MAD Synapse · Web & Research
Read the web (page text, DNS, WHOIS, TLS, uptime) + research (Wikipedia, arXiv, GitHub, packages).
我该使用它吗
质量与安全性
发现（3）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 package_info 中
- INFOTool description contains placeholder or incomplete text在 hn_search 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"synapse-web": {
"url": "https://agent.maddegen.art/hub/mcp/web"
}
}
}远程端点
https://agent.maddegen.art/hub/mcp/webstreamable-http它能做什么
工具清单
工具（15）
🟢web_read(url, max_chars, include_links)
Any public URL → clean readable markdown: the article/main content without nav, ads or boilerplate, plus title, author, date, word count and links. PDFs too. Fetches the page (redirects followed, public internet only), extracts the main content with Mozilla Readability and converts it to markdown. PDFs are converted to text. Use max_chars to bound the output. JavaScript-only pages return whatever the server sends (no headless browser). When to use: For a page's content; for its metadata only use web_meta; for uptime/redirects use http_probe. Price: $0.002 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "http(s) URL"
},
"max_chars": {
"type": "integer",
"minimum": 500,
"maximum": 100000,
"default": 20000,
"description": "Truncate the returned markdown to this many characters. Range 500-100000. Default 20000."
},
"include_links": {
"type": "boolean",
"default": false,
"description": "keep hyperlinks (absolute) in the markdown and return a link list. Default false."
}
},
"required": [
"url"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"url": {
"type": [
"string",
"null"
]
},
"status": {
"type": [
"number",
"null"
]
},
"type": {
"type": [
"string",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
},
"byline": {
"type": [
"string",
"null"
]
},
"site": {
"type": [
"string",
"null"
]
},
"published": {
"type": [
"string",
"null"
]
},
"lang": {
"type": [
"string",
"null"
]
},
"excerpt": {
"type": [
"string",
"null"
]
},
"words": {
"type": [
"number",
"null"
]
},
"truncated": {
"type": [
"boolean",
"null"
]
},
"markdown": {
"type": [
"string",
"null"
]
},
"extracted_with": {
"type": [
"string",
"null"
]
}
}
}🟢web_meta(url)
Everything a page says about itself: title, description, OpenGraph/Twitter card, canonical, favicon, language, RSS/Atom feeds, JSON-LD schema types, headings — and link-preview problems. Use to build link previews, check SEO/social cards, find a site's feeds or structured data. Flags missing og:image, missing description and non-absolute image URLs (common reasons a link shows up bare on X/Telegram). When to use: For title/OpenGraph/canonical; for the article text use web_read. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Absolute http(s) URL of the page."
}
},
"required": [
"url"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"url": {
"type": [
"string",
"null"
]
},
"status": {
"type": [
"number",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"canonical": {
"type": [
"string",
"null"
]
},
"lang": {
"type": [
"string",
"null"
]
},
"favicon": {
"type": [
"string",
"null"
]
},
"apple_touch_icon": {},
"manifest": {},
"robots": {},
"opengraph": {
"type": [
"object",
"null"
],
"properties": {
"og:type": {
"type": [
"string",
"null"
]
},
"og:title": {
"type": [
"string",
"null"
]
},
"og:description": {
"type": [
"string",
"null"
]
},
"og:url": {
"type": [
"string",
"null"
]
},
"og:image": {
"type": [
"string",
"null"
]
}
}
},
"twitter": {
"type": [
"object",
"null"
],
"properties": {
"twitter:card": {
"type": [
"string",
"null"
]
},
"twitter:site": {
"type": [
"string",
"null"
]
},
"twitter:image": {
"type": [
"string",
"null"
]
}
}
},
"feeds": {
"type": "array"
},
"json_ld_types": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"h1": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"h2": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"link_preview_problems": {
"type": "array"
}
}
}🟢dns_lookup(domain)
All DNS for a domain — A, AAAA, CNAME, MX, NS, TXT, CAA, SOA — plus SPF and DMARC parsed and graded, so an agent knows where a domain points and whether its email can be spoofed. Queried live against public resolvers (Cloudflare, Google, Quad9). Email grade: SPF present and ending in -all/~all, DMARC present with p=quarantine/reject. When to use: For DNS records; for ownership dates use domain_whois; for certificates use tls_check. Price: free. Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain name without scheme, e.g. \"example.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"domain": {
"type": [
"string",
"null"
]
},
"resolves": {
"type": [
"boolean",
"null"
]
},
"a": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"aaaa": {
"type": "array"
},
"cname": {
"type": "array"
},
"mx": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"exchange": {
"type": [
"string",
"null"
]
},
"priority": {
"type": [
"number",
"null"
]
}
}
}
},
"ns": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"txt": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"caa": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"critical": {
"type": [
"number",
"null"
]
},
"issue": {
"type": [
"string",
"null"
]
},
"issuewild": {
"type": [
"string",
"null"
]
}
}
}
},
"soa": {
"type": [
"object",
"null"
],
"properties": {
"nsname": {
"type": [
"string",
"null"
]
},
"hostmaster": {
"type": [
"string",
"null"
]
},
"serial": {
"type": [
"number",
"null"
]
},
"refresh": {
"type": [
"number",
"null"
]
},
"retry": {
"type": [
"number",
"null"
]
},
"expire": {
"type": [
"number",
"null"
]
},
"minttl": {
"type": [
"number",
"null"
]
}
}
},
"email_security": {
"type": [
"object",
"null"
],
"properties": {
"grade": {
"type": [
"string",
"null"
]
},
"spf": {
"type": [
"string",
"null"
]
},
"dmarc": {
"type": [
"string",
"null"
]
},
"dmarc_policy": {
"type": [
"string",
"null"
]
},
"issues": {
"type": "array"
}
}
}
}
}🟢domain_whois(domain)
Who registered a domain and when: registrar, creation/expiry dates, age, days to expiry, status locks, nameservers — or that it looks available to register. Uses RDAP, the registries' official successor to WHOIS (rdap.org bootstrap). A domain with no RDAP record and no DNS is reported as likely available. Young domains (< 30 days) are flagged: most phishing/scam sites are days old. When to use: For registration and expiry; for DNS records use dns_lookup. Price: $0.002 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Registrable domain without scheme, e.g. \"example.com\"."
}
},
"required": [
"domain"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"domain": {
"type": [
"string",
"null"
]
},
"registered": {
"type": [
"boolean",
"null"
]
},
"registrar": {
"type": [
"object",
"null"
],
"properties": {
"name": {
"type": [
"string",
"null"
]
},
"iana_id": {
"type": [
"string",
"null"
]
}
}
},
"created": {
"type": [
"string",
"null"
]
},
"updated": {
"type": [
"string",
"null"
]
},
"expires": {
"type": [
"string",
"null"
]
},
"age_days": {
"type": [
"number",
"null"
]
},
"days_to_expiry": {
"type": [
"number",
"null"
]
},
"young_domain_warning": {
"type": [
"boolean",
"null"
]
},
"status": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"nameservers": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"dnssec": {
"type": [
"boolean",
"null"
]
},
"registrant": {
"type": [
"object",
"null"
],
"properties": {
"name": {
"type": [
"string",
"null"
]
},
"iana_id": {}
}
},
"source": {
"type": [
"string",
"null"
]
}
}
}🟢tls_check(host, port)
A site's TLS certificate: issuer, validity, days until expiry, SANs, protocol, cipher, chain and whether browsers trust it. Live TLS handshake to the host. Flags expired, expiring (< 14 days), untrusted or name-mismatched certificates. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"host": {
"type": "string",
"description": "Hostname without scheme or path, e.g. \"example.com\"."
},
"port": {
"type": "integer",
"minimum": 1,
"maximum": 65535,
"default": 443,
"description": "TCP port serving TLS. Range 1-65535. Default 443."
}
},
"required": [
"host"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"host": {
"type": [
"string",
"null"
]
},
"port": {
"type": [
"number",
"null"
]
},
"handshake_ms": {
"type": [
"number",
"null"
]
},
"protocol": {
"type": [
"string",
"null"
]
},
"cipher": {
"type": [
"string",
"null"
]
},
"alpn": {
"type": [
"string",
"null"
]
},
"trusted": {
"type": [
"boolean",
"null"
]
},
"trust_error": {},
"subject": {
"type": [
"string",
"null"
]
},
"issuer": {
"type": [
"string",
"null"
]
},
"issuer_cn": {
"type": [
"string",
"null"
]
},
"valid_from": {
"type": [
"string",
"null"
]
},
"valid_to": {
"type": [
"string",
"null"
]
},
"days_left": {
"type": [
"number",
"null"
]
},
"san": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"serial": {
"type": [
"string",
"null"
]
},
"fingerprint_sha256": {
"type": [
"string",
"null"
]
},
"key_bits": {
"type": [
"number",
"null"
]
},
"chain": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"subject": {
"type": [
"string",
"null"
]
},
"issuer": {
"type": [
"string",
"null"
]
},
"valid_to": {
"type": [
"string",
"null"
]
}
}
}
},
"warnings": {
"type": "array"
},
"ok": {
"type": [
"boolean",
"null"
]
}
}
}🟢http_probe(url)
Is a site up and how is it served: status, full redirect chain, timings (DNS/TLS/first byte/total), server, CDN, caching, compression, and a graded security-header check (HSTS, CSP, frame, sniffing…). One real GET from our server. The security grade counts HSTS, Content-Security-Policy, X-Frame-Options/frame-ancestors, X-Content-Type-Options, Referrer-Policy and Permissions-Policy. When to use: For availability, status and timings; for page content use web_read. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Absolute http(s) URL to probe."
}
},
"required": [
"url"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"url": {
"type": [
"string",
"null"
]
},
"final_url": {
"type": [
"string",
"null"
]
},
"up": {
"type": [
"boolean",
"null"
]
},
"status": {
"type": [
"number",
"null"
]
},
"redirects": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"url": {
"type": [
"string",
"null"
]
},
"status": {
"type": [
"number",
"null"
]
},
"ms": {
"type": [
"number",
"null"
]
}
}
}
},
"timing_ms": {
"type": [
"object",
"null"
],
"properties": {
"dns_connect": {
"type": [
"number",
"null"
]
},
"tls": {
"type": [
"number",
"null"
]
},
"first_byte": {
"type": [
"number",
"null"
]
},
"total": {
"type": [
"number",
"null"
]
}
}
},
"server": {
"type": [
"string",
"null"
]
},
"powered_by": {},
"cdn": {
"type": [
"string",
"null"
]
},
"remote_ip": {
"type": [
"string",
"null"
]
},
"content_type": {
"type": [
"string",
"null"
]
},
"bytes": {
"type": [
"number",
"null"
]
},
"compressed": {
"type": [
"boolean",
"null"
]
},
"cache_control": {},
"http_tls": {
"type": [
"object",
"null"
],
"properties": {
"protocol": {
"type": [
"string",
"null"
]
},
"cipher": {
"type": [
"string",
"null"
]
},
"authorized": {
"type": [
"boolean",
"null"
]
},
"subject": {
"type": [
"string",
"null"
]
},
"issuer": {
"type": [
"string",
"null"
]
},
"valid_to": {
"type": [
"string",
"null"
]
}
}
},
"security_headers": {
"type": [
"object",
"null"
],
"properties": {
"hsts": {
"type": [
"boolean",
"null"
]
},
"csp": {
"type": [
"boolean",
"null"
]
},
"frame_protection": {
"type": [
"boolean",
"null"
]
},
"nosniff": {
"type": [
"boolean",
"null"
]
},
"referrer_policy": {
"type": [
"boolean",
"null"
]
},
"permissions_policy": {
"type": [
"boolean",
"null"
]
},
"grade": {
"type": [
"string",
"null"
]
}
}
}
}
}🟢robots_check(url, user_agent)
May I crawl this? Checks a URL against the site's robots.txt for any user-agent, lists sitemaps and crawl-delay, and reports which AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended…) the site blocks. Standard robots.txt matching (longest match wins, Allow beats Disallow on ties, * and $ wildcards). Missing robots.txt = everything allowed. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Absolute URL you intend to crawl."
},
"user_agent": {
"type": "string",
"default": "MAD-Synapse",
"description": "User-agent token to evaluate the rules for. Default \"MAD-Synapse\"."
}
},
"required": [
"url"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"url": {
"type": [
"string",
"null"
]
},
"robots_txt": {
"type": [
"string",
"null"
]
},
"user_agent": {
"type": [
"string",
"null"
]
},
"path": {
"type": [
"string",
"null"
]
},
"allowed": {
"type": [
"boolean",
"null"
]
},
"matched_group": {
"type": [
"string",
"null"
]
},
"rule": {
"type": [
"string",
"null"
]
},
"crawl_delay": {},
"sitemaps": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"ai_crawlers_site_root": {
"type": [
"object",
"null"
],
"properties": {
"GPTBot": {
"type": [
"string",
"null"
]
},
"ChatGPT-User": {
"type": [
"string",
"null"
]
},
"OAI-SearchBot": {
"type": [
"string",
"null"
]
},
"ClaudeBot": {
"type": [
"string",
"null"
]
},
"Claude-User": {
"type": [
"string",
"null"
]
},
"Claude-SearchBot": {
"type": [
"string",
"null"
]
},
"anthropic-ai": {
"type": [
"string",
"null"
]
},
"Google-Extended": {
"type": [
"string",
"null"
]
},
"PerplexityBot": {
"type": [
"string",
"null"
]
},
"Perplexity-User": {
"type": [
"string",
"null"
]
},
"CCBot": {
"type": [
"string",
"null"
]
},
"Bytespider": {
"type": [
"string",
"null"
]
},
"Applebot-Extended": {
"type": [
"string",
"null"
]
},
"Meta-ExternalAgent": {
"type": [
"string",
"null"
]
},
"Amazonbot": {
"type": [
"string",
"null"
]
},
"cohere-ai": {
"type": [
"string",
"null"
]
},
"Diffbot": {
"type": [
"string",
"null"
]
},
"DuckAssistBot": {
"type": [
"string",
"null"
]
},
"MistralAI-User": {
"type": [
"string",
"null"
]
}
}
},
"groups": {
"type": [
"number",
"null"
]
}
}
}🟢email_check(email)
Will this email address work? Syntax, domain MX records, disposable/throwaway provider detection, role address (info@, admin@) and free-mail provider — without sending anything. No SMTP probing (that gets servers blacklisted); the verdict is from syntax, live MX lookup and a maintained list of ~100k disposable domains. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"email": {
"type": "string",
"description": "Email address to check. No mail is sent."
}
},
"required": [
"email"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"email": {
"type": [
"string",
"null"
]
},
"valid_syntax": {
"type": [
"boolean",
"null"
]
},
"domain": {
"type": [
"string",
"null"
]
},
"mx": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"exchange": {
"type": [
"string",
"null"
]
},
"priority": {
"type": [
"number",
"null"
]
}
}
}
},
"accepts_mail": {
"type": [
"boolean",
"null"
]
},
"disposable": {
"type": [
"boolean",
"null"
]
},
"role_address": {
"type": [
"boolean",
"null"
]
},
"free_provider": {
"type": [
"boolean",
"null"
]
},
"verdict": {
"type": [
"string",
"null"
]
}
}
}🟢wiki(query, lang, full, max_chars)
Wikipedia in any language: search a topic and get the best article's summary, description, thumbnail and link — or the full article text. Search + REST summary from Wikipedia. full=true returns the article as plain text (sections kept), capped by max_chars. Disambiguation pages are flagged with alternatives. When to use: For encyclopedic topics; for papers use arxiv_search or doi_lookup. Price: free. Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Topic or article title to look up."
},
"lang": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z]+)?$",
"default": "en",
"description": "Wikipedia language code, e.g. \"en\", \"de\", \"pt-br\". Default \"en\"."
},
"full": {
"type": "boolean",
"default": false,
"description": "true = return the full article text, not just the summary. Default false."
},
"max_chars": {
"type": "integer",
"minimum": 500,
"maximum": 60000,
"default": 8000,
"description": "Truncate full article text to this many characters (with full=true). Range 500-60000. Default 8000."
}
},
"required": [
"query"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"found": {
"type": [
"boolean",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
},
"description": {},
"summary": {
"type": [
"string",
"null"
]
},
"type": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"thumbnail": {
"type": [
"string",
"null"
]
},
"last_edited": {
"type": [
"string",
"null"
]
},
"other_matches": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"title": {
"type": [
"string",
"null"
]
},
"snippet": {
"type": [
"string",
"null"
]
}
}
}
}
}
}🟢arxiv_search(query, sort, limit)
Search arXiv research papers by keywords, author or category — newest or most relevant — with abstracts, authors, dates and PDF links. arXiv's official API. query supports arXiv syntax (ti:, au:, abs:, cat:cs.AI, AND/OR). Paced to arXiv's one-request-per-3-seconds policy and cached, so repeated queries are instant. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "e.g. \"tool use agents\" or au:hinton or cat:cs.CL AND ti:reasoning"
},
"sort": {
"type": "string",
"enum": [
"relevance",
"newest"
],
"default": "relevance",
"description": "Order by relevance to the query or by submission date. One of \"relevance\", \"newest\". Default \"relevance\"."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 30,
"default": 10,
"description": "How many papers to return. Range 1-30. Default 10."
}
},
"required": [
"query"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"query": {
"type": [
"string",
"null"
]
},
"total_results": {
"type": [
"number",
"null"
]
},
"papers": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"id": {
"type": [
"string",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
},
"authors": {
"type": "array"
},
"published": {
"type": [
"string",
"null"
]
},
"updated": {
"type": [
"string",
"null"
]
},
"categories": {
"type": "array"
},
"abstract": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"pdf": {
"type": [
"string",
"null"
]
}
}
}
}
}
}🟢package_info(name, ecosystem)
Any npm, PyPI or crates.io package: latest version and release date, license, downloads, maintainers, repo, dependency count, deprecation — to pick or vet a dependency. Straight from each registry (plus npm and pypistats download counts). Flags deprecated packages and ones with no release in 2+ years. When to use: For package metadata; for known vulnerabilities in a version use vuln_check (on the MAD Synapse · Wallets & Risk server, https://agent.maddegen.art/hub/mcp/risk). Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Exact package name as published, e.g. \"express\" or \"requests\"."
},
"ecosystem": {
"type": "string",
"enum": [
"npm",
"pypi",
"crates"
],
"default": "npm",
"description": "Registry to look in. One of \"npm\", \"pypi\", \"crates\". Default \"npm\"."
}
},
"required": [
"name"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"ecosystem": {
"type": [
"string",
"null"
]
},
"name": {
"type": [
"string",
"null"
]
},
"latest": {
"type": [
"string",
"null"
]
},
"released": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
},
"deprecated": {},
"weekly_downloads": {
"type": [
"number",
"null"
]
},
"versions": {
"type": [
"number",
"null"
]
},
"dependencies": {
"type": [
"number",
"null"
]
},
"repository": {
"type": [
"string",
"null"
]
},
"homepage": {
"type": [
"string",
"null"
]
},
"maintainers": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"stale": {},
"url": {
"type": [
"string",
"null"
]
}
}
}🟢github_repo(repo)
A GitHub repository at a glance: stars, forks, open issues, last commit, latest release, license, languages, contributors, archived — is it alive and trustworthy? From the GitHub REST API. "activity" summarizes days since last push and last release so an agent can judge whether a project is maintained. Price: $0.002 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"repo": {
"type": "string",
"description": "owner/name or a github.com URL"
}
},
"required": [
"repo"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"repo": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"homepage": {
"type": [
"string",
"null"
]
},
"stars": {
"type": [
"number",
"null"
]
},
"forks": {
"type": [
"number",
"null"
]
},
"watchers": {
"type": [
"number",
"null"
]
},
"open_issues_and_prs": {
"type": [
"number",
"null"
]
},
"default_branch": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
},
"topics": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"archived": {
"type": [
"boolean",
"null"
]
},
"is_fork": {
"type": [
"boolean",
"null"
]
},
"parent": {},
"created": {
"type": [
"string",
"null"
]
},
"last_push": {
"type": [
"string",
"null"
]
},
"latest_release": {
"type": [
"object",
"null"
],
"properties": {
"tag": {
"type": [
"string",
"null"
]
},
"name": {
"type": [
"string",
"null"
]
},
"date": {
"type": [
"string",
"null"
]
},
"prerelease": {
"type": [
"boolean",
"null"
]
}
}
},
"languages_pct": {
"type": [
"object",
"null"
],
"properties": {
"TypeScript": {
"type": [
"number",
"null"
]
},
"JavaScript": {
"type": [
"number",
"null"
]
},
"Just": {
"type": [
"number",
"null"
]
},
"Shell": {
"type": [
"number",
"null"
]
},
"CSS": {
"type": [
"number",
"null"
]
}
}
},
"top_contributors": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"login": {
"type": [
"string",
"null"
]
},
"commits": {
"type": [
"number",
"null"
]
}
}
}
},
"activity": {
"type": [
"object",
"null"
],
"properties": {
"days_since_push": {
"type": [
"number",
"null"
]
},
"days_since_release": {
"type": [
"number",
"null"
]
},
"verdict": {
"type": [
"string",
"null"
]
}
}
}
}
}🟢hn_search(query, type, sort, days, min_points, ...)
Search Hacker News stories and comments by keyword, sorted by relevance or date, filtered by time window and minimum points — what developers are saying about anything. Algolia's official HN search. Returns title, url, points, comment count, author, date and the HN discussion link. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keywords to search for."
},
"type": {
"type": "string",
"enum": [
"story",
"comment",
"show_hn",
"ask_hn"
],
"default": "story",
"description": "Stories, comments, Show HN or Ask HN posts. One of \"story\", \"comment\", \"show_hn\", \"ask_hn\". Default \"story\"."
},
"sort": {
"type": "string",
"enum": [
"relevance",
"date"
],
"default": "relevance",
"description": "Order by relevance or newest first. One of \"relevance\", \"date\". Default \"relevance\"."
},
"days": {
"type": "integer",
"minimum": 1,
"maximum": 3650,
"default": 365,
"description": "Only items from the last N days. Range 1-3650. Default 365."
},
"min_points": {
"type": "integer",
"minimum": 0,
"default": 0,
"description": "Only items with at least this many points. Default 0."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 15,
"description": "How many results to return. Range 1-50. Default 15."
}
},
"required": [
"query"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"query": {
"type": [
"string",
"null"
]
},
"total": {
"type": [
"number",
"null"
]
},
"results": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"title": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"text": {
"type": [
"string",
"null"
]
},
"points": {
"type": [
"number",
"null"
]
},
"comments": {
"type": [
"number",
"null"
]
},
"author": {
"type": [
"string",
"null"
]
},
"date": {
"type": [
"string",
"null"
]
},
"hn": {
"type": [
"string",
"null"
]
}
}
}
}
}
}🟢doi_lookup(doi, query, limit)
Resolve a DOI — or search a paper title — to full citation metadata: title, authors, journal, year, citations count, publisher, license, and a ready-made APA/BibTeX citation. Crossref's open metadata (150M+ works). Search mode returns the top matches for a title/author query. When to use: For citation metadata of a known paper; to search preprints by topic use arxiv_search. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"doi": {
"type": "string",
"description": "e.g. 10.1038/nature14539"
},
"query": {
"type": "string",
"description": "title/author search instead of a DOI"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"default": 5,
"description": "How many matches to return when searching by title. Range 1-20. Default 5."
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"found": {
"type": [
"boolean",
"null"
]
},
"doi": {
"type": [
"string",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
},
"authors": {
"type": "array",
"items": {
"type": [
"string",
"null"
]
}
},
"year": {
"type": [
"number",
"null"
]
},
"journal": {
"type": [
"string",
"null"
]
},
"publisher": {
"type": [
"string",
"null"
]
},
"type": {
"type": [
"string",
"null"
]
},
"volume": {
"type": [
"string",
"null"
]
},
"issue": {
"type": [
"string",
"null"
]
},
"pages": {
"type": [
"string",
"null"
]
},
"cited_by": {
"type": [
"number",
"null"
]
},
"references": {
"type": [
"number",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"apa": {
"type": [
"string",
"null"
]
},
"bibtex": {
"type": [
"string",
"null"
]
}
}
}🟢book_search(query, limit)
Find books by title, author, subject or ISBN: first published year, editions, ISBNs, page count, ratings, subjects and cover image. Open Library (Internet Archive) catalogue of 30M+ titles. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "title, author or ISBN"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"default": 5,
"description": "How many books to return. Range 1-20. Default 5."
}
},
"required": [
"query"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"total": {
"type": [
"number",
"null"
]
},
"books": {
"type": "array",
"items": {
"type": [
"object",
"null"
],
"properties": {
"title": {
"type": [
"string",
"null"
]
},
"authors": {
"type": "array"
},
"first_published": {
"type": [
"number",
"null"
]
},
"editions": {
"type": [
"number",
"null"
]
},
"pages_median": {
"type": [
"number",
"null"
]
},
"rating": {
"type": [
"number",
"null"
]
},
"ratings": {
"type": [
"number",
"null"
]
},
"isbn": {
"type": "array"
},
"publishers": {
"type": "array"
},
"languages": {
"type": "array"
},
"subjects": {
"type": "array"
},
"cover": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
}
}
}
}
}
}社区
证据