Presend MCP Server

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Before an AI agent installs an npm/PyPI package: typosquat, vulnerability and existence checks.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Presend MCP Server": {
      "url": "https://presend.pages.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (40)

• address_risk read-only

  Screens a crypto address against every OFAC SDN digital currency address list. EVM (0x...) and Bitcoin (bc1..., 1..., 3...) addresses are fully covered (sanctioned true or false, with the matching lists). Addresses of other chains are flagged when listed; Cosmos SDK bech32 addresses return sanctioned: null when not listed, as OFAC publishes none. A sanctions signal only, not a full risk score.

  Parameters:

  • address (required) — string — Address to screen: EVM (0x + 40 hex chars) or Bitcoin (bc1..., 1..., 3...), both fully covered. Addresses of other chains are matched against their lists too; bech32 addresses of other chains (e.g. cosmos1...) return sanctioned: null (unchecked, not clean) when not listed.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• ai_crawler_check read-only

  Fetches a domain's robots.txt and reports which known AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot and others) are allowed or blocked, including wildcard rules. Reflects robots.txt only, not server-side blocking.

  Parameters:

  • domain (required) — string — Domain to check, e.g. example.com. robots.txt is fetched from https://<domain>/robots.txt.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• base64 read-only

  Encodes text to Base64 or decodes a Base64 string back to text (action = encode or decode).

  Parameters:

  • action (required) — string — Either 'encode' or 'decode'.
  • text (required) — string — Text to encode, or Base64 string to decode.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• color read-only

  Converts a color between hex, RGB and HSL. Provide exactly one of hex, rgb or hsl.

  Parameters:

  • hex — string — Hex color code, e.g. #ff0000 or ff0000. Provide exactly one of hex, rgb, or hsl.
  • hsl — string — HSL color, e.g. 0,100%,50%. Provide exactly one of hex, rgb, or hsl.
  • rgb — string — RGB color, e.g. 255,0,0. Provide exactly one of hex, rgb, or hsl.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• csv_json read-only

  Converts CSV text to JSON or JSON to CSV (direction: csv-to-json or json-to-csv), for data passed inline. CSV must be comma-separated, with a header row and at least one data row; double-quoted fields may contain commas. Semicolon- or tab-separated input is not detected and comes back as a single column. JSON input must be an array of objects: the union of their keys becomes the CSV header and missing values are left empty. Returns result (the converted text), rows and cols. Max 500,000 characters.

  Parameters:

  • direction (required) — string — Either 'csv-to-json' or 'json-to-csv'.
  • data (required) — string — The CSV or JSON text to convert, matching the chosen direction.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• cve_lookup read-only

  Looks up a vulnerability by identifier (CVE, GHSA or other OSV ID) on OSV.dev: summary, CVSS severity, affected packages and versions, references. Use when you already have an ID; use vulnerability_check when you have a package name instead.

  Parameters:

  • id (required) — string — CVE, GHSA, or other OSV-native identifier, e.g. CVE-2021-44228.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• dns_lookup read-only

  Returns DNS records for a domain via Cloudflare DNS-over-HTTPS: A, AAAA, CNAME, MX, TXT and NS in one call, or a single record type with 'type'. For registration data use whois_lookup; for SPF/DMARC/DKIM analysis use email_security.

  Parameters:

  • domain (required) — string — Domain to look up, e.g. example.com.
  • type — string — Narrow to a single record type. Omit to get all 6 at once.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• email_disposable read-only

  Checks only whether an email address uses a known disposable/temporary email domain. For syntax, MX, disposable and role-account checks in one call, use email_verify.

  Parameters:

  • email (required) — string — Email address to check against a list of known disposable/temporary email domains.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• email_security read-only

  Audits a domain's email anti-spoofing setup: SPF strength, DMARC policy and a best-effort DKIM lookup on common selectors. A missing DKIM match does not prove DKIM is absent. Checks a domain, not a single address.

  Parameters:

  • domain (required) — string — Domain to check SPF, DKIM, and DMARC records for, e.g. example.com.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• email_validate read-only

  Lightweight email check: syntax plus confirmation that the domain has an MX record. Does not detect disposable or role addresses; use email_verify for the combined check.

  Parameters:

  • email (required) — string — Email address to validate for correct syntax and a resolvable domain.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• email_verify read-only

  Most complete email check in one call: syntax, MX record, disposable-domain detection and role/generic account detection (e.g. info@, admin@). Prefer it over email_validate and email_disposable unless you need a single signal. Does not probe the mailbox. valid is null (not false) when the MX lookup could not be completed; retry later instead of treating the address as invalid.

  Parameters:

  • email (required) — string — Email address to run through combined syntax, disposable-domain, and MX-record checks.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• favicon read-only

  Returns the favicon URL a website declares: fetches the homepage and takes the first <link rel='icon'> (or 'shortcut icon') href, resolved to an absolute URL, which may be a data: URI when the page inlines its icon (source: declared). If no icon is declared, or the homepage cannot be fetched, returns the conventional https://<domain>/favicon.ico with source: default and a note, without checking that it exists. Use it to display a site icon; it does not download or validate the image.

  Parameters:

  • domain (required) — string — Domain to fetch the favicon URL for, e.g. example.com.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• iban_validate read-only

  Validates an IBAN offline: ISO 7064 mod-97 checksum and country-specific length. Confirms the number is well-formed, not that the account exists.

  Parameters:

  • iban (required) — string — IBAN to validate. Spaces are ignored.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• ip_reputation read-only

  Checks an IPv4 or IPv6 address against a curated list of netblocks known to be hijacked or run by spam/cyber-crime operations (IPv4-mapped IPv6 uses the IPv4 list). A narrow list-based signal: a clean result is not a safety guarantee. Includes list date and attribution.

  Parameters:

  • ip (required) — string — IPv4 or IPv6 address to check (IPv4-mapped IPv6 such as ::ffff:1.2.3.4 is checked against the IPv4 list) against a curated list of known hijacked or cyber-crime-controlled netblocks.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• jwt_decode read-only

  Decodes a JWT's header and payload WITHOUT verifying its signature, so its claims must not be trusted on this basis alone. To check authenticity, use jwt_verify.

  Parameters:

  • token (required) — string — The JWT to decode. Decodes header and payload only -- does not verify the signature (use /jwt-verify for that).

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• jwt_verify read-only

  Cryptographically verifies a JWT signature (HS256/384/512, RS/PS256/384/512, ES256/384/512) and checks exp/nbf claims. Provide a secret for HS*, or a JWK or JWKS URL for RS/PS/ES. Use instead of jwt_decode whenever authenticity matters.

  Parameters:

  • token (required) — string — The JWT to verify. Checks the cryptographic signature -- use /jwt-decode if you only need to read the header and payload.
  • jwk — object — Public key in JWK format, for RS/PS/ES algorithms.
  • secret — string — Required for HS256/384/512.
  • jwks_url — string — URL to a JWKS document; the key is matched by the token's "kid" header.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• link_metadata read-only

  Fetches a web page and extracts its title, description, canonical URL, Open Graph and Twitter Card tags and favicon (the data behind link previews). Follows redirects and returns final_url; favicon_source says whether the icon is declared by the page or only the /favicon.ico guess. To see each redirect hop, use redirect_trace.

  Parameters:

  • url (required) — string — URL to extract title, description, and Open Graph / Twitter Card metadata from.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• maintainer_change_check read-only

  Publisher-change analysis is npm only. Also reports whether the package exists (found) and its age (first_published, package_age_days, new_package if first published less than 30 days ago), for npm and for PyPI; on PyPI only existence and age are available. Flags a previously unseen human publisher taking over a package after 180+ days of inactivity, within the last 365 days (the event-stream attack pattern). npm trusted publishing (verified OIDC identity, not just a bot-like account name), pre-release, and handovers to a publisher who already maintains another widely used package (100k+ weekly downloads) are reported but not flagged. Does not detect hijacked existing accounts; a heuristic for review, not proof.

  Parameters:

  • ecosystem (required) — string — npm (full analysis) or pypi (existence and age only).
  • package (required) — string — Package name, e.g. lodash

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• password read-only

  Generates a random password, with options for length, symbols, uppercase, numbers and excluding ambiguous characters. To evaluate an existing password, use password_check.

  Parameters:

  • length — string — Desired password length. Defaults to a reasonable secure length if omitted.
  • numbers — string — Whether to include numeric digits. 1 for yes, 0 for no.
  • symbols — string — Whether to include symbol characters. 1 for yes, 0 for no.
  • uppercase — string — Whether to include uppercase letters. 1 for yes, 0 for no.
  • exclude_ambiguous — string — Whether to exclude visually ambiguous characters (e.g. 0/O, 1/l). 1 for yes, 0 for no.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• password_breach read-only

  Checks whether a password appears in known data breaches (Have I Been Pwned) and how many times, using k-anonymity towards HIBP. Breach check only; password_check adds strength scoring and sends the password in a POST body.

  Parameters:

  • password (required) — string — Password to check against known data-breach corpora. Only a 5-character SHA-1 hash prefix is sent to HIBP (k-anonymity), but the password itself travels in this request's URL; for real passwords, prefer password_check, which takes it in a POST body.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• password_check read-only

  Scores a password's strength (length, character variety, entropy as an upper bound, repeated patterns; passphrases are estimated per word) and, with check_breach=true, also looks it up in Have I Been Pwned breach data via k-anonymity (only a hash prefix is sent); a password found in breaches is always rated very_weak. Use it to evaluate a password someone is choosing; use password_breach when you only need the breach count, and password to generate a new one. The password travels in a POST body, never in a URL.

  Parameters:

  • password (required) — string — Password to evaluate for strength (length, character variety, common patterns).
  • check_breach — boolean — Whether to also check the password against known data-breach corpora via k-anonymity. true or false.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• phone_verify read-only

  Validates and formats a phone number: validity, country, line type, E.164, international and national formats. Numbers without a leading + require 'country', since the end user's country cannot be inferred over MCP.

  Parameters:

  • number (required) — string — Phone number to validate and format, ideally in E.164 format (e.g. +14155552671).
  • country — string — ISO 3166-1 alpha-2 country code (e.g. US, FR). Required unless the number starts with +: over MCP the end user's country cannot be inferred.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• redirect_trace read-only

  Follows a URL's full redirect chain (up to 15 hops) and returns every hop with its status code, plus whether the chain crossed domains. Use it to see where a short or tracking link really leads; check the final URL with url_reputation.

  Parameters:

  • url (required) — string — URL to follow the full redirect chain for, hop by hop.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• repo_health_check read-only

  Maintenance signals for a GitHub repository given as owner/name: stars, forks, open issues, license, archived and fork flags, creation date and age, days since last push, topics. Use it to judge whether a dependency looks maintained or abandoned. For an npm or PyPI package whose repository you do not know, supply_chain_check resolves it from registry metadata and includes these signals. GitHub only; missing or private repositories return found: false.

  Parameters:

  • repo (required) — string — GitHub repository in owner/name format, e.g. lodash/lodash.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• rpc_check read-only

  Read-only audit of a public CometBFT (Cosmos SDK) RPC endpoint: node status, health, peers, and whether unsafe admin methods (dial_seeds, dial_peers, unsafe_flush_mempool) are publicly exposed. Never calls an unsafe method; exposure is inferred from the node's route listing.

  Parameters:

  • url (required) — string — Base URL of a CometBFT RPC endpoint to audit, e.g. https://rpc.cosmos.network:443.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• security_headers read-only

  Audits the HTTP security headers of one URL (CSP, HSTS, X-Frame-Options, Permissions-Policy, cross-origin policies and others) and returns per-header findings with fix advice, a score and a letter grade. Use it when you need header hardening advice; security_scan runs this audit together with URL reputation and subdomain discovery in one call.

  Parameters:

  • url (required) — string — URL to audit HTTP security headers for (CSP, HSTS, X-Frame-Options, etc.).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• security_scan read-only

  Combined website check in one call: security headers, URL reputation and passive subdomain discovery, run in parallel, with an overall score and verdict. Use the individual tools when you need a single signal.

  Parameters:

  • url (required) — string — URL to run a combined security posture check against (headers, reputation, and related signals).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• subdomains read-only

  Passive subdomain discovery from Certificate Transparency logs (crt.sh): finds hostnames that appeared in public TLS certificates, not every DNS record. crt.sh is occasionally slow or unavailable.

  Parameters:

  • domain (required) — string — Domain to passively discover subdomains for via Certificate Transparency logs, e.g. example.com.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• supply_chain_check read-only

  Call this before installing or adding a package (npm install, pip install, a new entry in a manifest), especially one whose name you recalled or that a model suggested. One-call risk check: combines vulnerability_check (OSV.dev), typosquat_check, maintainer_change_check (npm only) and repo_health_check (when the GitHub repo can be resolved) into one overall verdict. A package that does not exist on npm or PyPI gets overall_risk 'package_not_found': the name may be invented and should not be installed. A package first published less than 30 days ago gets the 'new_package' flag and overall_risk 'review_recommended': new packages are where invented and look-alike names get registered, so the name is worth confirming against the project's own documentation before installing (on PyPI the age is that of the oldest release still published; being new does not make a package malicious). Use the individual tools to investigate one signal. Vulnerabilities are checked for the given version, or the latest published one (version_checked, version_source). If a check could not run (rate limit, upstream error), it is listed in unavailable_checks and overall_risk is 'incomplete', never 'no_signals_found'. Also flags a version marked deprecated on npm or yanked on PyPI.

  Parameters:

  • ecosystem (required) — string — Package ecosystem, e.g. npm. maintainer-change-check only runs for npm.
  • package (required) — string — Package name to check.
  • version — string — Exact version to check for known vulnerabilities. Optional: defaults to the latest published version (npm and PyPI).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• text_similarity read-only

  Near-duplicate detection with a 64-bit SimHash over word shingles: send 1 text to get its hash, or 2 texts to compare them. Detects paraphrased or lightly edited copies; unrelated texts score around 50%, not 0%.

  Parameters:

  • texts (required) — array — 1 text (hash only) or 2 texts (compare). Max 200,000 characters each.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• timestamp read-only

  Returns the current time, or converts between a Unix timestamp (seconds) and an ISO date. Provide unix or date, or neither for the current time.

  Parameters:

  • date — string — Date/time string to convert to a Unix timestamp. Provide either unix or date, not both.
  • unix — string — Unix timestamp (seconds since epoch) to convert to a human-readable date. Provide either unix or date, not both.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• tx_decode read-only

  Decodes a raw signed Cosmos SDK transaction (base64 TxRaw bytes, as found in a CometBFT block's data.txs) into JSON: messages, fee, gas, signers and signatures. Bank, staking, gov and authz messages are fully decoded; other types are returned as type URL plus raw hex.

  Parameters:

  • tx (required) — string — Base64-encoded Cosmos SDK TxRaw protobuf bytes, as returned by a chain's CometBFT RPC /block or /tx_search endpoints.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• typosquat_check read-only

  Call before installing a package whose name you typed or recalled. Checks whether an npm or PyPI package name is a near-miss of a well-known package (typosquatting), with an edit-distance threshold scaled to name length; names of 3 characters or fewer are not fuzzy-matched. Uses a curated list of popular names, so a clean result does not prove a package is safe. It does not check that the package exists: supply_chain_check does.

  Parameters:

  • ecosystem (required) — string — Package ecosystem, e.g. npm or PyPI.
  • package (required) — string — Package name to check for likely typosquatting of a well-known package in the given ecosystem.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• url_clean read-only

  Removes 60+ known tracking parameters (utm_*, fbclid, gclid and similar) from a URL and returns the clean URL. Does not follow redirects; for that, use redirect_trace.

  Parameters:

  • url (required) — string — URL to strip tracking parameters from (utm_*, fbclid, gclid, and similar).

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• url_reputation read-only

  Checks a URL against URLhaus (abuse.ch), a public database of known malware distribution URLs. A clean result only means the URL is not listed, not that it is safe.

  Parameters:

  • url (required) — string — URL to check against known phishing/malware URL databases.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• user_agent read-only

  Parses a User-Agent string into browser and version, operating system and version, device type, and whether it looks like a bot.

  Parameters:

  • ua (required) — string — User-Agent string to parse. Required over MCP: the server cannot see the end user's own User-Agent.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• uuid read-only

  Generates 1 to 100 random UUID v4 values.

  Parameters:

  • count — string — Number of UUIDs (v4) to generate. Defaults to 1 if omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• vat_validate read-only

  Checks an EU VAT number in real time against the European Commission's VIES service and, when valid, returns the registered company name and address. VIES is occasionally unavailable for some member states.

  Parameters:

  • vat (required) — string — VAT number, with or without the country prefix.
  • country — string — 2-letter EU country code (EL for Greece, XI for Northern Ireland). Optional if vat includes the prefix.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• vulnerability_check read-only

  Checks a package (optionally a specific version) against OSV.dev for known vulnerabilities: npm, PyPI, Go, crates.io, Maven, RubyGems, Packagist and NuGet. For npm and PyPI, a name that does not exist returns found: false and vulnerable: null, never a clean result. Use cve_lookup when you already have a CVE/GHSA ID, or supply_chain_check for a combined verdict.

  Parameters:

  • ecosystem (required) — string — Package ecosystem, e.g. npm, PyPI, Go, crates.io, Maven, RubyGems, Packagist, or NuGet.
  • package (required) — string — Package name to check against OSV.dev for known CVEs.
  • version — string — Omit to check all versions of the package.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• whois_lookup read-only

  Domain registration data via RDAP (the modern WHOIS): registrar, creation and expiration dates, domain age in days, nameservers. For DNS records, use dns_lookup.

  Parameters:

  • domain (required) — string — Domain to look up registration details for via RDAP, e.g. example.com.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.