Super Send

The vendor ships and maintains the server itself. A wrapper built by Zapier, Composio or a similar third party does not count as official. The status was established by hand on 2026-09-07. On 2026-09-04 the recorded URL served a documentation page, not an MCP endpoint. That is where to read about the server, not where to connect to it. An agent needs the second.

mcp_status, verbatim from the file:

official

mcp_url, verbatim from the file:

https://mcp.supersend.io/mcp ; https://docs.supersend.io/docs/mcp-server (endpoint mcp.supersend.io)

• https://mcp.supersend.io/mcp
• https://docs.supersend.io/docs/mcp-server

A tool below is one the server NAMES. Nobody has called it. That is the same two tier honesty rule the rest of the directory runs on: a named tool is research, and BENCH-TESTED stays the only claim that anybody ran anything.

• activate_campaign
  Turn a campaign on
  evidence: in the vendor docs · calling it reads · required: CampaignId
• add_to_blacklist
  Add to blacklist
  evidence: in the vendor docs · calling it writes
• analyze_capacity_and_schedule
  Capacity planning: when campaigns finish, allocated capacity
  evidence: in the vendor docs · calling it reads
• analyze_domain_health
  Per-domain DNS/health: SPF, DKIM, DMARC, MX, at-risk flags
  evidence: in the vendor docs · calling it reads
• analyze_sender_health
  Per-sender health: sends, bounces, at-risk flags
  evidence: in the vendor docs · calling it reads
• bulk_import_contacts
  Bulk import contacts
  evidence: in the vendor docs · calling it writes
• create_campaign
  Create a new campaign
  evidence: in the vendor docs · calling it writes · required: name, TeamId
• create_contact
  Create/upsert contact or profile-only
  evidence: in the vendor docs · calling it writes · required: TeamId
• create_webhook
  Create a webhook
  evidence: in the vendor docs · calling it writes · required: url, events
• deactivate_campaign
  Turn a campaign off
  evidence: in the vendor docs · calling it reads · required: CampaignId
• delete_contact
  Delete a contact (soft delete)
  evidence: in the vendor docs · calling it writes · required: ContactId
• diagnose_deliverability
  Deliverability diagnosis: reply rate, bounces, placement tests
  evidence: in the vendor docs · calling it reads
• get_campaign
  Get a campaign by ID
  evidence: in the vendor docs · calling it reads · required: CampaignId
• get_campaign_sequence
  Get campaign sequence
  evidence: in the vendor docs · calling it reads · required: CampaignId
• get_contact
  Get a contact by ID
  evidence: in the vendor docs · calling it reads · required: ContactId
• get_conversation
  Get a conversation by ID
  evidence: in the vendor docs · calling it reads · required: ConversationId
• get_conversation_messages
  Get messages in a conversation
  evidence: in the vendor docs · calling it reads · required: ConversationId
• get_domain
  Get a domain by ID
  evidence: in the vendor docs · calling it reads · required: DomainId
• get_domain_bounce_insights
  AI bounce breakdown per domain
  evidence: in the vendor docs · calling it reads · required: DomainId
• get_event
  Get an event by ID
  evidence: in the vendor docs · calling it reads · required: EventId
• get_health
  Check SuperSend API health and connectivity
  evidence: in the vendor docs · calling it reads
• get_outbound_summary
  Team outbound metrics: sends, replies, top campaigns
  evidence: in the vendor docs · calling it reads
• get_sender
  Get a sender by ID
  evidence: in the vendor docs · calling it reads · required: SenderId
• get_sender_bounce_insights
  AI bounce type breakdown per sender
  evidence: in the vendor docs · calling it reads · required: SenderId
• get_team
  Get a team by ID
  evidence: in the vendor docs · calling it reads · required: TeamId
• list_blacklist
  List blacklisted emails/domains
  evidence: in the vendor docs · calling it reads
• list_campaigns
  List campaigns in a team
  evidence: in the vendor docs · calling it reads · required: TeamId
• list_contacts
  List contacts in a team
  evidence: in the vendor docs · calling it reads · required: TeamId
• list_conversations
  List conversations
  evidence: in the vendor docs · calling it reads
• list_domains
  List managed domains
  evidence: in the vendor docs · calling it reads
• list_events
  List events (sends, opens, clicks, replies, bounces)
  evidence: in the vendor docs · calling it reads
• list_labels
  List conversation labels
  evidence: in the vendor docs · calling it reads
• list_placement_tests
  List placement tests
  evidence: in the vendor docs · calling it reads
• list_senders
  List email senders
  evidence: in the vendor docs · calling it reads
• list_teams
  List teams the user has access to
  evidence: in the vendor docs · calling it reads
• list_webhooks
  List webhooks
  evidence: in the vendor docs · calling it reads
• purchase_domain
  Purchase domains (requires payment method, contact details)
  evidence: in the vendor docs · calling it spends money
• purchase_domains_and_mailboxes
  Purchase domains and mailboxes in one transaction
  evidence: in the vendor docs · calling it spends money
• purchase_mailbox
  Purchase mailboxes for existing domains
  evidence: in the vendor docs · calling it spends money
• remove_from_blacklist
  Remove from blacklist
  evidence: in the vendor docs · calling it writes
• send_conversation_message
  Send a message in a conversation
  evidence: in the vendor docs · calling it writes · required: ConversationId
• update_campaign_sequence
  Update campaign sequence
  evidence: in the vendor docs · calling it writes
• update_contact
  Update a contact
  evidence: in the vendor docs · calling it writes · required: ContactId
• update_sender
  Update a sender
  evidence: in the vendor docs · calling it writes · required: SenderId
• verify_email
  Standalone email verification
  evidence: in the vendor docs · calling it reads · required: email

141 of the 741 entries that record an official or community MCP server carry a harvested tool list. The other 600 are unmeasured, which is not the same as empty. Harvest last run 2026-09-27. Every name across every server is on the tools index.

Install, as the source shows it:

npm install -g supersendtx-cli

quoted from https://www.npmjs.com/package/supersendtx-cli on 2026-09-27, via npm

Packages seen, with the version on 2026-09-27:

• npm: supersendtx-cli 0.15.7

A CLI being listed means the harvest found an install command or a package on a stated date. Nobody has run it. Every command is quoted verbatim from the URL beneath it. Harvest date 2026-09-27.

api_gate, verbatim from the file:

paid

No documentation URL recorded.

727 of 1252 entries are in the same position. Blank is legal and it is published as blank.

Not measured. github_url, github_stars, github_last_commit and github_archived are null on every entry in this build.

The refresh rail specced in SPEC section 7.2 has not been run. An unstamped star count is a lie, so nothing is shown rather than something stale.

No GitHub organisation could be tied to supersend.io with evidence on 2026-09-08.

Recorded by the harvest: github candidates were seen but none passed the evidence rules.

3 candidate accounts seen and rejected by the evidence rules: Super-Send, SpacePayafrica, MeetContactsApp. A name match alone is never accepted; the account has to point at the vendor domain.

• Run an email sequence
• Warm up an inbox
• Provision sending infrastructure
• Check inbox placement

A job tag means the vendor says the tool does this. It is not a test result, not proof the capability is reachable through the tool's MCP server, and not proof it is available on the gate this entry records.

Tagged by machine-pass on 2026-08-25 against the closed 56 job vocabulary. 271 of 1,252 entries carry at least one tag; 849 tags are assigned in total.

• https://www.pulsemcp.com/servers/supersend
• https://supersend.io
• https://mcp.supersend.io/mcp

3 source URLs. Raw sources field, verbatim:

https://www.pulsemcp.com/servers/supersend, https://supersend.io, https://mcp.supersend.io/mcp

Every field above is rendered from directory.json exactly as the build produced it. Nothing is summarised and nothing is dropped. The one change made at render time is typographic and it is disclosed on the methodology page.