Emailens MCP
REMOTE · EMAILENS.DEV · 2 COMPONENTS
Analyze, audit, fix and diff HTML, MJML, Maizzle and React Email across 21 email clients.
Available components
Last scanned (9 hours ago)
Scores higher than 91% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Testing and QA
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. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability81
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2034 tokens (~135/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management77
- Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +5
- HTTPS: unverified → pass ▲ security
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.
- 27 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Oct 26 −9
- Tool “analyze_email” rewrote its description, which is the text the model reads security
- Tool “audit_email” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- Stability: pass → 0.40 functional
- Server version: 0.9.1 → 0.13.0 functional
- New tool “capture_screenshots” functional
- New tool “share_preview” functional
- “analyze_email” added an optional parameter “clients” cosmetic
- “analyze_email” added an optional parameter “detail” cosmetic
- “analyze_email” added an optional parameter “targetingPolicy” cosmetic
- “audit_email” added an optional parameter “clients” cosmetic
- “audit_email” added an optional parameter “detail” cosmetic
- “audit_email” added an optional parameter “emailType” cosmetic
- “audit_email” added an optional parameter “previousHtml” cosmetic
- “audit_email” added an optional parameter “targetingPolicy” cosmetic
- “preview_email” added an optional parameter “targetingPolicy” cosmetic
- “analyze_email” reworded the description of “format” cosmetic
- “analyze_email” reworded the description of “html” cosmetic
- “audit_email” reworded the description of “format” cosmetic
- “audit_email” reworded the description of “html” cosmetic
- “audit_email” reworded the description of “skip” cosmetic
- “preview_email” reworded the description of “format” cosmetic
- 19 Oct 26 0
- Endpoint reachability: reachable → unreachable ▼ security
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Authorization: partial → unverified ▼ security
- Transport: pass → fail ▼ security
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Endpoint reachability: unreachable → reachable ▲ functional
- 17 Oct 26 +54
- Stability: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- Transport: unverified → pass ▲ security
- Authorization: fail → partial ▲ security
- Endpoint reachability: behind authorisation → reachable ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://emailens.dev/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=emailens.dev | CN=WE1,O=Google Trust Services,C=US | 24 Sept 2026 | 23 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 7190c53a5a0fb3de0eac08a968ece4c1 |
| SANs: emailens.dev, *.emailens.dev | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of emailens.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| emailens.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline'; img-src 'self' data: https:; media-src 'self' https://cdn.emailens.dev; font-src 'self' data:; frame-src 'self'; worker-src 'self' blob:; connect-src 'self' https://api-openpanel.philippekam.dev https://*.ingest.de.sentry.io https://*.ingest.sentry.io https://ebwqcitgedxwwrswebew.supabase.co wss://ebwqcitgedxwwrswebew.supabase.co; object-src 'none'; base-uri 'self' |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://emailens.dev/api/mcp | Verified | 200 | |
| http (plaintext) | http://emailens.dev/api/mcp | HTTPS enforced | 301 | https://emailens.dev/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
analyze_email Analyze Email ~369
Fix error and warning findings. Info findings are not problems (the email falls back safely there): never remove responsive (@media) or dark-mode CSS to clear them. Quick CSS compatibility analysis, returns per-client scores and one finding per problem, listing the clients it affects. For HTML input each finding carries loc (line, column, offset) and alsoAtLines, so you can edit the exact source. Narrow with clients, or pass detail:'full' for the per-client breakdown with fix snippets. Use audit_email for a full quality report (spam, links, a11y, images, etc.).
| Name | Type | Req | Description |
|---|---|---|---|
| clients | array | – | Only report these client IDs (e.g. ['gmail-web','outlook-windows']). The fastest way to cut the response when you care about specific clients. Use list_clients for the IDs. |
| detail | string | – | 'summary' (default) returns one entry per error or warning, listing the clients it affects, and only counts info findings (safe fallbacks). 'full' returns one entry per client with fix snippets, info… |
| format | string | – | Source format: 'html' (default), 'jsx' (React Email), 'mjml', or 'maizzle' (HTML template or Vue single-file component). Anything but 'html' is compiled before analysis and sets the syntax of the fix… |
| html | string | yes | The email source |
| targetingPolicy | string | – | 'progressive' (default) suppresses compatibility false-positives inside client-targeted scopes and only flags deprecated or dangerous hacks. 'strict' treats targeting as non-standard and reports ever… |
No output schema declared.
No examples provided.
audit_email Audit Email ~624
Fix error and warning findings, and restore anything listed in designRemovals. Info findings are not problems (the email falls back safely there): never remove responsive (@media), dark-mode CSS or rounded corners to clear them. designRemovals compares this version with the first one audited for the same email (or with previousHtml): design the edits deleted, such as @media rules, dark mode, corners, gradients, VML fallbacks or images. Comprehensive email quality audit: CSS compatibility, spam scoring, link validation, accessibility, images, inbox preview, size (Gmail clipping), template variables, content overflow, visual fallbacks, dark-mode and mobile text contrast, design consistency, structural faults in Outlook-only VML, style survival (CSS a client parses and then discards, such as a stylesheet past Gmail's 16 KB ceiling or every rule after a `}}`), and client targeting (HowToTarget hacks such as Gmail u+.body or MSO conditionals). For HTML input, findings tied to a specific element carry loc (line, column, offset). Compatibility is collapsed to one finding per problem listing the clients it affects; pass detail:'full' for the per-client breakdown with fix snippets. Use skip to omit checks, targetingPolicy to change how targeted scopes affect scores, and clients to narrow which clients are reported.
| Name | Type | Req | Description |
|---|---|---|---|
| clients | array | – | Only report these client IDs (e.g. ['gmail-web','outlook-windows']). The fastest way to cut the response when you care about specific clients. Use list_clients for the IDs. |
| detail | string | – | 'summary' (default) returns one entry per error or warning, listing the clients it affects, and only counts info findings (safe fallbacks). 'full' returns one entry per client with fix snippets, info… |
| emailType | string | – | 'transactional' (receipts, password resets, codes, alerts: no unsubscribe link required) or 'marketing'. Omitted: guessed from the content, which misses many transactional emails. |
| format | string | – | Source format: 'html' (default), 'jsx' (React Email), 'mjml', or 'maizzle' (HTML template or Vue single-file component). Anything but 'html' is compiled before analysis and sets the syntax of the fix… |
| html | string | yes | The email source |
| previousHtml | string | – | The design to hold this version to, usually your first draft. Omitted: the first version of this email you audited recently (matched by <title> and text). |
| skip | array | – | Checks to skip (e.g. ['spam', 'images']) |
| targetingPolicy | string | – | 'progressive' (default) suppresses compatibility false-positives inside client-targeted scopes and only flags deprecated or dangerous hacks. 'strict' treats targeting as non-standard and reports ever… |
No output schema declared.
No examples provided.
build_email Build Email ~173
Generate a cross-client-compatible email from a brief using Emailens's self-healing loop (generate → score across 21 clients → repair). Output stays in the framework you choose. Returns a runId immediately , poll get_build_status for progress and the final code. Requires a Pro/Team API key.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Output framework: 'html' (default), 'jsx', 'mjml', or 'maizzle' |
| intent | string | yes | What the email should be and contain , the brief to build from |
| maxIterations | number | – | Max repair rounds, 1-8 (default 5) |
| seedHtml | string | – | Optional existing code to improve from instead of starting blank |
| threshold | number | – | Target compatibility score, 50-100 (default 90) |
No output schema declared.
No examples provided.
capture_screenshots Capture Screenshots ~105
Capture real email screenshots across 21 clients (Gmail, Outlook, Apple Mail, etc.) with light and dark mode variants. Screenshots are rendered in real browsers and hosted on CDN.
| Name | Type | Req | Description |
|---|---|---|---|
| clients | array | – | Filter to specific client IDs |
| format | string | – | Input format |
| html | string | yes | The email source |
| modes | array | – | Screenshot modes (default: ['light']) |
| title | string | – | Name for the hosted preview |
No output schema declared.
No examples provided.
check_deliverability Check Deliverability ~48
Check email deliverability for a domain , SPF, DKIM, DMARC, MX, BIMI.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Domain to check (e.g. 'company.com') |
No output schema declared.
No examples provided.
diff_emails Diff Emails ~57
Compare two email HTML versions , shows score changes, fixed issues, and regressions per client.
| Name | Type | Req | Description |
|---|---|---|---|
| after | string | yes | Modified email HTML |
| before | string | yes | Original email HTML |
| format | string | – | Input format |
No output schema declared.
No examples provided.
fix_email Fix Email ~68
Generate a structured fix prompt for email compatibility issues.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Input format , controls fix syntax |
| html | string | yes | The email HTML source code to fix |
| scope | string | – | Fix scope |
| selectedClientId | string | – | Client ID for scoped fixes |
No output schema declared.
No examples provided.
get_build_status Get Build Status ~50
Check a build_email run by runId , returns status, iteration, best compatibility score, and the current best source once available.
| Name | Type | Req | Description |
|---|---|---|---|
| runId | string | yes | The runId returned by build_email |
No output schema declared.
No examples provided.
list_clients List Email Clients ~49
List all 21 supported email clients with IDs, names, rendering engines, dark mode support, and deprecation status. Use the returned IDs to filter other tools like preview_email or capture_screenshots.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
preview_email Preview Email ~196
Full email compatibility preview , transforms HTML for 21 email clients, analyzes CSS, generates scores, simulates dark mode, checks inbox preview and email size.
| Name | Type | Req | Description |
|---|---|---|---|
| clients | array | – | Optional client ID filter |
| format | string | – | Source format: 'html' (default), 'jsx' (React Email), 'mjml', or 'maizzle' (HTML template or Vue single-file component). Anything but 'html' is compiled before analysis and sets the syntax of the fix… |
| html | string | yes | The email HTML source code |
| targetingPolicy | string | – | 'progressive' (default) suppresses compatibility false-positives inside client-targeted scopes and only flags deprecated or dangerous hacks. 'strict' treats targeting as non-standard and reports ever… |
No output schema declared.
No examples provided.
sandbox_get_inbox Get Sandbox Inbox ~40
Retrieve or auto-create your Emailens sandbox test email address for capturing test emails.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional friendly name for the sandbox inbox |
No output schema declared.
No examples provided.
sandbox_get_message Get Sandbox Message ~51
Get complete email details: HTML/text body, parsed headers, spam score, SPF/DKIM/DMARC auth status, and validated links.
| Name | Type | Req | Description |
|---|---|---|---|
| messageId | string | yes | ID of the sandbox message |
No output schema declared.
No examples provided.
sandbox_list_messages List Sandbox Messages ~32
List recently captured test emails in the Emailens sandbox.
| Name | Type | Req | Description |
|---|---|---|---|
| inboxId | string | – | Optional inbox ID filter |
No output schema declared.
No examples provided.
sandbox_wait_for_email Wait for Sandbox Email ~104
Poll and wait for a matching incoming test email in the sandbox (ideal for auth OTPs, magic links, transactional email assertions).
| Name | Type | Req | Description |
|---|---|---|---|
| inboxId | string | – | Optional inbox ID filter |
| sender | string | – | Substring match for sender address (case-insensitive) |
| subject | string | – | Substring match for email subject (case-insensitive) |
| timeoutSeconds | number | – | Max seconds to wait (default: 30, max: 60) |
No output schema declared.
No examples provided.
share_preview Share Preview ~68
Create a shareable link for an email preview. Recipients see the full analysis without needing an account. Requires the Dev plan or above.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Input format |
| html | string | yes | The email source |
| title | string | – | Display title for the share page |
No output schema declared.
No examples provided.
How do I install the Emailens MCP server?
Emailens MCP is a hosted endpoint at https://emailens.dev/api/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.
remote · emailens.dev
claude mcp add --transport http emailens-mcp 'https://emailens.dev/api/mcp'
What is the Emailens MCP server?
Emailens MCP is listed in the public MCP registry as io.github.emailens/mcp. Analyze, audit, fix and diff HTML, MJML, Maizzle and React Email across 21 email clients. This page covers its hosted endpoint (https://emailens.dev/api/mcp).
Is the Emailens MCP server safe to use?
Emailens MCP scores 85 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 Emailens MCP server expose?
Emailens MCP exposes 15 tools: preview_email, analyze_email, audit_email, fix_email, list_clients, and 10 more. Their descriptions and schemas cost roughly 2,034 tokens of context every time the server is loaded.
Does the Emailens MCP server require authentication?
No. We connected to Emailens MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Emailens MCP server still maintained?
Emailens MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.