co.youraitools/hub

None of its 36 tools are described as changing anything. For 36 the reading was uncertain, so no mark is shown.

• check_agenton 7 other servers

  “Check whether an AI agent is registered in the Concordium Agent Registry (CIS-8004), Active (not revoked), and Verified by Concordium (its Agent Card hash matches the on-chain metadata_hash).”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  3 inputs, 1 required

  • idstringrequired“Badge (CIS-2 token address, short or CAIP-19 form) or Concordium account address”
  • networkstring“Concordium network”
  • tierstring“Paid tier: check $0.005.”
• read_urlon 27 other servers

  “Fetches one public web page and returns its main content as clean Markdown (boilerplate removed, links absolute) plus title and metadata.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  3 inputs, 1 required

  • urlstringrequired“Absolute http:// or https:// URL of a public page, e.g.”
  • maxCharsinteger“Maximum Markdown characters to return, 100-200,000 (default 50000).”
  • tierstring“Paid tier: read $0.002.”
• scan_texton 36 other servers

  “Scans untrusted text (web page text, emails, documents, tool results, another agent's message) for prompt injection before your agent acts on it: instruction overrides, jailbreak personas, system-pro…”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  4 inputs, 1 required

  • textstringrequired“The untrusted text to scan, as one plain string (1-100000 characters; longer text is truncated and flagged).”
  • toolsarray“(paid calls only)”
  • urlstring“(paid calls only)”
  • tierstring“Paid tier: scan $0.003.”
• scan_urlon 9 other servers

  “Fetches a public web page and scans its visible text plus hidden HTML (comments, hidden elements, alt/aria/meta text) for prompt injection before your agent browses or summarizes it.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  4 inputs, 1 required

  • urlstringrequired“Absolute http:// or https:// URL of a public web page, e.g.”
  • textstring“(paid calls only)”
  • toolsarray“(paid calls only)”
  • tierstring“Paid tier: scan $0.003.”
• scan_tools

  “Checks MCP / function-calling tool definitions for tool poisoning (hidden instructions, data-exfiltration requests, hijack attempts in names, descriptions and schemas) before your agent installs or c…”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  4 inputs, 1 required

  • toolsarrayrequired“1-100 tool definitions as objects {name, description, inputSchema} (as returned by an MCP server's tools/list; input_schema or parameters are also read).”
  • textstring“(paid calls only)”
  • urlstring“(paid calls only)”
  • tierstring“Paid tier: scan $0.003.”
• check_domainon 43 other servers

  “Check a domain before your agent trusts a link, a sender or a counterparty: does it exist, where does its mail go, SPF and DMARC policy, nameservers, DNSSEC.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  2 inputs, 1 required

  • domainstringrequired“Domain, URL or email address”
  • tierstring“Paid tier: domain $0.002.”
• check_emailon 9 other servers

  “Check an email address an agent is about to store, email or trust: syntax, disposable / throwaway provider, role account, free webmail.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  2 inputs, 1 required

  • emailstringrequired“Email address”
  • tierstring“Paid tier: email $0.001.”
• screen_addresson 9 other servers

  “Checks one crypto address against the US Treasury OFAC SDN list of sanctioned digital currency addresses (refreshed daily).”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  2 inputs, 1 required

  • addressstringrequired“One blockchain address, e.g.”
  • tierstring“Paid tier: address $0.001.”
• screen_batchon 2 other servers

  “Checks 1-50 crypto addresses against the US Treasury OFAC SDN list in one call (counts as one call): payee lists, counterparties, transaction inputs/outputs.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  2 inputs, 1 required

  • addressesarrayrequired“1-50 blockchain addresses, one string per element, e.g.”
  • tierstring“Paid tier: batch $0.01.”
• scan_dependencieson 5 other servers

  “Checks a package.json, lockfile, requirements.txt, go.mod, Cargo.lock, poetry.lock or composer.lock (or a list of packages) against OSV.dev for known vulnerabilities and confirmed-malicious packages.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  6 inputs

  • manifeststring“Manifest or lockfile contents (package.json, package-lock.json, requirements.txt, Pipfile.lock, poetry.lock, go.mod, Cargo.lock, composer.lock)”
  • filenamestring“Optional file name, helps type detection”
  • packagesarray“Alternative to manifest: [{ecosystem, name, version}], up to 500”
  • include_devboolean“Include devDependencies (default true)”
  • typestring“(paid calls only)”
  • tierstring“Paid tier: scan $0.003.”
• check_packageon 26 other servers

  “Checks one package version (npm, PyPI, Go, crates.io, Packagist, RubyGems, Maven, NuGet) against OSV.dev: advisory ids, severity, CVSS, fixed-in versions and malicious flags.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  4 inputs, 2 required

  • ecosystemstring“One of npm, PyPI, Go, crates.io, Packagist, RubyGems, Maven, NuGet, Pub, Hex (default npm)”
  • namestringrequired“Package name, e.g.”
  • versionstringrequired“Exact version, e.g.”
  • tierstring“Paid tier: package $0.001.”
• detect_stackon 4 other servers

  “Detects the technologies a website uses (CMS, ecommerce platform, JS framework, web server, CDN/hosting, analytics, ad pixels, chat, payments, consent tools) from one page load.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes

  2 inputs, 1 required

  • urlstringrequired“Absolute http(s) URL or a bare domain, e.g.”
  • tierstring“Paid tier: detect $0.003.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-24.

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.