# Presend MCP Server (remote · presend.pages.dev)

Free MCP server: 36 security & dev API tools -- WHOIS, DNS, CVE, IP reputation, Cosmos SDK.

- Trust score: 67/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `presend.pages.dev`: 67/100 (this document), [markdown](https://verifymcp.io/servers/presendapp-presend-mcp/presend.md), [page](https://verifymcp.io/servers/presendapp-presend-mcp/presend)

## Channel facts

- Endpoint: `https://presend.pages.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 37 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1978 tokens (~53/item across 37 items; 37 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 37 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 37 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Presend MCP Server server?

Presend MCP Server is a hosted endpoint at https://presend.pages.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http presendapp-presend-mcp 'https://presend.pages.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "presendapp-presend-mcp": {
      "url": "https://presend.pages.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "presendapp-presend-mcp": {
      "type": "http",
      "url": "https://presend.pages.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.presendapp-presend-mcp]
url = "https://presend.pages.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "presendapp-presend-mcp": {
      "type": "remote",
      "url": "https://presend.pages.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add presendapp-presend-mcp --url 'https://presend.pages.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  presendapp-presend-mcp:
    url: "https://presend.pages.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "presendapp-presend-mcp": {
      "Transport": "http",
      "Url": "https://presend.pages.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add presendapp-presend-mcp -t streamable-http -u 'https://presend.pages.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "presendapp-presend-mcp": {
      "type": "http",
      "url": "https://presend.pages.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-19 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 66, 0)

- [functional] New tool “rpc_check”
- [functional] New tool “address_risk”
- [functional] New tool “tx_decode”

### 2026-09-17 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 65, 0)

- [functional] New tool “supply_chain_check”

### 2026-09-14 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 64, +7)

- [functional regression] Schema quality: 29 → 52
- [functional improvement] Tool coverage: 14% → 100%
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: fair → excellent
- [functional] New tool “maintainer_change_check”
- [cosmetic] “ai_crawler_check” reworded the description of “domain”
- [cosmetic] “base64” reworded the description of “action”
- [cosmetic] “base64” reworded the description of “text”
- [cosmetic] “color” reworded the description of “hex”
- [cosmetic] “color” reworded the description of “hsl”
- [cosmetic] “color” reworded the description of “rgb”
- [cosmetic] “csv_json” reworded the description of “data”
- [cosmetic] “csv_json” reworded the description of “direction”
- [cosmetic] “dns_lookup” reworded the description of “domain”
- [cosmetic] “email_disposable” reworded the description of “email”
- [cosmetic] “email_security” reworded the description of “domain”
- [cosmetic] “email_validate” reworded the description of “email”
- [cosmetic] “email_verify” reworded the description of “email”
- [cosmetic] “favicon” reworded the description of “domain”
- [cosmetic] “ip_reputation” reworded the description of “ip”
- [cosmetic] “jwt_decode” reworded the description of “token”
- [cosmetic] “jwt_verify” reworded the description of “token”
- [cosmetic] “password” reworded the description of “exclude_ambiguous”
- [cosmetic] “password” reworded the description of “length”
- [cosmetic] “password” reworded the description of “numbers”
- [cosmetic] “password” reworded the description of “symbols”
- [cosmetic] “password” reworded the description of “uppercase”
- [cosmetic] “password_breach” reworded the description of “password”
- [cosmetic] “password_check” reworded the description of “check_breach”
- [cosmetic] “password_check” reworded the description of “password”
- [cosmetic] “phone_verify” reworded the description of “number”
- [cosmetic] “redirect_trace” reworded the description of “url”
- [cosmetic] “repo_health_check” reworded the description of “repo”
- [cosmetic] “security_headers” reworded the description of “url”
- [cosmetic] “security_scan” reworded the description of “url”
- [cosmetic] “subdomains” reworded the description of “domain”
- [cosmetic] “timestamp” reworded the description of “date”
- [cosmetic] “timestamp” reworded the description of “unix”
- [cosmetic] “typosquat_check” reworded the description of “ecosystem”
- [cosmetic] “typosquat_check” reworded the description of “package”
- [cosmetic] “url_clean” reworded the description of “url”
- [cosmetic] “url_reputation” reworded the description of “url”
- [cosmetic] “user_agent” reworded the description of “ua”
- [cosmetic] “uuid” reworded the description of “count”
- [cosmetic] “vulnerability_check” reworded the description of “ecosystem”
- [cosmetic] “vulnerability_check” reworded the description of “package”
- [cosmetic] “whois_lookup” reworded the description of “domain”

### 2026-09-12 (score 57)

First indexed and scored.

## MCP tools (37)

### `address_risk` (~59 tokens)

Check a crypto address against the OFAC sanctions list (EVM)

Input parameters:

- `address` (string, required): EVM address (0x + 40 hex chars) or Cosmos SDK bech32 address to check against the OFAC SDN sanctions list.

### `ai_crawler_check` (~50 tokens)

Check which AI crawlers are allowed by robots.txt

Input parameters:

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

### `base64` (~46 tokens)

Encode or decode Base64

Input parameters:

- `action` (string, required): Either \"encode\" or \"decode\".
- `text` (string, required): Text to encode, or Base64 string to decode.

### `color` (~109 tokens)

Convert color formats

Input 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.

### `csv_json` (~55 tokens)

Convert between JSON and CSV (GET)

Input parameters:

- `data` (string, required): The CSV or JSON text to convert, matching the chosen direction.
- `direction` (string, required): Either \"csv-to-json\" or \"json-to-csv\".

### `dns_lookup` (~66 tokens)

DNS record lookup (A, AAAA, CNAME, MX, TXT, NS)

Input parameters:

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

### `email_disposable` (~35 tokens)

Detect disposable email domains

Input parameters:

- `email` (string, required): Email address to check against a list of known disposable/temporary email domains.

### `email_security` (~52 tokens)

Domain email anti-spoofing check (SPF/DMARC/DKIM)

Input parameters:

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

### `email_validate` (~33 tokens)

Validate an email address

Input parameters:

- `email` (string, required): Email address to validate for correct syntax and a resolvable domain.

### `email_verify` (~34 tokens)

Combined email verification

Input parameters:

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

### `favicon` (~34 tokens)

Fetch a domain's favicon URL

Input parameters:

- `domain` (string, required): Domain to fetch the favicon URL for, e.g. example.com.

### `ip` (~13 tokens)

Get caller IP geolocation

### `ip_reputation` (~43 tokens)

IP reputation check (Spamhaus DROP)

Input parameters:

- `ip` (string, required): IPv4 address to check against the Spamhaus DROP list of known spam/hijacker netblocks.

### `jwt_decode` (~44 tokens)

Decode a JWT

Input parameters:

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

### `jwt_verify` (~114 tokens)

Verify a JWT's cryptographic signature

Input parameters:

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

### `maintainer_change_check` (~47 tokens)

Detect a suspicious npm package maintainer change

Input parameters:

- `ecosystem` (string, required): Currently only \"npm\" is supported.
- `package` (string, required): Package name, e.g. lodash

### `password` (~134 tokens)

Generate a secure password

Input parameters:

- `exclude_ambiguous` (string): Whether to exclude visually ambiguous characters (e.g. 0/O, 1/l). 1 for yes, 0 for no.
- `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.

### `password_breach` (~57 tokens)

Check if a password has been breached

Input parameters:

- `password` (string, required): Password to check against known data-breach corpora. Checked via k-anonymity (only a partial hash prefix is sent) -- the full password is never transmitted.

### `password_check` (~66 tokens)

Combined password strength + breach check

Input parameters:

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

### `phone_verify` (~79 tokens)

Validate and format a phone number

Input parameters:

- `country` (string): ISO 3166-1 alpha-2 country code (e.g. US, FR), used to interpret a number with no leading +.
- `number` (string, required): Phone number to validate and format, ideally in E.164 format (e.g. +14155552671).

### `redirect_trace` (~32 tokens)

Full redirect chain trace

Input parameters:

- `url` (string, required): URL to follow the full redirect chain for, hop by hop.

### `repo_health_check` (~37 tokens)

GitHub repository health signals

Input parameters:

- `repo` (string, required): GitHub repository in owner/name format, e.g. lodash/lodash.

### `rpc_check` (~56 tokens)

Audit a CometBFT RPC endpoint (health, peers, unsafe-method exposure)

Input parameters:

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

### `security_headers` (~41 tokens)

Audit HTTP security headers

Input parameters:

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

### `security_scan` (~37 tokens)

Combined security posture report

Input parameters:

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

### `subdomains` (~38 tokens)

Passive subdomain discovery

Input parameters:

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

### `supply_chain_check` (~62 tokens)

Combined supply-chain risk check (maintainer-change + vulnerability + typosquat + repo-health)

Input parameters:

- `ecosystem` (string, required): Package ecosystem, e.g. npm. maintainer-change-check only runs for npm.
- `package` (string, required): Package name to check.

### `text_similarity` (~48 tokens)

Text similarity via SimHash (1 or 2 texts)

Input parameters:

- `texts` (array, required): 1 text (hash only) or 2 texts (compare). Max 200,000 characters each.

### `timestamp` (~65 tokens)

Convert timestamps

Input 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.

### `tx_decode` (~54 tokens)

Decode a raw signed Cosmos SDK transaction (protobuf)

Input parameters:

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

### `typosquat_check` (~61 tokens)

Package name typosquatting check

Input parameters:

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

### `url_clean` (~38 tokens)

Clean a single URL

Input parameters:

- `url` (string, required): URL to strip tracking parameters from (utm_*, fbclid, gclid, and similar).

### `url_reputation` (~35 tokens)

Check URL against malware/phishing database

Input parameters:

- `url` (string, required): URL to check against known phishing/malware URL databases.

### `user_agent` (~40 tokens)

Parse a User-Agent string

Input parameters:

- `ua` (string): User-Agent string to parse. If omitted, the request's own User-Agent header is parsed instead.

### `uuid` (~35 tokens)

Generate UUIDs

Input parameters:

- `count` (string): Number of UUIDs (v4) to generate. Defaults to 1 if omitted.

### `vulnerability_check` (~87 tokens)

Package vulnerability check (OSV.dev)

Input parameters:

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

### `whois_lookup` (~42 tokens)

Domain registration lookup (WHOIS via RDAP)

Input parameters:

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

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/presendapp-presend-mcp/presend#diagnostics

## Score history

- 2026-09-20: 67
- 2026-09-19: 67
- 2026-09-18: 66
- 2026-09-17: 66
- 2026-09-16: 65
- 2026-09-15: 65
- 2026-09-14: 65
- 2026-09-13: 64
- 2026-09-12: 57

## Common questions

### What is the Presend MCP Server server?

Presend MCP Server is listed in the public MCP registry as io.github.presendapp/presend-mcp. Free MCP server: 36 security & dev API tools -- WHOIS, DNS, CVE, IP reputation, Cosmos SDK. This page covers its hosted endpoint (https://presend.pages.dev/mcp).

### Is the Presend MCP Server server safe to use?

Presend MCP Server scores 67 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Presend MCP Server server expose?

Presend MCP Server exposes 37 tools: address_risk, ai_crawler_check, base64, color, csv_json, and 32 more. Their descriptions and schemas cost roughly 1,978 tokens of context every time the server is loaded.

### Does the Presend MCP Server server require authentication?

No. We connected to Presend MCP Server without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Presend MCP Server server still maintained?

Presend MCP Server is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://presend.pages.dev/mcp
- Repository: https://github.com/presendapp/presend
- Changelog RSS feed: https://verifymcp.io/servers/presendapp-presend-mcp/presend.xml
- Changelog JSON feed: https://verifymcp.io/servers/presendapp-presend-mcp/presend.json
- HTML version of this page: https://verifymcp.io/servers/presendapp-presend-mcp/presend