Community Gmail server with auto-auth: search, read and send email via MCP.
Nothing to run from here
SendGrid Transactional is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
200
downloads a day
local
runs on your machine
766
downloads in 30d
What it does
SendGrid transactional email: preflight send, templates, and delivery diagnostics.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'SENDGRID_API_KEY=${SENDGRID_API_KEY}' --env 'SENDGRID_FROM_EMAIL=${SENDGRID_FROM_EMAIL}' --transport stdio sendgrid-transactional-mcp '--' npx -y @neschadin/sendgrid-mcp
# 2 — ask your agent for something these tools do
# search_message_activity, get_message_activity, list_event_webhooks and 75 more
It needs SENDGRID_API_KEY, SENDGRID_FROM_EMAIL: this reads them from your environment, so export them first.
SendGrid Transactional costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
NEAll 2 servers
Neschadin2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts SendGrid Transactional as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads SENDGRID_API_KEY (SendGrid API key (SG....)), SENDGRID_FROM_EMAIL (Default From address. Must be a verified sender) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx SENDGRID_API_KEY …, setx SENDGRID_FROM_EMAIL … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'SENDGRID_API_KEY=${SENDGRID_API_KEY}' --env 'SENDGRID_FROM_EMAIL=${SENDGRID_FROM_EMAIL}' --transport stdio sendgrid-transactional-mcp '--' npx -y @neschadin/sendgrid-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: SENDGRID_API_KEY — SendGrid API key (SG....); SENDGRID_FROM_EMAIL — Default From address. Must be a verified sender.. You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
78 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search SendGrid Email Activity (GET /v3/messages). Pass xMessageId for the Mail Send x-message-id header; it is compiled to msg_id LIKE. offset is not supported by this API. On 403/404, or an empty EU Activity result, falls back to POST /v3/logs.
No parameter schema on file.
Get Email Activity for one message. msgId may be a full msg_id or the Mail Send x-message-id (resolved with msg_id LIKE). On Activity 403/404 for a full id, falls back to POST /v3/logs.
No parameter schema on file.
List all Event Webhook configurations directly from SendGrid.
No parameter schema on file.
Get one Event Webhook config by ID from SendGrid.
No parameter schema on file.
Update Event Webhook settings in SendGrid (URL, enabled flag, and event toggles).
No parameter schema on file.
Enable or disable SendGrid signature verification for a specific Event Webhook.
No parameter schema on file.
Create, delete, or test a SendGrid Event Webhook. create requires url. delete requires id. test sends a sample event to url, or to the saved webhook url when only id is set.
No parameter schema on file.
Show local webhook receiver status for incoming SendGrid Event Webhook posts.
No parameter schema on file.
Read recent Event Webhook payloads captured by this server (for SendGrid-side diagnostics).
No parameter schema on file.
Clear locally captured SendGrid Event Webhook payloads.
No parameter schema on file.
Classify SendGrid API errors and return likely causes with targeted remediation steps.
No parameter schema on file.
Run targeted delivery triage for common incidents (202 accepted no inbox, processing, sender identity, DMARC/auth, template drops, deferrals, unsubscribe spikes).
No parameter schema on file.
Analyze Event Webhook events for non-human engagement patterns, machine opens, and unique-open approximation.
No parameter schema on file.
List ASM unsubscribe groups (GET /v3/asm/groups). Use the id as asm.groupId when sending. This is not a marketing contact list.
No parameter schema on file.
Create an ASM unsubscribe group (POST /v3/asm/groups) for transactional mail. Does not create a marketing list.
No parameter schema on file.
List SendGrid suppressions by type (bounces, blocks, unsubscribes, spam reports, invalid emails, global unsubscribes).
No parameter schema on file.
Check bounce, block, global unsubscribe, spam report, invalid email, and ASM group suppressions (GET /v3/asm/suppressions/{email}) for one recipient.
No parameter schema on file.
Get email statistics. dimension=global is the account daily rollup. category requires categories. mailbox_provider, geo, browser, device, and client are the other SendGrid stats cuts. Browser, device, and client stats retain about 7 days.
No parameter schema on file.
List category names (GET /v3/categories) so get_email_stats dimension=category can be given a real categories array.
No parameter schema on file.
Search Email Logs (POST /v3/logs). Use when Email Activity is unavailable, especially for EU regional subusers. Query fields: sg_message_id =, subject =, to_email =, status IN, reason =, categories IN, sg_message_id_created_at comparisons. Combine with AND. No nesting. Parent accounts pass exactly…
No parameter schema on file.
Remove one recipient from a suppression list: bounce, block, spam_report, invalid_email, global unsubscribe, or one ASM group. Does not delete the group itself.
No parameter schema on file.
Run this before any send_* call. Validates /v3/mail/send payload shape, active dynamic template, sender identity (domain authentication or verified sender), link branding alignment, recipient suppressions, and scheduling limits (send_at must be in the future and within 72 hours per SendGrid Mail…
No parameter schema on file.
Preferred production send path: runs validate_send_request checks first, then POST /v3/mail/send only when no blockers (and optionally no warnings with abortOnWarnings). Use validate_send_request alone for a dry-run review before calling send_email_advanced or send_template_email_advanced.
No parameter schema on file.
Read SendGrid account overview (account type, reputation, and related metadata).
No parameter schema on file.
Read SendGrid user profile (company, address, contact fields).
No parameter schema on file.
Read SendGrid account email credits/quota overview.
No parameter schema on file.
List OAuth scopes granted to the current SendGrid API key (GET /v3/scopes). Use this after a 403 to see what the key can actually call.
No parameter schema on file.
List SendGrid subusers for the parent API key (GET /v3/subusers). Use a returned username as onBehalfOf on later calls, or as SENDGRID_ON_BEHALF_OF. Pass onBehalfOf="parent" when that env var is already set and this list must run as the parent.
No parameter schema on file.
List verified sender identities configured in SendGrid.
No parameter schema on file.
Read one verified sender identity by ID.
No parameter schema on file.
List domain authentication (whitelabel domain) records and DNS validation state.
No parameter schema on file.
Read one authenticated domain record by ID.
No parameter schema on file.
List link branding (click-tracking domain) records.
No parameter schema on file.
Read one branded link record by ID.
No parameter schema on file.
List SendGrid account alerts (usage limits and stats notifications).
No parameter schema on file.
Read one SendGrid alert by ID.
No parameter schema on file.
Create a verified sender identity. SendGrid emails a verification link to from_email.
No parameter schema on file.
Resend verification email for a verified sender identity.
No parameter schema on file.
Delete a verified sender identity by ID.
No parameter schema on file.
Start domain authentication (whitelabel domain). Returns DNS records to configure.
No parameter schema on file.
Validate DNS for an authenticated domain. Returns validation results and errors.
No parameter schema on file.
Validate DNS for a branded link (click-tracking domain) by ID.
No parameter schema on file.
Update a branded link (e.g. set default=true for click-tracking domain).
No parameter schema on file.
Create a SendGrid alert (usage_limit or stats_notification).
No parameter schema on file.
Update an existing SendGrid alert by ID.
No parameter schema on file.
Delete a SendGrid alert by ID.
No parameter schema on file.
Read Enforced TLS settings (GET /v3/user/settings/enforced_tls). require_tls drops mail when the recipient MX does not offer TLS.
No parameter schema on file.
List SendGrid mail settings summaries (footer, bounce purge, spam check, etc.).
No parameter schema on file.
Read one SendGrid mail setting by name.
No parameter schema on file.
List SendGrid tracking settings summaries (click, open, subscription, etc.).
No parameter schema on file.
Read one SendGrid tracking setting by name.
No parameter schema on file.
List inbound parse (receive email webhook) settings.
No parameter schema on file.
Update one SendGrid mail setting (PATCH /mail_settings/{name}). Payload fields depend on setting type.
No parameter schema on file.
Update one SendGrid tracking setting (click/open/subscription/google_analytics).
No parameter schema on file.
Create inbound parse setting. Hostname MX must point to SendGrid.
No parameter schema on file.
Update inbound parse setting for a hostname.
No parameter schema on file.
Delete inbound parse setting by hostname.
No parameter schema on file.
Send email with full /mail/send payload surface (content/template, tracking, asm, scheduling, categories, etc).…
No parameter schema on file.
Send a dynamic-template email with optional cc/bcc, reply-to, asm, categories, custom args, and scheduling.…
No parameter schema on file.
Send using mail_settings.sandbox_mode=true for payload/template validation without live recipient delivery.…
No parameter schema on file.
Create a SendGrid batch ID for scheduled sends and later pause/cancel control.
No parameter schema on file.
Schedule an email by setting send_at. Creates batch ID automatically when not provided.…
No parameter schema on file.
List paused or canceled scheduled-send batches (GET /v3/user/scheduled_sends). A batch that was only scheduled with send_at, and never paused or canceled, is not in this list.
No parameter schema on file.
Read pause/cancel state for one scheduled-send batch_id. SendGrid answers a missing batch with 200 and an empty array; this tool reports that as not found.
No parameter schema on file.
Pause a scheduled send batch by batch ID.
No parameter schema on file.
Resume a previously paused/canceled batch by deleting its scheduled-send status.
No parameter schema on file.
Cancel a scheduled send batch. This is not guaranteed close to send time.
No parameter schema on file.
Send a test email using a template with mock data. Uses mail_settings.sandbox_mode by default (SendGrid accepts but does not deliver). Set liveDelivery=true with confirmToken="CONFIRM" for real delivery.
No parameter schema on file.
No parameter schema on file.
List all dynamic SendGrid templates with their IDs, names, and version counts
No parameter schema on file.
Rename a dynamic template (updates the template name, not a version label)
No parameter schema on file.
Bulk rename templates by ID and/or current name. Supports dry-run and stop-on-error.
No parameter schema on file.
Get full HTML content of a template's active (or specific) version
No parameter schema on file.
Create a new dynamic template with a first version
No parameter schema on file.
Update the HTML, subject, or name of a specific template version
No parameter schema on file.
Activate a specific version of a template (only one version can be active at a time)
No parameter schema on file.
Delete all inactive versions for one or more templates (keeps the active version only)
No parameter schema on file.
Permanently delete a SendGrid template and all its versions. Use with caution.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install SendGrid Transactional or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 3.0.3 · scanned 13 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest61e2b8699ff15a5b2ec40ab164dfd90f4748ece4d2a72db8d10eca65af07720e
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (78 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>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_account_info | no tags | |
| get_user_profile | no tags | |
| get_user_credits | no tags | |
| get_scopes | no tags | |
| list_subusers | no tags | |
| list_verified_senders | no tags | |
| get_verified_sender | no tags | |
| list_authenticated_domains | no tags | |
| get_authenticated_domain | no tags | |
| list_branded_links | no tags | |
| get_branded_link | no tags | |
| list_alerts | no tags | |
| get_alert | no tags | |
| create_verified_sender | no tags | |
| resend_verified_sender_verification | no tags | |
| delete_verified_sender | no tags | |
| create_authenticated_domain | no tags | |
| validate_authenticated_domain | no tags | |
| validate_branded_link | no tags | |
| update_branded_link | no tags | |
| create_alert | no tags | |
| update_alert | no tags | |
| delete_alert | no tags | |
| get_enforced_tls | no tags | |
| list_mail_settings | no tags | |
| get_mail_setting | no tags | |
| list_tracking_settings | no tags | |
| get_tracking_setting | no tags | |
| list_inbound_parse_settings | no tags | |
| update_mail_setting | no tags | |
| update_tracking_setting | no tags | |
| create_inbound_parse_setting | no tags | |
| update_inbound_parse_setting | no tags | |
| delete_inbound_parse_setting | no tags | |
| search_message_activity | no tags | |
| get_message_activity | no tags | |
| list_event_webhooks | no tags | |
| get_event_webhook | no tags | |
| update_event_webhook | external-sink | external-sink: keyword "webhook" |
| toggle_event_webhook_signature | external-sink | external-sink: keyword "webhook" |
| manage_event_webhook | external-sink | external-sink: keyword "webhook" |
| get_webhook_receiver_status | no tags | |
| get_received_webhook_events | no tags | |
| clear_received_webhook_events | external-sink | external-sink: keyword "webhook" |
| classify_sendgrid_error | no tags | |
| triage_delivery_issue | no tags | |
| analyze_engagement_anomalies | external-sink | external-sink: keyword "webhook" |
| list_asm_groups | no tags | |
| create_asm_group | no tags | |
| list_suppressions | no tags | |
| check_suppression | no tags | |
| get_email_stats | no tags | |
| list_categories | no tags | |
| search_email_logs | no tags | |
| delete_suppression | no tags | |
| send_email_advanced | external-sink | external-sink: keyword "send_email" |
| send_template_email_advanced | no tags | |
| send_sandbox_email | no tags | |
| create_batch_id | no tags | |
| schedule_email | no tags | |
| list_scheduled_sends | no tags | |
| get_scheduled_send | no tags | |
| pause_scheduled_send | no tags | |
| resume_scheduled_send | no tags | |
| cancel_scheduled_send | no tags | |
| send_test_email | no tags | |
| validate_send_request | no tags | |
| send_with_preflight | external-sink | external-sink: keyword "send_email" |
| sync_template_ids | no tags | |
| list_templates | no tags | |
| rename_template | no tags | |
| rename_templates_bulk | no tags | |
| get_template_html | no tags | |
| create_template | no tags | |
| update_template_html | no tags | |
| activate_template_version | no tags | |
| prune_inactive_template_versions | no tags | |
| delete_template | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest61e2b8699ff15a5b
Scanned2026-10-13
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 3.0.3. Pin a release below and the command asks for exactly that one.
3.0.3
12 Oct 2026
latestNo release note was published with this version.
3.0.2
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish SendGrid Transactional can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.