apex-ai MCP server
xyz.apexfaucet/apex-aiapexfaucet.xyzstreamable-httpv1.3.0Scanned
AI, Synapse Work Royalties, Agent KV Memory, Deep Research, LLM, Vision, OCR & PDF MCP.
31 tools: 29 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 30
- Can send data out · 4
- 7 findings
Tools listed without sign-in. Remote posture
With Anlyon
29 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
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 apex-ai MCP server can do
The apex-ai MCP server is published by apexfaucet.xyz, a domain the MCP Registry verified. It has 31 tools. It can create or change data (29 tools: work_commons, work_mint, agent_memory, deep_research and 25 more), but cannot delete data. 2 tools only read.
1 tool reads private data (text_summarize); 30 tools bring in text other people can write (work_commons, work_mint, agent_memory and 27 more); 4 tools can send data out of your system (image_analyze, image_ocr, audio_transcribe and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 7 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 1.3.0.
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.
31 tools
Changes things 29Claude Code: ask
agent_memoryPersistent 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)…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 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-API-Key.
Annotations the server declares
- title: Agent memory
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
audio_transcribeTranscribe speech from any public audio URL (MP3/WAV/M4A/OGG/WebM/FLAC, max 15 MB) via Whisper Large v3 Turbo with optional timestamps.Reads text others writeCan send data outNo 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.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Transcribe speech from any public audio URL (MP3/WAV/M4A/OGG/WebM/FLAC, max 15 MB) via Whisper Large v3 Turbo with optional timestamps. $0.005 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`.
Annotations the server declares
- title: Audio transcribe
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
chat_completionsOpenAI-compatible LLM chat completion (gpt-oss-120b, gpt-oss-20b, llama-3.3-70b, llama-3.1-8b, qwen3-30b on Cloudflare Workers AI).No findings
Why it is in this group
- The description's first verb is "open": a word for a change.
Description, as the server wrote it OpenAI-compatible LLM chat completion (gpt-oss-120b, gpt-oss-20b, llama-3.3-70b, llama-3.1-8b, qwen3-30b on Cloudflare Workers AI). $0.002 per call over x402 (Base, Solana or X1). Call once without `payment` for terms, then pass `payment`.
content_safetyFast text content-safety & moderation check across CSAM, self-harm, violence/weapons, malware, phishing scams, and severe harassment ($0.001).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 Fast text content-safety & moderation check across CSAM, self-harm, violence/weapons, malware, phishing scams, and severe harassment ($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`.
Annotations the server declares
- title: Content safety
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
deep_research1-Call Deep Web Research & Verified Citation Engine: queries Wikipedia, HackerNews, and ArXiv in parallel and synthesizes an executive brief, bulleted key facts, numbered URL citat…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 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.
Annotations the server declares
- title: Deep research
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
html_sanitizeSanitize 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 …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 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`.
Annotations the server declares
- title: Html sanitize
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
html_to_pdfConvert raw HTML markup into a print-ready base64 PDF via hermetic sandboxed headless Chrome (no external network requests).Reads text others write1 finding
Why it is in this group
- The description's first verb is "convert": a word for a change.
- 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 server marks "html_to_pdf" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "convert": a word for a change.
Description, as the server wrote it 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`.
Annotations the server declares
- title: Html to pdf
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
image_generateGenerate a 1024x1024 JPEG image from a text prompt with FLUX.1 Schnell on Cloudflare Workers AI ($0.005).Reads text others write1 finding
Why it is in this group
- The name "image_generate" says "generate": a word for a change.
- 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 server marks "image_generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "image_generate" says "generate": a word for a change.
Description, as the server wrote it Generate a 1024x1024 JPEG image from a text prompt with FLUX.1 Schnell on Cloudflare Workers AI ($0.005). Sexual content, minors and graphic violence refused before payment. $0.005 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`.
Annotations the server declares
- title: Image generate
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
image_ocrExtract text from scanned documents, receipts, screenshots, or scanned PDFs (max 10 MB, up to 3 PDF pages) via sharp, Ghostscript (-dSAFER) and Tesseract OCR.Reads text others writeCan send data outNo 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.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Extract text from scanned documents, receipts, screenshots, or scanned PDFs (max 10 MB, up to 3 PDF pages) via sharp, Ghostscript (-dSAFER) and Tesseract OCR. $0.004 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`.
Annotations the server declares
- title: Image ocr
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
json_extractExtract structured JSON data from unstructured text (invoices, emails, receipts, pages) using fields or JSON Schema via Workers AI + deterministic JSON repair.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 Extract structured JSON data from unstructured text (invoices, emails, receipts, pages) using fields or JSON Schema via Workers AI + deterministic JSON repair. $0.005 per call over x402 (Base, Solana or X1) or X-API-Key. Call once without `payment` for terms, then pass `payment`.
Annotations the server declares
- title: Json extract
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
json_repairClean and repair broken JSON from LLM outputs or scraped text (fences, trailing commas, single quotes, bare keys, Python literals, truncated brackets) ($0.001).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 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`.
Annotations the server declares
- title: Json repair
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
json_toolboxDeterministic JSON Schema validator, structural JSON diff, dot-path query, flatten/unflatten, and JSON<->CSV converter.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 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`.
Annotations the server declares
- title: Json toolbox
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
llm_messagesAnthropic Messages API shape backed by open Workers AI models (gpt-oss-120b default, gpt-oss-20b, llama-3.3-70b, llama-3.1-8b, qwen3-30b).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 Anthropic Messages API shape backed by open Workers AI models (gpt-oss-120b default, gpt-oss-20b, llama-3.3-70b, llama-3.1-8b, qwen3-30b). $0.002 per call over x402 (Base, Solana or X1) or X-API-Key. Call once without `payment` for terms, then pass `payment`.
Annotations the server declares
- title: Llm messages
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
markdown_to_pdfConvert Markdown (headings, GFM tables, fenced code blocks, lists, links) into a styled print-ready base64 PDF via hermetic sandboxed headless Chrome.Reads text others write1 finding
Why it is in this group
- The description's first verb is "convert": a word for a change.
- 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 server marks "markdown_to_pdf" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "convert": a word for a change.
Description, as the server wrote it 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`.
Annotations the server declares
- title: Markdown to pdf
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
pdf_to_markdownConvert any public PDF URL or base64 PDF into clean LLM-ready Markdown with headings, bullet formatting, page markers, title/author metadata, and word count.Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "convert": a word for a change.
- 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.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "pdf_to_markdown" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "convert": a word for a change.
Description, as the server wrote it 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`.
Annotations the server declares
- title: Pdf to markdown
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
pii_redactDetect and redact private keys, API tokens, JWTs, emails, IBANs, SSNs, phones, IPs, and Luhn-validated payment cards before LLM logging or sharing ($0.001).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 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`.
Annotations the server declares
- title: Pii redact
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
prompt_guardScan untrusted text for prompt injection, jailbreak attempts, delimiter spoofing, wallet exfiltration, and encoded payloads ($0.001).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 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`.
Annotations the server declares
- title: Prompt guard
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
qr_generateGenerate 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.Reads text others write1 finding
Why it is in this group
- The name "qr_generate" says "generate": a word for a change.
- 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 server marks "qr_generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "qr_generate" says "generate": a word for a change.
Description, as the server wrote it 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`.
Annotations the server declares
- title: Qr generate
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
svg_generateGenerate a clean, sanitized standalone SVG vector graphic (icon, logo, badge, or diagram) from a text prompt.Reads text others write1 finding
Why it is in this group
- The name "svg_generate" says "generate": a word for a change.
- 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 server marks "svg_generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "svg_generate" says "generate": a word for a change.
Description, as the server wrote it Generate a clean, sanitized standalone SVG vector graphic (icon, logo, badge, or diagram) from a text prompt. $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`.
Annotations the server declares
- title: Svg generate
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
text_classifyClassify text into 12 built-in topics (crypto_defi, ai_agents, software_dev, security_privacy, finance_markets, ecommerce_retail, legal_compliance, support_ticket, marketing_sales,…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 Classify text into 12 built-in topics (crypto_defi, ai_agents, software_dev, security_privacy, finance_markets, ecommerce_retail, legal_compliance, support_ticket, marketing_sales, news_world, science_research, general) or custom labels (mode=fast|ai). $0.001 per call over x402 or X-API-Key. Call once without `payment` for terms, then call again with `payment`.
Annotations the server declares
- title: Text classify
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
text_embeddingsOpenAI-compatible BGE text embeddings for RAG and semantic search (bge-large-en-v1.5 1024d default, bge-base-en-v1.5, bge-small-en-v1.5, bge-m3 multilingual).Reads text others write1 finding
Why it is in this group
- The description's first verb is "open": a word for a change.
- 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 server marks "text_embeddings" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "open": a word for a change.
Description, as the server wrote it OpenAI-compatible BGE text embeddings for RAG and semantic search (bge-large-en-v1.5 1024d default, bge-base-en-v1.5, bge-small-en-v1.5, bge-m3 multilingual). $0.001 per call over x402 (Base, Solana or X1) or X-API-Key. Call once without `payment` for terms, then pass `payment`.
Annotations the server declares
- title: Text embeddings
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
text_keywordsDeterministic keyword, keyphrase, proper-noun, URL, email, hashtag, ticker, EVM-address, and amount extractor (<5 ms, up to 32,000 chars).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 Deterministic keyword, keyphrase, proper-noun, URL, email, hashtag, ticker, EVM-address, and amount extractor (<5 ms, up to 32,000 chars). $0.001 per call over x402 or X-API-Key. Call once without `payment` for terms, then call again with `payment`.
Annotations the server declares
- title: Text keywords
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
text_rewriteAI text rewrite & paraphrase in professional, concise, casual, technical, executive, plain, friendly, or formal tone while preserving facts & numbers (Llama 3.1 8B Fast).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 AI text rewrite & paraphrase in professional, concise, casual, technical, executive, plain, friendly, or formal tone while preserving facts & numbers (Llama 3.1 8B Fast). $0.001 per call over x402 or X-API-Key. Call once without `payment` for terms, then call again with `payment`.
Annotations the server declares
- title: Text rewrite
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
text_sentimentClassify text sentiment (fast sub-200ms DistilBERT SST-2 positive/negative, or 3-way positive/neutral/negative with mode="detailed") and optional custom zero-shot labels.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 Classify text sentiment (fast sub-200ms DistilBERT SST-2 positive/negative, or 3-way positive/neutral/negative with mode="detailed") and optional custom zero-shot labels. $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`.
Annotations the server declares
- title: Text sentiment
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
text_to_speechSynthesize spoken English MP3 audio (base64 audio_base64) from text (3-1000 chars) via Deepgram Aura-2.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 Synthesize spoken English MP3 audio (base64 audio_base64) from text (3-1000 chars) via Deepgram Aura-2. $0.004 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`.
Annotations the server declares
- title: Text to speech
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
text_translateTranslate text across 100 languages using Meta M2M100 1.2B AI.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 Translate text across 100 languages using Meta M2M100 1.2B AI. $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`.
Annotations the server declares
- title: Text translate
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
work_commonsAPEX 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-…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 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.
Annotations the server declares
- title: Work commons
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
work_gradeGrade 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, …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 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.xyz/grade/ . $0.004 per call over x402 or X-API-Key. Call once without `payment` for terms, then call again with `payment`.
Annotations the server declares
- title: Work grade
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
work_mintMint a verified AI agent work deliverable into the APEX Synapse Proof-of-Work Royalty Commons (https://apexfaucet.xyz/synapse/).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 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.
Annotations the server declares
- title: Work mint
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
image_analyzeAnalyze any public image URL (max 8 MB) with technical metadata plus Llama 3.2 11B Vision scene, object, and visible-text analysis.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "image_analyze" says "analyze": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "analyze" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Analyze any public image URL (max 8 MB) with technical metadata plus Llama 3.2 11B Vision scene, object, and visible-text analysis. $0.005 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`.
Annotations the server declares
- title: Image analyze
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
text_summarizeSummarize articles, docs, or transcripts into concise bullets, a paragraph, or a 1-sentence TL;DR via Llama 3.1 8B Fast AI.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "text_summarize" says "summarize": a word for reading.
What it can reach
- private-dataThe description's first sentence says "summarize" and "doc": it reads documents.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Summarize articles, docs, or transcripts into concise bullets, a paragraph, or a 1-sentence TL;DR via Llama 3.1 8B Fast AI. $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`.
Annotations the server declares
- title: Text summarize
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- 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.
120 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write30
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__apex-ai__text_summarize"
]
}
}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.
Looked at Nov 19, 2026, 17:20 UTC, unchanged since Nov 19, 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
- 25
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 25 tools that change things (25 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://apexfaucet.xyz/api/mcp/ai: tools/list returned 27 tools to an anonymous client, including chat_completions (write), llm_messages (write), text_embeddings (write), json_extract (write), json_repair (write) and 20 more
Findings
Matches of fixed checks, with the text they matched.
- Warntext_embeddings
The server marks "text_embeddings" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "open": a word for a change.
- Warnsvg_generate
The server marks "svg_generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "svg_generate" says "generate": a word for a change.
- Warnqr_generate
The server marks "qr_generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "qr_generate" says "generate": a word for a change.
- Warnimage_generate
The server marks "image_generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "image_generate" says "generate": a word for a change.
- Warnhtml_to_pdf
The server marks "html_to_pdf" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "convert": a word for a change.
- Warnmarkdown_to_pdf
The server marks "markdown_to_pdf" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "convert": a word for a change.
Show 1 more findingShow fewer
- Warnpdf_to_markdown
The server marks "pdf_to_markdown" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "convert": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools4 added.+4 addedView diff
- Added:agent_memoryChanges things
- Added:deep_researchChanges things
- Added:work_commonsChanges things
- Added:work_mintChanges things
Tools5 added.+5 addedView diff
- Added:html_sanitizeChanges things
- Added:text_classifyChanges things
- Added:text_keywordsChanges things
- Added:text_rewriteChanges things
- Added:work_gradeChanges things
Tools3 added.+3 addedView diff
- Added:json_toolboxChanges things
- Added:pdf_to_markdownChanges things
- Added:qr_generateChanges things
Install
Pinned to version 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http apex-ai https://apexfaucet.xyz/api/mcp/aiclaude mcp add --transport http apex-ai https://apexfaucet.xyz/api/mcp/aiRun 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.
{
"permissions": {
"allow": [
"mcp__apex-ai__text_summarize"
],
"ask": [
"mcp__apex-ai__work_commons",
"mcp__apex-ai__work_mint",
"mcp__apex-ai__agent_memory",
"mcp__apex-ai__deep_research",
"mcp__apex-ai__chat_completions",
"mcp__apex-ai__llm_messages",
"mcp__apex-ai__text_embeddings",
"mcp__apex-ai__json_extract",
"mcp__apex-ai__json_repair",
"mcp__apex-ai__json_toolbox",
"mcp__apex-ai__text_rewrite",
"mcp__apex-ai__text_keywords",
"mcp__apex-ai__text_classify",
"mcp__apex-ai__text_translate",
"mcp__apex-ai__text_sentiment",
"mcp__apex-ai__work_grade",
"mcp__apex-ai__svg_generate",
"mcp__apex-ai__qr_generate",
"mcp__apex-ai__image_generate",
"mcp__apex-ai__image_analyze",
"mcp__apex-ai__image_ocr",
"mcp__apex-ai__audio_transcribe",
"mcp__apex-ai__text_to_speech",
"mcp__apex-ai__html_to_pdf",
"mcp__apex-ai__markdown_to_pdf",
"mcp__apex-ai__pdf_to_markdown",
"mcp__apex-ai__html_sanitize",
"mcp__apex-ai__prompt_guard",
"mcp__apex-ai__pii_redact",
"mcp__apex-ai__content_safety"
],
"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 apex-ai. Review it before you use it.
Capability tags behind 30 rules
- mcp__apex-ai__work_commons untrusted-input
- mcp__apex-ai__work_mint untrusted-input
- mcp__apex-ai__agent_memory untrusted-input
- mcp__apex-ai__deep_research untrusted-input
- mcp__apex-ai__llm_messages untrusted-input
- mcp__apex-ai__text_embeddings untrusted-input
- mcp__apex-ai__json_extract untrusted-input
- mcp__apex-ai__json_repair untrusted-input
- mcp__apex-ai__json_toolbox untrusted-input
- mcp__apex-ai__text_rewrite untrusted-input
- mcp__apex-ai__text_keywords untrusted-input
- mcp__apex-ai__text_classify untrusted-input
- mcp__apex-ai__text_translate untrusted-input
- mcp__apex-ai__text_summarize private-data, untrusted-input
- mcp__apex-ai__text_sentiment untrusted-input
- mcp__apex-ai__work_grade untrusted-input
- mcp__apex-ai__svg_generate untrusted-input
- mcp__apex-ai__qr_generate untrusted-input
- mcp__apex-ai__image_generate untrusted-input
- mcp__apex-ai__image_analyze untrusted-input, outbound
- mcp__apex-ai__image_ocr untrusted-input, outbound
- mcp__apex-ai__audio_transcribe untrusted-input, outbound
- mcp__apex-ai__text_to_speech untrusted-input
- mcp__apex-ai__html_to_pdf untrusted-input
- mcp__apex-ai__markdown_to_pdf untrusted-input
- mcp__apex-ai__pdf_to_markdown untrusted-input, outbound
- mcp__apex-ai__html_sanitize untrusted-input
- mcp__apex-ai__prompt_guard untrusted-input
- mcp__apex-ai__pii_redact untrusted-input
- mcp__apex-ai__content_safety 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/xyz.apexfaucet/apex-ai/verify?hash=e3750fb97b5a857590459519aea9bc7470914e6fe72c19edb4ceef8ed7f27038" | jq -e '.changed == false'Pinned hash e3750fb97b5a, from Nov 19, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/xyz.apexfaucet/apex-ai/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/xyz.apexfaucet/apex-ai)Source: MCP Registry. Synced Nov 19, 2026, 20:18 UTC.
apex-ai MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the apex-ai MCP server safe?
- No scan can promise that. What its definitions show: 31 tools, 29 of which can change, send or delete something, and 7 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 apex-ai MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the apex-ai MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the apex-ai MCP server have?
- 31 tools: 29 write, 2 read. work_commons, work_mint, agent_memory, deep_research, chat_completions, llm_messages, text_embeddings, json_extract and 23 more.
Does the apex-ai MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the apex-ai MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): image_analyze, image_ocr, audio_transcribe and pdf_to_markdown.
Has the apex-ai MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.