Mailtrap MCP Server
mcp-mailtrap
npm
v0.9.0
Published by mailtrap — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Official MCP Server for Mailtrap
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 4 = 96. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 1
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([get-sandbox-attachment, create-contact-export, get-contact-export, list-inbound-messages, get-inbound-message, list-inbound-threads]) co-exist with external-action tools ([send-email, create-webhook, update-webhook, delete-webhook]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [get-sandbox-attachment, create-contact-export, get-contact-export, list-inbound-messages, get-inbound-message, list-inbound-threads] → sinks [send-em
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow get-sandbox-attachment → send-email
Tools 125
Each tool and what it can reach — statically extracted from the published source.
create-contact-exportingests untrusted inputcreate-webhooknetwork egressdelete-webhooknetwork egressget-contact-exportingests untrusted inputget-inbound-messageingests untrusted inputget-sandbox-attachmentingests untrusted inputlist-inbound-messagesingests untrusted inputlist-inbound-threadsingests untrusted inputsend-emailnetwork egressupdate-webhooknetwork egress
Show 115 more tools ↓
batch-send-bulk-emailno sensitive capabilitybatch-send-sandbox-emailno sensitive capabilitybatch-send-transactional-emailno sensitive capabilitybulk-update-permissionsno sensitive capabilitycancel-email-campaignno sensitive capabilityclean-sandbox-inboxno sensitive capabilitycreate-api-tokenno sensitive capabilitycreate-company-infono sensitive capabilitycreate-contactno sensitive capabilitycreate-contact-eventno sensitive capabilitycreate-contact-fieldno sensitive capabilitycreate-contact-importno sensitive capabilitycreate-contact-listno sensitive capabilitycreate-email-campaignno sensitive capabilitycreate-inbound-folderno sensitive capabilitycreate-inbound-inboxno sensitive capabilitycreate-sandbox-inboxno sensitive capabilitycreate-sandbox-projectno sensitive capabilitycreate-sending-domainno sensitive capabilitycreate-sub-accountno sensitive capabilitycreate-suppressionno sensitive capabilitycreate-templateno sensitive capabilitycreate-tracking-opt-outno sensitive capabilitydelete-api-tokenno sensitive capabilitydelete-contactno sensitive capabilitydelete-contact-fieldno sensitive capabilitydelete-contact-listno sensitive capabilitydelete-email-campaignno sensitive capabilitydelete-inbound-folderno sensitive capabilitydelete-inbound-inboxno sensitive capabilitydelete-inbound-messageno sensitive capabilitydelete-inbound-threadno sensitive capabilitydelete-sandbox-inboxno sensitive capabilitydelete-sandbox-messageno sensitive capabilitydelete-sandbox-projectno sensitive capabilitydelete-sending-domainno sensitive capabilitydelete-suppressionno sensitive capabilitydelete-templateno sensitive capabilitydelete-tracking-opt-outno sensitive capabilityenable-sandbox-email-addressno sensitive capabilityforward-inbound-messageno sensitive capabilityforward-sandbox-messageno sensitive capabilityget-api-tokenno sensitive capabilityget-billing-usageno sensitive capabilityget-company-infono sensitive capabilityget-contactno sensitive capabilityget-contact-fieldno sensitive capabilityget-contact-importno sensitive capabilityget-contact-listno sensitive capabilityget-email-campaignno sensitive capabilityget-email-campaign-statsno sensitive capabilityget-email-log-messageno sensitive capabilityget-inbound-folderno sensitive capabilityget-inbound-inboxno sensitive capabilityget-inbound-threadno sensitive capabilityget-permission-resourcesno sensitive capabilityget-sandbox-inboxno sensitive capabilityget-sandbox-message-emlno sensitive capabilityget-sandbox-message-headersno sensitive capabilityget-sandbox-message-htmlno sensitive capabilityget-sandbox-message-html-analysisno sensitive capabilityget-sandbox-message-html-sourceno sensitive capabilityget-sandbox-message-rawno sensitive capabilityget-sandbox-message-spam-scoreno sensitive capabilityget-sandbox-message-textno sensitive capabilityget-sandbox-messagesno sensitive capabilityget-sandbox-projectno sensitive capabilityget-sending-domainno sensitive capabilityget-sending-statsno sensitive capabilityget-templateno sensitive capabilityget-webhookno sensitive capabilitylist-account-accessesno sensitive capabilitylist-accountsno sensitive capabilitylist-api-tokensno sensitive capabilitylist-contact-fieldsno sensitive capabilitylist-contact-listsno sensitive capabilitylist-email-campaignsno sensitive capabilitylist-email-logsno sensitive capabilitylist-inbound-foldersno sensitive capabilitylist-inbound-inboxesno sensitive capabilitylist-sandbox-attachmentsno sensitive capabilitylist-sandbox-projectsno sensitive capabilitylist-sandboxesno sensitive capabilitylist-sending-domainsno sensitive capabilitylist-sub-accountsno sensitive capabilitylist-suppressionsno sensitive capabilitylist-templatesno sensitive capabilitylist-tracking-opt-outsno sensitive capabilitylist-webhooksno sensitive capabilitymark-sandbox-as-readno sensitive capabilityremove-account-accessno sensitive capabilityreply-all-to-inbound-messageno sensitive capabilityreply-to-inbound-messageno sensitive capabilityreset-api-tokenno sensitive capabilityreset-email-campaignno sensitive capabilityreset-sandbox-credentialsno sensitive capabilityreset-sandbox-email-addressno sensitive capabilityschedule-email-campaignno sensitive capabilitysend-sandbox-emailno sensitive capabilitysend-sending-domain-setup-instructionsno sensitive capabilityshow-sandbox-email-messageno sensitive capabilitystart-email-campaignno sensitive capabilityterminate-email-campaignno sensitive capabilityupdate-company-infono sensitive capabilityupdate-contactno sensitive capabilityupdate-contact-fieldno sensitive capabilityupdate-contact-listno sensitive capabilityupdate-email-campaignno sensitive capabilityupdate-inbound-folderno sensitive capabilityupdate-inbound-inboxno sensitive capabilityupdate-sandbox-inboxno sensitive capabilityupdate-sandbox-messageno sensitive capabilityupdate-sandbox-projectno sensitive capabilityupdate-sending-domainno sensitive capabilityupdate-templateno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (125 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 6
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.9.0 latest |
A 96/100 | 1 | 1.13.0 | 2026-09-07 |
v0.8.0 |
A 96/100 | 1 | 1.13.0 | 2026-09-01 |
v0.7.0 |
A 96/100 | 1 | 1.12.1 | 2026-08-20 |
v0.6.0 |
A 96/100 | 1 | 1.12.1 | 2026-08-04 |
v0.5.0 |
A 96/100 | 1 | 1.12.1 | 2026-07-28 |
Show 1 more version ↓
v0.4.3 |
A 100/100 | 0 | 1.5.0 | 2026-07-22 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan mcp-mailtrap --onlineMore in API Development
Adapters for the FrontMCP framework
Transcend MCP Server — Admin tools.
Transcend MCP Server — Assessments tools.
MCP Server for Bling
MCP Server for Blogger API
Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, and more.