call once without `payment` for terms, then call again with `payment`.
- `package_audit` (says read-only): npm and PyPI package security and supply-chain audit: checks registry existence (catches hallucinated packages), deprecation, install scripts, age, and Google OSV.dev CVEs/GHSAs with SAFE/CAUTION/RISKY verdict. $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `github_repo_intel` (says read-only): GitHub repository info and maintenance health intelligence: stars, forks, open issues, primary language, license, latest release, days since last push, 0-100 health score, and ACTIVE/MAINTAINED/STALE/ARCHIVED verdict. $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `cve_lookup` (says read-only): CVE vulnerability lookup by CVE ID or keyword combining official NVD 2.0, OSV.dev affected package versions, and CISA Known Exploited Vulnerabilities (KEV). $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `tech_stack_detect` (says read-only): Detect the technology stack of any public website (45+ CDNs, hosting, Next.js/React/Vue/Astro frameworks, CMS, analytics, Stripe/payments, auth, security). $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `url_threat_check` (says read-only): Check any URL for phishing, brand impersonation, Punycode/IDN homographs, credential tricks, executable downloads, DNS resolution, and redirect chain risk (SAFE/CAUTION/RISKY). $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `json_toolbox` (says read-only): Deterministic JSON Schema validator, structural JSON diff, dot-path query, flatten/unflatten, and JSON<->CSV converter. $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `json_repair` (says read-only): Clean and repair broken JSON from LLM outputs or scraped text (fences, trailing commas, single quotes, bare keys, Python literals, truncated brackets) ($0.001). $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for the terms, sign them with your own wallet, call again with `payment`.
- `qr_generate` (says read-only): Generate a scannable ISO 18004 QR code (SVG vector and/or base64 PNG data URI) for any URL, wallet address, payment URI, or text up to 271 bytes. $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `pdf_to_markdown` (says read-only): PDF to Markdown. Convert any public PDF URL or base64 PDF into clean LLM-ready Markdown with headings, bullet formatting, page markers, title/author metadata, and word count. $0.002 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `markdown_to_pdf` (says read-only): Convert Markdown (headings, GFM tables, fenced code blocks, lists, links) into a styled print-ready base64 PDF via hermetic sandboxed headless Chrome. $0.003 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `html_to_pdf` (says read-only): Convert raw HTML markup into a print-ready base64 PDF via hermetic sandboxed headless Chrome (no external network requests). $0.003 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `rss_to_json` (says read-only): Parse any public RSS 2.0, Atom 1.0, or JSON Feed URL into clean structured JSON items with ISO timestamps, authors, categories, and plain-text summaries. $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `fx_convert` (says read-only): Official ECB foreign exchange currency converter across 30+ major fiat currencies (USD, EUR, GBP, JPY, CHF, CAD, AUD, CNY, INR, BRL, etc.). Not financial advice. $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `whois_lookup` (says read-only): WHOIS and authoritative IANA RDAP domain registration lookup (registrar, IANA ID, creation/update/expiry dates, age in days, DNSSEC, EPP statuses, nameservers). $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `ip_geolocate` (says read-only): IP geolocation and ASN lookup for any public IPv4, IPv6, or hostname (country, region, city, lat/lon, timezone, ISP, org, ASN). $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `agent_card_grade` (says read-only): Audit and grade any AI agent domain or A2A agent card (/.well-known/agent-card.json, agent.json, mcp-server-card.json, x402, /llms.txt) with a 0-100 score, A+-F grade, and concrete fixes. $0.002 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `x402_price_comps` (says read-only): Live x402 market price comparison across 38,000+ indexed Coinbase Bazaar, Circle, and Arc paid APIs: min/p25/median/p75/max USD, suggested competitive price, and top competing endpoints. $0.002 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for terms, then call again with `payment`.
- `delivery_score`: Free sample: https://apexfaucet.xyz/delivery-score?url=https://apexfaucet.xyz/api/x402/page-markdown ($0.003). Score one https x402 URL from 0 to 100. Five parts of 0 to 20: watchtower 7-day uptime for that exact URL, a valid unpaid 402, the USDC price, how fast that probe was, and test buys we already recorded. This call does not pay the URL. A URL we have never bought scores 0 on test buys and s
- `prompt_guard` (says read-only): Prompt injection. Scan untrusted text for prompt injection, jailbreak attempts, delimiter spoofing, wallet exfiltration, and encoded payloads ($0.001). $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for the terms, sign them with your own wallet, call again with `payment`.
- `pii_redact` (says read-only): Detect and redact private keys, API tokens, JWTs, emails, IBANs, SSNs, phones, IPs, and Luhn-validated payment cards before LLM logging or sharing ($0.001). $0.001 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1). Call once without `payment` for the terms, sign them with your own wallet, call again with `payment`.

## FAQ

### How is the firewall called?

The README shows a POST request to the agent-firewall endpoint with an X-API-Key header or x402 payment, sending the agent ID, action, policy limits and target details.

### How is a receipt verified?

The site says receipts are verifiable offline using the public key published at /.well-known/jwks.json.

### What does one firewall call cost?

The product page lists $0.005 per call via x402 or with an API key.

### How do I add Apex Dev to Claude Code?

Run this command in your terminal: claude mcp add --transport http apex-dev https://apexfaucet.xyz/api/mcp/dev

### What are the best alternatives to Apex Dev?

The closest alternatives to Apex Dev are agentguard — policy proxy for agent tool calls, Imperium MCP Gateway — Universal 490+ Tool Discovery, Safe-Proxy & Router, Imperium Pre-Flight Readiness Auditor — A2A, MCP & x402 Validator, SatGate – Economic Firewall for AI Agents and ThoughtProof.

## Where this comes from

- Description: written from the project's website and its MCP Registry entry.
- Status and tools: checked automatically by AIPoweredBot on 21 November 2026.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [agentguard — policy proxy for agent tool calls](https://ai-powered.com/mcp/agentguard-policy-proxy-for-agent-tool-calls): agentguard — policy proxy for agent tool calls is a freemium MCP server for agent tooling.
- [Imperium MCP Gateway — Universal 490+ Tool Discovery, Safe-Proxy & Router](https://ai-powered.com/mcp/imperium-mcp-gateway-universal-490-tool-discovery-safe-proxy): Imperium MCP Gateway — Universal 490+ Tool Discovery, Safe-Proxy & Router is a paid MCP server for agent tooling.
- [Imperium Pre-Flight Readiness Auditor — A2A, MCP & x402 Validator](https://ai-powered.com/mcp/imperium-pre-flight-readiness-auditor-a2a-mcp-and-x402-valid): Imperium Pre-Flight Readiness Auditor — A2A, MCP & x402 Validator is a freemium MCP server for agent tooling.
- [SatGate – Economic Firewall for AI Agents](https://ai-powered.com/mcp/satgate-economic-firewall-for-ai-agents): SatGate – Economic Firewall for AI Agents is a freemium MCP server for agent tooling.
- [ThoughtProof](https://ai-powered.com/mcp/thoughtproof): ThoughtProof is a paid MCP server for agent tooling.
- [APEX AI, LLM, PDF, QR, JSON & Media MCP](https://ai-powered.com/mcp/apex-ai-llm-pdf-qr-json-and-media-mcp): APEX AI, LLM, PDF, QR, JSON & Media MCP is a freemium MCP server for files and documents.
- [VariantGate](https://ai-powered.com/mcp/variantgate): VariantGate is a freemium MCP server for agent tooling.
- [Agentiam MCP](https://ai-powered.com/mcp/agentiam-mcp): Agentiam MCP is an open-source MCP server for agent tooling.

---
Source: https://ai-powered.com/mcp/apex-dev
