Agent Hub MCP Server

by torbrooknews-mcp Your server? Claim it

answering

Agent Hub is answering right now. Last checked 2 min ago. It exposes 71 tools.

48 pay-per-call tools: search, scraping, PDF, OCR, LLM, crypto, DeFi, SEC. x402 USDC.

Uptime history 5 days of history · worst day 99%

5 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

549 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 21

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 13 October 2026. No other catalogue keeps this.

13 Oct 18 tools appeared audio_speech, audio_transcriptions, coder_chat_completions and 15 more

13 Oct 2 tool descriptions were rewritten chat_completions, token_report

13 Oct a tool changed the parameters it asks for chat_completions

Agent Hub missed one check this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-hub --transport http https://mcp.torbrooknews.com/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agent-hub": {
      "url": "https://mcp.torbrooknews.com/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.agent-hub]
url = "https://mcp.torbrooknews.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "agent-hub": {
      "url": "https://mcp.torbrooknews.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "agent-hub": {
      "url": "https://mcp.torbrooknews.com/mcp"
    }
  }
}

Available tools 71

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

token

token_chart

Price history for any token contract: a time series at 5m to 1w intervals (up to 500 points) with open, close, high, low and percent change. Works for DEX-only tokens. Costs $0.003 USDC per call (x402).

token_price

USD price and 24h change for any token by contract address (up to 30 at once) on Base, Ethereum, Polygon, Arbitrum, Optimism, BSC, Avalanche, Solana or World Chain. Covers long-tail DEX tokens that ticker-based price feeds miss. Costs $0.002 USDC per call (x402).

token_report

Token risk report with a plain-English AI verdict for any token on Base, Ethereum, Polygon, Arbitrum, Optimism or Solana. EVM: honeypot sell simulation, buy/sell tax, verified source, upgradeable proxy, owner, supply, holders, main pool liquidity, price and 24h change, plus a low/medium/high/critical risk rating. Costs $0.01 USDC per call (x402).

token_scan

Batch token risk scan: up to 5 tokens in one call, any mix of Base, Ethereum, Polygon, Arbitrum, Optimism and Solana. Each gets a risk rating, red flags, price and liquidity; the riskiest one is named. For screening a watchlist, a wallet's holdings or a list of new launches. Costs $0.02 USDC per call (x402).

token_solana

Solana token risk report (rug check) for any SPL or Token-2022 mint: mint and freeze authority, top-holder and developer concentration, serial-launcher check, Jupiter suspicious flag, liquidity, pool age, organic trading score, holders, price and market cap, a low/medium/high/critical rating and a plain-English AI verdict. Costs $0.01 USDC per call (x402).

token_verdict

Quick AI token verdict: a 2-3 sentence plain-English risk summary plus risk level and red flags for any token on Base, Ethereum, Polygon, Arbitrum, Optimism or Solana. Built on honeypot sell simulation and tax checks (EVM) or mint/freeze authority and holder concentration (Solana). Half the price of the full report. Costs $0.005 USDC per call (x402).

audio

audio_speech

OpenAI-compatible text to speech (MeloTTS): same request shape as OpenAI /v1/audio/speech (input, voice, model); returns a WAV file. Languages en, es, fr, zh, jp, kr via language. Up to 2000 characters, flat price, no API key. Costs $0.005 USDC per call (x402).

audio_transcriptions

OpenAI-compatible speech to text (Whisper large v3 turbo): multipart file upload exactly like OpenAI /v1/audio/transcriptions, with response_format json, text, srt, vtt or verbose_json. Also accepts a public audio url. Up to 20 MB, flat price, no API key. Costs $0.01 USDC per call (x402).

company

company

Company profile from a domain: reads the website and returns name, tagline, description, industry, products, audience, headquarters, founding year and business model, plus contact emails, phone numbers and social profiles (LinkedIn, X, GitHub...). Costs $0.01 USDC per call (x402).

company_registry

Official legal-entity registry lookup (GLEIF Global LEI Index, 200+ jurisdictions): legal name, LEI, active/inactive status, legal form, jurisdiction, company registration number and authority, legal and headquarters address, creation date and direct parent. Search by name (optionally country) or by LEI. For KYB, compliance and due diligence. Costs $0.003 USDC per call (x402).

defi

defi_tvl

Total value locked for a DeFi protocol (aave, uniswap, aerodrome, lido...) and/or a chain (Base, Ethereum, Solana...), with the chain's TVL rank. Costs $0.002 USDC per call (x402).

defi_yields

Best DeFi yields across 16,000+ pools: filter by chain, protocol, token symbol, stablecoin-only and minimum TVL; sort by APY or TVL. Returns APY (base + reward), 30-day mean APY, TVL, IL risk and a link. Costs $0.003 USDC per call (x402).

gpt

gpt_oss_20b_chat_completions

OpenAI-compatible chat completions on OpenAI gpt-oss-20b open-weight reasoning model with tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/gpt-oss-20b and pay $0.003 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Costs $0.003 USDC per call (x402).

gpt_oss_chat_completions

OpenAI-compatible chat completions on OpenAI gpt-oss-120b, the strongest open-weight OpenAI model, reasoning with tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/gpt-oss and pay $0.006 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Costs $0.006 USDC per call (x402).

image

image_describe

Describe an image and read every piece of visible text in it (vision LLM). Send a public image URL or base64 image; optional custom question. Works for receipts, screenshots, signs and charts. Costs $0.01 USDC per call (x402).

image_generate

Generate an image from a text prompt (FLUX.1 schnell). Returns JPEG bytes. Good for thumbnails, social posts, mockups and illustrations. Costs $0.02 USDC per call (x402).

llm

llm

Pay-per-call LLM chat completion (Llama 3.1 8B, fast), no API key. Send OpenAI-style messages, get the assistant reply. Flat price per request, up to 2k output tokens. Costs $0.005 USDC per call (x402).

llm_large

Pay-per-call LLM chat completion on Llama 3.3 70B for harder reasoning, no API key. Same OpenAI-style messages body as /v1/llm. Flat price per request, up to 2k output tokens. Costs $0.01 USDC per call (x402).

chat

chat_completions

OpenAI-compatible chat completions on Meta Llama 3.1 8B, fast general chat. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1 and pay $0.003 per request with x402 instead of an API key. Same request/response shape as OpenAI (streaming supported), up to 2048 output tokens. Pass model to switch to any same-price model listed at /v1/models. Costs $0.003 USDC per call (x402).

coder

coder_chat_completions

OpenAI-compatible chat completions on Qwen 2.5 Coder 32B for code generation, review and fixes. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/coder and pay $0.006 per request with x402 instead of an API key. Same request/response shape as OpenAI (streaming supported), up to 2048 output tokens. Costs $0.006 USDC per call (x402).

crypto

crypto_price

Live crypto prices with 24h change and market cap. Pass symbols (btc,eth,sol) or CoinGecko ids, up to 50 coins, in up to 10 currencies (usd,cad,eur...). Costs $0.002 USDC per call (x402).

devtools

devtools

Developer toolbox in one call: sha256/sha1/sha512 hashes, base64/url/hex encode and decode, JWT decode, JSON format/validate, UUIDs, secure random numbers and passwords, regex test, slugify, word count and timestamp conversion. Costs $0.002 USDC per call (x402).

document

document

Document to text: convert PDF, Word (docx), Excel (xlsx/xls), ODS/ODT, CSV, HTML, XML or images to clean Markdown. Send a public file URL or base64 file plus filename (max 15 MB). Costs $0.01 USDC per call (x402).

domain

domain

Domain lookup: availability, registrar, created and expiry dates (RDAP/WHOIS), nameservers, A/AAAA/MX/NS/TXT records, and whether the site answers over HTTPS. Costs $0.002 USDC per call (x402).

economy

economy

Macroeconomic indicators for any country: GDP growth, inflation, unemployment, GDP, GDP per capita, government debt, budget balance, current account and population (IMF World Economic Outlook, including forecasts), plus World Bank interest rates, exports, FDI and more; ECB policy rate for euro countries. Costs $0.003 USDC per call (x402).

email_verify

Verify an email address: syntax check, domain MX lookup, disposable-domain and role-account flags. Use before sending or storing an address. Costs $0.002 USDC per call (x402).

embed

embed

Text embeddings for semantic search and RAG (BGE-M3, multilingual, 1024 dimensions). Up to 100 texts per call, one flat price. Costs $0.002 USDC per call (x402).

embeddings

embeddings

OpenAI-compatible embeddings endpoint (bge-m3, 1024 dimensions, 100+ languages): same request and response shape as OpenAI /v1/embeddings, including encoding_format base64. Up to 100 inputs per call, flat price, no API key: point any OpenAI SDK at https://agents.torbrooknews.com/v1 and pay per request with x402. Costs $0.002 USDC per call (x402).

ens

ens

Crypto name lookup: resolve ENS and Basenames (vitalik.eth, jesse.base.eth) to a wallet address with avatar, url, twitter and description records, or reverse-resolve a 0x address to its primary name. Costs $0.002 USDC per call (x402).

extract

extract

Extract structured JSON from any web page. Give a URL plus a JSON schema or a plain-English prompt describing the fields you want; a headless browser renders the page and an LLM fills the schema. Costs $0.03 USDC per call (x402).

facts

facts

Fact lookup for grounding: best-matching Wikipedia article summary plus structured Wikidata facts (website, founding date, birth/death dates, population, coordinates) and the source link. Any language edition. Costs $0.002 USDC per call (x402).

filings

filings

US public company filings and fundamentals from SEC EDGAR: latest annual revenue, net income, EPS, assets, liabilities, cash, shares, plus recent 10-K/10-Q/8-K filings with links. Query by ticker or CIK. Costs $0.005 USDC per call (x402).

fun

fun

Something fun on demand: a joke, a true fun fact, a riddle with answer, a famous quote, a trivia question or a piece of life advice. Costs $0.002 USDC per call (x402).

fx

Live foreign-exchange rates (ECB reference, 30+ currencies) and conversion. Query base, symbols and an optional amount. Costs $0.002 USDC per call (x402).

gas

gas

Live gas prices on Ethereum, Base, Arbitrum, Optimism and Polygon: gas price, next base fee, slow/normal/fast priority tips, and USD cost of a simple transfer. Costs $0.002 USDC per call (x402).

gemma

gemma_chat_completions

OpenAI-compatible chat completions on Google Gemma 4 26B, reasoning and tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/gemma and pay $0.002 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Costs $0.002 USDC per call (x402).

geocode

geocode

Geocode a place, landmark or street address to latitude/longitude with city, region, country, postcode, timezone and population where known. Cities via GeoNames, addresses and points of interest via OpenStreetMap. Costs $0.002 USDC per call (x402).

glm

glm_chat_completions

OpenAI-compatible chat completions on Zhipu GLM 4.7 Flash, reasoning and tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/glm and pay $0.003 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Costs $0.003 USDC per call (x402).

holidays

holidays

Public holidays for 100+ countries (optional state/province), plus business-day math: count business days between two dates, add N business days to a date, or check if a date is a business day. Costs $0.002 USDC per call (x402).

images

images_generations

OpenAI-compatible image generation (FLUX.1 schnell): same shape as OpenAI /v1/images/generations, returns b64_json (or a data URL with response_format=url). One 1024px JPEG per call, flat price, no API key. Costs $0.01 USDC per call (x402).

ip

IP address and ASN lookup from the internet registries (RDAP): network name and range, owning organization, country, origin ASN, abuse contact email, registration dates and reverse DNS. Pass ip= (IPv4/IPv6) or asn=. Costs $0.002 USDC per call (x402).

large

large_chat_completions

OpenAI-compatible chat completions on Meta Llama 3.3 70B, strong general chat with tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/large and pay $0.01 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, streaming supported), up to 2048 output tokens. Costs $0.01 USDC per call (x402).

llama4

llama4_chat_completions

OpenAI-compatible chat completions on Meta Llama 4 Scout, multimodal (image input) with tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/llama4 and pay $0.004 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, image input, streaming supported), up to 2048 output tokens. Costs $0.004 USDC per call (x402).

markdown

markdown

Fetch any public web page with a real headless browser (JavaScript rendered) and return clean Markdown. Use to read articles, docs, product pages or SPAs that a plain fetch cannot render. Costs $0.01 USDC per call (x402).

mistral

mistral_chat_completions

OpenAI-compatible chat completions on Mistral Small 3.1 24B, tool calling and image input. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/mistral and pay $0.003 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, image input, streaming supported), up to 2048 output tokens. Costs $0.003 USDC per call (x402).

moderate

moderate

Safety check (Llama Guard 3): classify up to 10 texts as safe or unsafe with hazard categories (violence, weapons, hate, self-harm, sexual content, privacy, elections and more). Check user input or your own reply before posting. Costs $0.002 USDC per call (x402).

moderations

moderations

OpenAI-compatible moderation (Llama Guard 3): same response shape as OpenAI /v1/moderations with flagged, categories and category_scores, plus the raw Llama Guard codes. Up to 10 inputs per call. Costs $0.002 USDC per call (x402).

nemotron

nemotron_chat_completions

OpenAI-compatible chat completions on NVIDIA Nemotron 3 120B, agentic reasoning with tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/nemotron and pay $0.01 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Costs $0.01 USDC per call (x402).

news

news

Latest news headlines matching a query from 12 major outlets (BBC, NPR, Guardian, Al Jazeera, CBC, CNBC, NYT, TechCrunch, Verge, Ars Technica, CoinDesk, ESPN) plus Hacker News. Titles, links, source and time. Costs $0.005 USDC per call (x402).

nft

nft

NFT lookup on Ethereum, Base, Polygon, Arbitrum or Optimism: collection name, symbol, standard and supply; with token_id also the current owner and resolved metadata (name, description, image, attributes) from IPFS/Arweave/HTTP. Costs $0.003 USDC per call (x402).

papers

papers

Academic paper search across 250M+ works (OpenAlex): title, authors, year, venue, DOI, open-access PDF link, citation count and abstract. Sort by relevance, most recent or most cited. Costs $0.003 USDC per call (x402).

pdf

pdf

Render a URL or raw HTML to a PDF file with a headless browser. Returns the PDF bytes. Use for invoices, reports, receipts, archiving pages. Costs $0.02 USDC per call (x402).

perps

perps

Perpetual futures market data from Hyperliquid: mark and oracle price, 24h change, hourly and annualized funding rate, open interest, 24h volume, premium and max leverage. Pick coins or get the top markets by volume. Costs $0.002 USDC per call (x402).

predictions

predictions

Live prediction market odds from Polymarket: search any topic or get the most-traded markets. Returns each outcome's implied probability, 24h and total volume, liquidity, end date and link. Costs $0.002 USDC per call (x402).

qwen

qwen_chat_completions

OpenAI-compatible chat completions on Alibaba Qwen3 30B mixture-of-experts, thinking model with tool calling, the cheapest chat here. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/qwen and pay $0.002 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Costs $0.002 USDC per call (x402).

rerank

rerank

Rerank up to 100 documents by relevance to a query (BGE reranker). Returns indices and scores, best first. Drop-in step for RAG and search pipelines. Costs $0.002 USDC per call (x402).

rpc

rpc

JSON-RPC read access to EVM chains (base, ethereum, polygon, arbitrum, optimism) with no API key. Send a standard JSON-RPC body (eth_call, eth_getBalance, eth_blockNumber, eth_getLogs). Costs $0.002 USDC per call (x402).

scrape

scrape

Scrape text and attributes from a rendered web page using CSS selectors. Returns every match per selector. Costs $0.01 USDC per call (x402).

screenshot

screenshot

Full-page PNG screenshot of any public URL rendered by a real browser. Returns PNG bytes. Costs $0.02 USDC per call (x402).

search

Web search for AI agents. Send a natural-language query, get ranked results with title, url and snippet. Use when you need fresh information from the live web. Costs $0.006 USDC per call (x402).

sentiment

sentiment

Sentiment and tone classification for text (positive / negative / neutral with confidence, plus a one-line reason). Batch up to 20 texts per call. Costs $0.002 USDC per call (x402).

seo

seo

SEO audit of a page: score, list of issues, title and meta description length, canonical, robots, Open Graph, H1/H2 headings, images missing alt text, internal/external links, broken-link check on 25 links, word count and response time. Costs $0.02 USDC per call (x402).

serp

serp

Search engine results page in the familiar SERP shape: organic_results with position, title, link, displayed_link, domain, favicon and snippet, plus total results and top domains. Up to 20 results. For SEO, rank tracking and research agents. Costs $0.006 USDC per call (x402).

sitemap

sitemap

List every page on a website: reads robots.txt and all sitemaps (including sitemap indexes), with last-modified dates; falls back to on-page links. Up to 5000 URLs. Costs $0.02 USDC per call (x402).

speak

speak

Text to speech. Send up to 2000 characters and a language (en, es, fr, zh, jp, kr); get a natural-sounding WAV recording back. Costs $0.01 USDC per call (x402).

summarize

summarize

Summarize any web page or long text. A headless browser renders the URL, an LLM writes a faithful summary: short (2-3 sentences), medium (one paragraph) or bullets. Costs $0.02 USDC per call (x402).

time

time

Trusted current time (or a given moment) in UTC, unix seconds/ms, and up to 20 IANA time zones with local time, weekday and UTC offset. Also converts a timestamp between zones. Costs $0.002 USDC per call (x402).

transcribe

transcribe

Speech to text (Whisper large v3 turbo). Send a public audio/video URL or base64 audio (max 20 MB); get the transcript, detected language, timed segments and WebVTT subtitles. Costs $0.02 USDC per call (x402).

translate

translate

Translate text between about 100 languages (M2M-100). One text or a batch of up to 20; give target_lang and optionally source_lang (default en). Costs $0.003 USDC per call (x402).

wallet

wallet

Wallet snapshot on Base or Ethereum: native ETH balance, nonzero balances of the major tokens (USDC, USDT, WETH, DAI, cbBTC, WBTC and more), transaction count and contract flag. Costs $0.003 USDC per call (x402).

weather

weather

Current weather and up to 14-day forecast for any place name or lat/lon: temperature, feels-like, humidity, rain chance, wind, sunrise and sunset. Metric or imperial. Costs $0.002 USDC per call (x402).

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.torbrooknews.com/mcp	streamable-http	answering	602 ms	2 min ago

Alternatives to Agent Hub

same job, measured the same way

Webbersites X402 Data API

by webberdesign

45 pay-per-call AI agent tools: scraping, SEO, crypto data, lint, agent memory. x402 USDC on Base.

78 tools answering

Webbersites X402 MCP

by webberdesign

45 pay-per-call AI agent tools + wallet-owned agent memory. Scraping, SEO, lint, crypto. x402 USDC

33 installs/wk local only

Citiview Agent Market

by citiviewgroup-mcp

186 pay-per-call tools: search, LLMs, UK KYB, FRED, Census, maps, crypto. x402 USDC.

211 tools answering

Agent Data API

by ptrgit1

19 pay-per-call data tools for AI agents: crypto/DeFi, web, PDF, FX, weather, DNS. x402 on Base.

54 installs/wk local only

x402 Seller

by entreprisedaney33-rgb

Pay-per-call MCP tools (crypto/DeFi data, web reading, AI tasks) in USDC over x402 on Base.

38 installs/wk local only

Gate402 MCP

by pgalyen1987

x402 pay-per-call agent APIs: LLM inference, Base trading data, SEC filings & scraping

80 installs/wk local only

ThirdMade Shelf

by thirdmade

26 pay-per-call tools for agents: scrape, verify, guards, crypto. x402 USDC on Base.

26 tools answering

Agent Web Reader

by charliemorrison

Pay-per-call data tools for AI agents: crypto signal, web reader, SEO audit. x402 USDC on Base.

3 tools answering

Agent Hub — questions

Answers built from our own checks of this server.

What can Agent Hub do?

It exposes 71 tools, read directly from the server on our last check. Among them: audio_speech, audio_transcriptions, chat_completions, coder_chat_completions, company, company_registry and 65 more. 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 →

What is Agent Hub mostly used for?

Its tools cluster around token, audio and gpt. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is Agent Hub working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 549 ms. The bar chart above shows every period we have measured.

How do I connect Agent Hub?

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 Agent Hub need an API key?

No. Agent Hub completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 71 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Agent Hub?

It answers our handshake in 549 ms on average, which is faster than 20% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.