MCP Server
MAD Synapse · Web & Research
art.maddegen.agent/synapse-web
What this MCP does
Reads public web pages and searches research sources while providing DNS, WHOIS, TLS, HTTP, package, repository, and email checks.
Capabilities
Tools
15
tools
arxiv_search
arXiv paper search
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['query'], 'properties': {'sort': {'enum': ['relevance', 'newest'], 'type': 'string', 'default': 'relevance', 'description': 'Order by relevance to the query or by submission date. One of "relevance", "newest". Default "relevance".'}, 'limit': {'type': 'integer', 'default': 10, 'maximum': 30, 'minimum': 1, 'description': 'How many papers to return. Range 1-30. Default 10.'}, 'query': {'type': 'string', 'description': 'e.g. "tool use agents" or au:hinton or cat:cs.CL AND ti:reasoning'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'query': {'type': ['string', 'null']}, 'papers': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'id': {'type': ['string', 'null']}, 'pdf': {'type': ['string', 'null']}, 'url': {'type': ['string', 'null']}, 'title': {'type': ['string', 'null']}, 'authors': {'type': 'array'}, 'updated': {'type': ['string', 'null']}, 'abstract': {'type': ['string', 'null']}, 'published': {'type': ['string', 'null']}, 'categories': {'type': 'array'}}}}, 'total_results': {'type': ['number', 'null']}}}
book_search
Book search
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'default': 5, 'maximum': 20, 'minimum': 1, 'description': 'How many books to return. Range 1-20. Default 5.'}, 'query': {'type': 'string', 'description': 'title, author or ISBN'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'books': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'url': {'type': ['string', 'null']}, 'isbn': {'type': 'array'}, 'cover': {'type': ['string', 'null']}, 'title': {'type': ['string', 'null']}, 'rating': {'type': ['number', 'null']}, 'authors': {'type': 'array'}, 'ratings': {'type': ['number', 'null']}, 'editions': {'type': ['number', 'null']}, 'subjects': {'type': 'array'}, 'languages': {'type': 'array'}, 'publishers': {'type': 'array'}, 'pages_median': {'type': ['number', 'null']}, 'first_published': {'type': ['number', 'null']}}}}, 'total': {'type': ['number', 'null']}}}
dns_lookup
DNS records + email security
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['domain'], 'properties': {'domain': {'type': 'string', 'description': 'Domain name without scheme, e.g. "example.com".'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'a': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'mx': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'exchange': {'type': ['string', 'null']}, 'priority': {'type': ['number', 'null']}}}}, 'ns': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'caa': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'issue': {'type': ['string', 'null']}, 'critical': {'type': ['number', 'null']}, 'issuewild': {'type': ['string', 'null']}}}}, 'soa': {'type': ['object', 'null'], 'properties': {'retry': {'type': ['number', 'null']}, 'expire': {'type': ['number', 'null']}, 'minttl': {'type': ['number', 'null']}, 'nsname': {'type': ['string', 'null']}, 'serial': {'type': ['number', 'null']}, 'refresh': {'type': ['number', 'null']}, 'hostmaster': {'type': ['string', 'null']}}}, 'txt': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'aaaa': {'type': 'array'}, 'cname': {'type': 'array'}, 'domain': {'type': ['string', 'null']}, 'resolves': {'type': ['boolean', 'null']}, 'email_security': {'type': ['object', 'null'], 'properties': {'spf': {'type': ['string', 'null']}, 'dmarc': {'type': ['string', 'null']}, 'grade': {'type': ['string', 'null']}, 'issues': {'type': 'array'}, 'dmarc_policy': {'type': ['string', 'null']}}}}}
doi_lookup
Citation / DOI lookup
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'doi': {'type': 'string', 'description': 'e.g. 10.1038/nature14539'}, 'limit': {'type': 'integer', 'default': 5, 'maximum': 20, 'minimum': 1, 'description': 'How many matches to return when searching by title. Range 1-20. Default 5.'}, 'query': {'type': 'string', 'description': 'title/author search instead of a DOI'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'apa': {'type': ['string', 'null']}, 'doi': {'type': ['string', 'null']}, 'url': {'type': ['string', 'null']}, 'type': {'type': ['string', 'null']}, 'year': {'type': ['number', 'null']}, 'found': {'type': ['boolean', 'null']}, 'issue': {'type': ['string', 'null']}, 'pages': {'type': ['string', 'null']}, 'title': {'type': ['string', 'null']}, 'bibtex': {'type': ['string', 'null']}, 'volume': {'type': ['string', 'null']}, 'authors': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'journal': {'type': ['string', 'null']}, 'license': {'type': ['string', 'null']}, 'cited_by': {'type': ['number', 'null']}, 'publisher': {'type': ['string', 'null']}, 'references': {'type': ['number', 'null']}}}
domain_whois
Domain WHOIS / RDAP + availability
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['domain'], 'properties': {'domain': {'type': 'string', 'description': 'Registrable domain without scheme, e.g. "example.com".'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'dnssec': {'type': ['boolean', 'null']}, 'domain': {'type': ['string', 'null']}, 'source': {'type': ['string', 'null']}, 'status': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'created': {'type': ['string', 'null']}, 'expires': {'type': ['string', 'null']}, 'updated': {'type': ['string', 'null']}, 'age_days': {'type': ['number', 'null']}, 'registrar': {'type': ['object', 'null'], 'properties': {'name': {'type': ['string', 'null']}, 'iana_id': {'type': ['string', 'null']}}}, 'registered': {'type': ['boolean', 'null']}, 'registrant': {'type': ['object', 'null'], 'properties': {'name': {'type': ['string', 'null']}, 'iana_id': {}}}, 'nameservers': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'days_to_expiry': {'type': ['number', 'null']}, 'young_domain_warning': {'type': ['boolean', 'null']}}}
email_check
Email address check
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['email'], 'properties': {'email': {'type': 'string', 'description': 'Email address to check. No mail is sent.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'mx': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'exchange': {'type': ['string', 'null']}, 'priority': {'type': ['number', 'null']}}}}, 'email': {'type': ['string', 'null']}, 'domain': {'type': ['string', 'null']}, 'verdict': {'type': ['string', 'null']}, 'disposable': {'type': ['boolean', 'null']}, 'accepts_mail': {'type': ['boolean', 'null']}, 'role_address': {'type': ['boolean', 'null']}, 'valid_syntax': {'type': ['boolean', 'null']}, 'free_provider': {'type': ['boolean', 'null']}}}
github_repo
GitHub repo health
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['repo'], 'properties': {'repo': {'type': 'string', 'description': 'owner/name or a github.com URL'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'url': {'type': ['string', 'null']}, 'repo': {'type': ['string', 'null']}, 'forks': {'type': ['number', 'null']}, 'stars': {'type': ['number', 'null']}, 'parent': {}, 'topics': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'created': {'type': ['string', 'null']}, 'is_fork': {'type': ['boolean', 'null']}, 'license': {'type': ['string', 'null']}, 'activity': {'type': ['object', 'null'], 'properties': {'verdict': {'type': ['string', 'null']}, 'days_since_push': {'type': ['number', 'null']}, 'days_since_release': {'type': ['number', 'null']}}}, 'archived': {'type': ['boolean', 'null']}, 'homepage': {'type': ['string', 'null']}, 'watchers': {'type': ['number', 'null']}, 'last_push': {'type': ['string', 'null']}, 'description': {'type': ['string', 'null']}, 'languages_pct': {'type': ['object', 'null'], 'properties': {'CSS': {'type': ['number', 'null']}, 'Just': {'type': ['number', 'null']}, 'Shell': {'type': ['number', 'null']}, 'JavaScript': {'type': ['number', 'null']}, 'TypeScript': {'type': ['number', 'null']}}}, 'default_branch': {'type': ['string', 'null']}, 'latest_release': {'type': ['object', 'null'], 'properties': {'tag': {'type': ['string', 'null']}, 'date': {'type': ['string', 'null']}, 'name': {'type': ['string', 'null']}, 'prerelease': {'type': ['boolean', 'null']}}}, 'top_contributors': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'login': {'type': ['string', 'null']}, 'commits': {'type': ['number', 'null']}}}}, 'open_issues_and_prs': {'type': ['number', 'null']}}}
hn_search
Hacker News search
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['query'], 'properties': {'days': {'type': 'integer', 'default': 365, 'maximum': 3650, 'minimum': 1, 'description': 'Only items from the last N days. Range 1-3650. Default 365.'}, 'sort': {'enum': ['relevance', 'date'], 'type': 'string', 'default': 'relevance', 'description': 'Order by relevance or newest first. One of "relevance", "date". Default "relevance".'}, 'type': {'enum': ['story', 'comment', 'show_hn', 'ask_hn'], 'type': 'string', 'default': 'story', 'description': 'Stories, comments, Show HN or Ask HN posts. One of "story", "comment", "show_hn", "ask_hn". Default "story".'}, 'limit': {'type': 'integer', 'default': 15, 'maximum': 50, 'minimum': 1, 'description': 'How many results to return. Range 1-50. Default 15.'}, 'query': {'type': 'string', 'description': 'Keywords to search for.'}, 'min_points': {'type': 'integer', 'default': 0, 'minimum': 0, 'description': 'Only items with at least this many points. Default 0.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'query': {'type': ['string', 'null']}, 'total': {'type': ['number', 'null']}, 'results': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'hn': {'type': ['string', 'null']}, 'url': {'type': ['string', 'null']}, 'date': {'type': ['string', 'null']}, 'text': {'type': ['string', 'null']}, 'title': {'type': ['string', 'null']}, 'author': {'type': ['string', 'null']}, 'points': {'type': ['number', 'null']}, 'comments': {'type': ['number', 'null']}}}}}}
http_probe
HTTP probe + security headers
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Absolute http(s) URL to probe.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'up': {'type': ['boolean', 'null']}, 'cdn': {'type': ['string', 'null']}, 'url': {'type': ['string', 'null']}, 'bytes': {'type': ['number', 'null']}, 'server': {'type': ['string', 'null']}, 'status': {'type': ['number', 'null']}, 'http_tls': {'type': ['object', 'null'], 'properties': {'cipher': {'type': ['string', 'null']}, 'issuer': {'type': ['string', 'null']}, 'subject': {'type': ['string', 'null']}, 'protocol': {'type': ['string', 'null']}, 'valid_to': {'type': ['string', 'null']}, 'authorized': {'type': ['boolean', 'null']}}}, 'final_url': {'type': ['string', 'null']}, 'redirects': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'ms': {'type': ['number', 'null']}, 'url': {'type': ['string', 'null']}, 'status': {'type': ['number', 'null']}}}}, 'remote_ip': {'type': ['string', 'null']}, 'timing_ms': {'type': ['object', 'null'], 'properties': {'tls': {'type': ['number', 'null']}, 'total': {'type': ['number', 'null']}, 'first_byte': {'type': ['number', 'null']}, 'dns_connect': {'type': ['number', 'null']}}}, 'compressed': {'type': ['boolean', 'null']}, 'powered_by': {}, 'content_type': {'type': ['string', 'null']}, 'cache_control': {}, 'security_headers': {'type': ['object', 'null'], 'properties': {'csp': {'type': ['boolean', 'null']}, 'hsts': {'type': ['boolean', 'null']}, 'grade': {'type': ['string', 'null']}, 'nosniff': {'type': ['boolean', 'null']}, 'referrer_policy': {'type': ['boolean', 'null']}, 'frame_protection': {'type': ['boolean', 'null']}, 'permissions_policy': {'type': ['boolean', 'null']}}}}}
package_info
Software package info
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'Exact package name as published, e.g. "express" or "requests".'}, 'ecosystem': {'enum': ['npm', 'pypi', 'crates'], 'type': 'string', 'default': 'npm', 'description': 'Registry to look in. One of "npm", "pypi", "crates". Default "npm".'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'url': {'type': ['string', 'null']}, 'name': {'type': ['string', 'null']}, 'stale': {}, 'latest': {'type': ['string', 'null']}, 'license': {'type': ['string', 'null']}, 'homepage': {'type': ['string', 'null']}, 'released': {'type': ['string', 'null']}, 'versions': {'type': ['number', 'null']}, 'ecosystem': {'type': ['string', 'null']}, 'deprecated': {}, 'repository': {'type': ['string', 'null']}, 'description': {'type': ['string', 'null']}, 'maintainers': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'dependencies': {'type': ['number', 'null']}, 'weekly_downloads': {'type': ['number', 'null']}}}
robots_check
robots.txt + AI crawler policy
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['url'], '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".'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'url': {'type': ['string', 'null']}, 'path': {'type': ['string', 'null']}, 'rule': {'type': ['string', 'null']}, 'groups': {'type': ['number', 'null']}, 'allowed': {'type': ['boolean', 'null']}, 'sitemaps': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'robots_txt': {'type': ['string', 'null']}, 'user_agent': {'type': ['string', 'null']}, 'crawl_delay': {}, 'matched_group': {'type': ['string', 'null']}, 'ai_crawlers_site_root': {'type': ['object', 'null'], 'properties': {'CCBot': {'type': ['string', 'null']}, 'GPTBot': {'type': ['string', 'null']}, 'Diffbot': {'type': ['string', 'null']}, 'Amazonbot': {'type': ['string', 'null']}, 'ClaudeBot': {'type': ['string', 'null']}, 'cohere-ai': {'type': ['string', 'null']}, 'Bytespider': {'type': ['string', 'null']}, 'Claude-User': {'type': ['string', 'null']}, 'ChatGPT-User': {'type': ['string', 'null']}, 'anthropic-ai': {'type': ['string', 'null']}, 'DuckAssistBot': {'type': ['string', 'null']}, 'OAI-SearchBot': {'type': ['string', 'null']}, 'PerplexityBot': {'type': ['string', 'null']}, 'MistralAI-User': {'type': ['string', 'null']}, 'Google-Extended': {'type': ['string', 'null']}, 'Perplexity-User': {'type': ['string', 'null']}, 'Claude-SearchBot': {'type': ['string', 'null']}, 'Applebot-Extended': {'type': ['string', 'null']}, 'Meta-ExternalAgent': {'type': ['string', 'null']}}}}}
tls_check
TLS certificate check
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['host'], 'properties': {'host': {'type': 'string', 'description': 'Hostname without scheme or path, e.g. "example.com".'}, 'port': {'type': 'integer', 'default': 443, 'maximum': 65535, 'minimum': 1, 'description': 'TCP port serving TLS. Range 1-65535. Default 443.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'ok': {'type': ['boolean', 'null']}, 'san': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'alpn': {'type': ['string', 'null']}, 'host': {'type': ['string', 'null']}, 'port': {'type': ['number', 'null']}, 'chain': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'issuer': {'type': ['string', 'null']}, 'subject': {'type': ['string', 'null']}, 'valid_to': {'type': ['string', 'null']}}}}, 'cipher': {'type': ['string', 'null']}, 'issuer': {'type': ['string', 'null']}, 'serial': {'type': ['string', 'null']}, 'subject': {'type': ['string', 'null']}, 'trusted': {'type': ['boolean', 'null']}, 'key_bits': {'type': ['number', 'null']}, 'protocol': {'type': ['string', 'null']}, 'valid_to': {'type': ['string', 'null']}, 'warnings': {'type': 'array'}, 'days_left': {'type': ['number', 'null']}, 'issuer_cn': {'type': ['string', 'null']}, 'valid_from': {'type': ['string', 'null']}, 'trust_error': {}, 'handshake_ms': {'type': ['number', 'null']}, 'fingerprint_sha256': {'type': ['string', 'null']}}}
web_meta
Page metadata + link preview
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'Absolute http(s) URL of the page.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'h1': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'h2': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'url': {'type': ['string', 'null']}, 'lang': {'type': ['string', 'null']}, 'feeds': {'type': 'array'}, 'title': {'type': ['string', 'null']}, 'robots': {}, 'status': {'type': ['number', 'null']}, 'favicon': {'type': ['string', 'null']}, 'twitter': {'type': ['object', 'null'], 'properties': {'twitter:card': {'type': ['string', 'null']}, 'twitter:site': {'type': ['string', 'null']}, 'twitter:image': {'type': ['string', 'null']}}}, 'manifest': {}, 'canonical': {'type': ['string', 'null']}, 'opengraph': {'type': ['object', 'null'], 'properties': {'og:url': {'type': ['string', 'null']}, 'og:type': {'type': ['string', 'null']}, 'og:image': {'type': ['string', 'null']}, 'og:title': {'type': ['string', 'null']}, 'og:description': {'type': ['string', 'null']}}}, 'description': {'type': ['string', 'null']}, 'json_ld_types': {'type': 'array', 'items': {'type': ['string', 'null']}}, 'apple_touch_icon': {}, 'link_preview_problems': {'type': 'array'}}}
web_read
Read a web page (clean markdown)
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'http(s) URL'}, 'max_chars': {'type': 'integer', 'default': 20000, 'maximum': 100000, 'minimum': 500, '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.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'url': {'type': ['string', 'null']}, 'lang': {'type': ['string', 'null']}, 'site': {'type': ['string', 'null']}, 'type': {'type': ['string', 'null']}, 'title': {'type': ['string', 'null']}, 'words': {'type': ['number', 'null']}, 'byline': {'type': ['string', 'null']}, 'status': {'type': ['number', 'null']}, 'excerpt': {'type': ['string', 'null']}, 'markdown': {'type': ['string', 'null']}, 'published': {'type': ['string', 'null']}, 'truncated': {'type': ['boolean', 'null']}, 'extracted_with': {'type': ['string', 'null']}}}
wiki
Wikipedia lookup
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).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['query'], 'properties': {'full': {'type': 'boolean', 'default': False, 'description': 'true = return the full article text, not just the summary. Default false.'}, 'lang': {'type': 'string', 'default': 'en', 'pattern': '^[a-z]{2,3}(-[a-z]+)?$', 'description': 'Wikipedia language code, e.g. "en", "de", "pt-br". Default "en".'}, 'query': {'type': 'string', 'description': 'Topic or article title to look up.'}, 'max_chars': {'type': 'integer', 'default': 8000, 'maximum': 60000, 'minimum': 500, 'description': 'Truncate full article text to this many characters (with full=true). Range 500-60000. Default 8000.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'url': {'type': ['string', 'null']}, 'type': {'type': ['string', 'null']}, 'found': {'type': ['boolean', 'null']}, 'title': {'type': ['string', 'null']}, 'summary': {'type': ['string', 'null']}, 'thumbnail': {'type': ['string', 'null']}, 'description': {}, 'last_edited': {'type': ['string', 'null']}, 'other_matches': {'type': 'array', 'items': {'type': ['object', 'null'], 'properties': {'title': {'type': ['string', 'null']}, 'snippet': {'type': ['string', 'null']}}}}}}
History
Recent tool changes
Added
book_search
Sept. 29, 2026, 2:40 a.m.
Added
doi_lookup
Sept. 29, 2026, 2:40 a.m.
Added
hn_search
Sept. 29, 2026, 2:40 a.m.
Added
github_repo
Sept. 29, 2026, 2:40 a.m.
Added
package_info
Sept. 29, 2026, 2:40 a.m.
Added
arxiv_search
Sept. 29, 2026, 2:40 a.m.
Added
wiki
Sept. 29, 2026, 2:40 a.m.
Added
email_check
Sept. 29, 2026, 2:40 a.m.
Added
robots_check
Sept. 29, 2026, 2:40 a.m.
Added
http_probe
Sept. 29, 2026, 2:40 a.m.
Added
tls_check
Sept. 29, 2026, 2:40 a.m.
Added
domain_whois
Sept. 29, 2026, 2:40 a.m.
Added
dns_lookup
Sept. 29, 2026, 2:40 a.m.
Added
web_meta
Sept. 29, 2026, 2:40 a.m.
Added
web_read
Sept. 29, 2026, 2:40 a.m.
Discover
Similar MCP servers
1cent Web Intelligence for AI Agents
ru.maxzoa/1cent
Performs SSRF-safe public web inspection, URL extraction, metadata and content analysis, accessibility checks, feed and sitemap d…
fetcher
cloud.fetcher/fetcher
Fetches and renders web pages, extracts content and PDFs, parses feeds, inspects domains and headers, and screens web content or …
Ground Truth - Fresh Evidence for AI Agents
io.github.anish632/ground-truth
Checks live endpoints, security headers, pricing, package metadata, compliance signals, and claims, and supports scheduled eviden…
mcp
com.geekflare/mcp
Searches and scrapes websites and performs web diagnostics including Lighthouse, DNS, TLS, port, network, redirect, and broken-li…
mercury-x402-mcp
io.github.mercuryx402/mercury-x402-mcp
Fetches, extracts, parses, compares, and validates web content and metadata, including DNS, headers, redirects, robots policies, …
Go Vulnerability Database Tracker — buy per-query in-session (govulnwatch)
com.a2awire/data-go-vulnerability-golang-security
Provides query access to Go module vulnerability data, including CVE aliases and fixed versions.
Dependency Vulnerability Tracker — package security advisories ($0.01/query)
com.a2awire/data-dependency-vulnerability-malicious-package-security
Provides query access to software dependency vulnerabilities and malicious-package advisories affecting ecosystems such as npm an…
Aayat AI
io.github.faisal-maverick/aayat-ai
Provides pay-per-call AI chat and model pricing, current developer documentation, package and vulnerability checks, company resea…