{"generated_at":"2026-08-17T10:36:11+00:00","item":{"added_at":"2026-03-31T21:01:23.519000+00:00","analysis_method":"capability_triage","category":"Desktop Extension","description":"[Mailtrap.io](https://mailtrap.io) is a comprehensive email platform that helps developers and teams test, debug, and deliver emails safely. It provides ...","did":"ant-dir-gh-mailtrap-mailtrap-mcp","homepage_url":"","icon":"https://claude.ai/api/dxt/extensions/ant.dir.gh.mailtrap.mailtrap-mcp/versions/0.3.0/icon.png","id":"ant.dir.gh.mailtrap.mailtrap-mcp","installs":50694,"last_scanned":"","license":"MIT","long_description":"[Mailtrap.io](https://mailtrap.io) is a comprehensive email platform that helps developers and teams test, debug, and deliver emails safely. It provides both email testing (sandbox) and email delivery services. \n This MCP (Model Context Protocol) server provides AI assistants with the ability to: \n - Send emails via Mailtrap's delivery API \n - Test emails using Mailtrap's sandbox environment \n - Manage email templates (create, update, delete, list).","name":"Mailtrap","plutonium_url":"https://plutonium.pluto.security/detail.html?planet=claudesec&did=ant-dir-gh-mailtrap-mailtrap-mcp&utm_source=plutonium_analysis_skill&utm_medium=claude_skill&utm_campaign=connector_risk_assessment","publisher":"Mailtrap.io","publisher_url":"https://mailtrap.io","repository_url":"https://github.com/mailtrap/mailtrap-mcp","risk":"high","risk_severity":"high","security_risks":[{"description":"This connector can read data the connected service holds about you - documents, messages, contact lists, source code, customer records, or saved profile details - and pass it back to the AI.","evidence":"Connector has 23 tools; permissions on claude.ai/directory: \"unknown\". Data flows out of the connected service into the model.","remediation":{"block_tool_categories":[],"steps":["Connect using an account that only has access to the information you actually want Claude to read - not your main admin login.","When you grant access, pick the smallest set of folders, mailboxes, or channels possible.","Check the connector's activity log every so often to make sure nothing unexpected is being read."]},"risk_type":"reads_private_data","severity":"medium","title":"Reads your private information"},{"description":"This connector can post messages, emails, or chat replies on your behalf. Recipients will believe the message came from you, which makes phishing or social-engineering risks higher.","evidence":"5 sends externally tools on this connector - e.g. send-email, send-sandbox-email, show-sandbox-email-message, list-email-logs and 1 more.","remediation":{"block_tool_categories":["sends_externally"],"steps":["In the tools list below, turn off any tool tagged Block if you don't need Claude to send messages or emails on your behalf.","If you do enable sending, restrict it to a private channel or distribution list - never customer-facing or company-wide.","Read the message before it goes out: don't let Claude send anything without you confirming first."]},"risk_type":"sends_messages_as_you","severity":"medium","title":"Can send messages as you"},{"description":"This connector can edit, rename, overwrite, or otherwise modify records in the connected service. If a request gets manipulated, your data could be altered without you noticing.","evidence":"6 state change tools on this connector - e.g. create-template, update-template, create-sandbox-project, create-sandbox-inbox and 2 more.","remediation":{"block_tool_categories":["state_change"],"steps":["Try the connector on a test account first to see what it changes before letting it touch your real records.","Where the connected service supports it, give Claude read-only access and only allow writes for the specific things you need updated.","In the tools list below, turn off any tool you don't actively need - the ones tagged Block are the most important to disable."]},"risk_type":"modifies_data","severity":"medium","title":"Can change or update your information"},{"description":"This connector can erase records, files, or accounts. Once deleted the data may be unrecoverable - even an accidental request can cause permanent loss.","evidence":"5 destructive tools on this connector - e.g. delete-template, delete-sandbox-project, delete-sandbox-inbox, clean-sandbox-inbox and 1 more.","remediation":{"block_tool_categories":["destructive"],"steps":["In the tools list below, turn off any tool tagged Block - most workflows don't need Claude to delete anything.","If you really do need deletion, use a login that doesn't have delete permission and have a person handle removals manually.","Make sure the connected service has a trash / recycle bin enabled so accidental deletes can be recovered."]},"risk_type":"deletes_data","severity":"high","title":"Can permanently delete data"}],"signature_status":"unsigned","source_code_reviewed":true,"tags":["reads_private_data","email_messaging","database_access","deletes_data"],"tools":[{"description":"","name":"send-email","risk":{"category":"sends_externally","level":"medium","recommendation":"Restrict to specific channels; require confirmation before sending. Disable if the connector is used in untrusted contexts.","why":"Sends a message or post on the user's behalf to people or channels outside the conversation. Phishing, leaking secrets, or impersonation become possible if the tool is hijacked."}},{"description":"","name":"create-template","risk":{"category":"state_change","level":"medium","recommendation":"Allow only for low-stakes resources; require approval for production data changes.","why":"Creates, modifies, or uploads data on the connected service. Hijacking the tool can pollute records, plant content, or create rogue resources that bill the user."}},{"description":"","name":"list-templates"},{"description":"","name":"update-template","risk":{"category":"state_change","level":"medium","recommendation":"Allow only for low-stakes resources; require approval for production data changes.","why":"Creates, modifies, or uploads data on the connected service. Hijacking the tool can pollute records, plant content, or create rogue resources that bill the user."}},{"description":"","name":"delete-template","risk":{"category":"destructive","level":"high","recommendation":"Block by default. Only enable for read-only or sandbox accounts; require explicit human confirmation for any destructive action.","why":"Irreversibly removes data or resources. A prompt-injection or mistaken instruction could destroy production data with no recovery path."}},{"description":"","name":"send-sandbox-email","risk":{"category":"sends_externally","level":"medium","recommendation":"Restrict to specific channels; require confirmation before sending. Disable if the connector is used in untrusted contexts.","why":"Sends a message or post on the user's behalf to people or channels outside the conversation. Phishing, leaking secrets, or impersonation become possible if the tool is hijacked."}},{"description":"","name":"get-sandbox-messages"},{"description":"","name":"show-sandbox-email-message","risk":{"category":"sends_externally","level":"medium","recommendation":"Restrict to specific channels; require confirmation before sending. Disable if the connector is used in untrusted contexts.","why":"Sends a message or post on the user's behalf to people or channels outside the conversation. Phishing, leaking secrets, or impersonation become possible if the tool is hijacked."}},{"description":"","name":"list-sandbox-projects"},{"description":"","name":"create-sandbox-project","risk":{"category":"state_change","level":"medium","recommendation":"Allow only for low-stakes resources; require approval for production data changes.","why":"Creates, modifies, or uploads data on the connected service. Hijacking the tool can pollute records, plant content, or create rogue resources that bill the user."}},{"description":"","name":"delete-sandbox-project","risk":{"category":"destructive","level":"high","recommendation":"Block by default. Only enable for read-only or sandbox accounts; require explicit human confirmation for any destructive action.","why":"Irreversibly removes data or resources. A prompt-injection or mistaken instruction could destroy production data with no recovery path."}},{"description":"","name":"create-sandbox-inbox","risk":{"category":"state_change","level":"medium","recommendation":"Allow only for low-stakes resources; require approval for production data changes.","why":"Creates, modifies, or uploads data on the connected service. Hijacking the tool can pollute records, plant content, or create rogue resources that bill the user."}},{"description":"","name":"get-sandbox-inbox"},{"description":"","name":"update-sandbox-inbox","risk":{"category":"state_change","level":"medium","recommendation":"Allow only for low-stakes resources; require approval for production data changes.","why":"Creates, modifies, or uploads data on the connected service. Hijacking the tool can pollute records, plant content, or create rogue resources that bill the user."}},{"description":"","name":"delete-sandbox-inbox","risk":{"category":"destructive","level":"high","recommendation":"Block by default. Only enable for read-only or sandbox accounts; require explicit human confirmation for any destructive action.","why":"Irreversibly removes data or resources. A prompt-injection or mistaken instruction could destroy production data with no recovery path."}},{"description":"","name":"clean-sandbox-inbox","risk":{"category":"destructive","level":"high","recommendation":"Block by default. Only enable for read-only or sandbox accounts; require explicit human confirmation for any destructive action.","why":"Irreversibly removes data or resources. A prompt-injection or mistaken instruction could destroy production data with no recovery path."}},{"description":"","name":"get-sending-stats"},{"description":"","name":"list-email-logs","risk":{"category":"sends_externally","level":"medium","recommendation":"Restrict to specific channels; require confirmation before sending. Disable if the connector is used in untrusted contexts.","why":"Sends a message or post on the user's behalf to people or channels outside the conversation. Phishing, leaking secrets, or impersonation become possible if the tool is hijacked."}},{"description":"","name":"get-email-log-message","risk":{"category":"sends_externally","level":"medium","recommendation":"Restrict to specific channels; require confirmation before sending. Disable if the connector is used in untrusted contexts.","why":"Sends a message or post on the user's behalf to people or channels outside the conversation. Phishing, leaking secrets, or impersonation become possible if the tool is hijacked."}},{"description":"","name":"list-sending-domains"},{"description":"","name":"get-sending-domain"},{"description":"","name":"create-sending-domain","risk":{"category":"state_change","level":"medium","recommendation":"Allow only for low-stakes resources; require approval for production data changes.","why":"Creates, modifies, or uploads data on the connected service. Hijacking the tool can pollute records, plant content, or create rogue resources that bill the user."}},{"description":"","name":"delete-sending-domain","risk":{"category":"destructive","level":"high","recommendation":"Block by default. Only enable for read-only or sandbox accounts; require explicit human confirmation for any destructive action.","why":"Irreversibly removes data or resources. A prompt-injection or mistaken instruction could destroy production data with no recovery path."}}],"tools_count":23,"type":"desktop_extension","url":"","uuid":"de6a9e45-625b-5d3f-9bb6-23631e1d1a3d","version":"0.3.0"},"query_key":"mailtrap","schema_version":1,"status":"match"}