MCP server

Status — available today

Reply MCP is an official, live, remote Streamable HTTP MCP server exposing Reply.io’s sales-engagement, inbox, AI SDR (Jason), task, account, and help workflows as 70 tools for any MCP-compatible client — Claude, Cursor, Make, n8n, and custom agents.

Endpoint	https://mcp.reply.io/
Transport	Streamable HTTP (JSON-RPC 2.0, MCP protocol 2025-06-18)
Auth	x-api-key: <key> or Authorization: Bearer <key>
Rate limit	Hourly window, ~3000/hour (X-Rate-Limit-* headers on every response)
Sessions	None required — initialize and tools/list work without Mcp-Session-Id
Tools	70 — 31 read-only (readOnlyHint), 39 mutations (destructiveHint)

Connect

claude mcp add --transport http reply https://mcp.reply.io/ \
  --header "x-api-key: YOUR_REPLY_API_KEY"

Or in any MCP client config:

{
  "mcpServers": {
    "reply": {
      "type": "http",
      "url": "https://mcp.reply.io/",
      "headers": { "x-api-key": "YOUR_REPLY_API_KEY" }
    }
  }
}

Client-by-client instructions, the OAuth discovery flow, and rate limits: docs.reply.io/mcp/connect.

Contract essentials

What an agent needs to know before calling — full rules and the safe-retry matrix at docs.reply.io/mcp/tool-contract:

• Responses are SSE frames; the payload is a JSON string in result.content[0].text — {"Success":true,"Data":{...}} or {"Success":false,"ErrorCode":"...","ErrorMessage":"..."} (tool errors arrive as HTTP 200 with isError: true; branch on ErrorCode).
• Schemas are strict — additionalProperties: false; required fields reject null, "", [].
• Pagination is uniform — top (default 20, max 100) + skip; iterate until HasMore is false.
• Updates are patches — omitted fields keep their value; a passed list replaces the whole list.
• IDs come from resolvers — resolve exact numeric IDs with search_*/list_* tools first; never invent one, never ask the user for one.
• Batches cap at 100 and report per-item results (NotProcessed, AffectedContactIds) — report exact counts.
• Gate high-stakes tools — anything that sends, starts outreach, enrolls, blacklists, changes ownership, rejects a draft (also removes the contact from the sequence!), or switches Jason to Autonomous executes immediately with no undo. Confirm with the user first.

All 70 tools

Grouped by domain: read = readOnlyHint · write = destructiveHint · gate = confirm with the user first. Full signatures, arguments, enums, and failure modes: docs.reply.io/mcp/tools (site index: /mcp/tools).

Sequences — discover & inspect

Tool	Type	Purpose
reply_search_sequences	read	Find sequences by name / status / archive flag
reply_get_sequence_steps	read	Ordered steps of a sequence (type, delay, variants)
reply_get_sequence_step_variants	read	A/B content variants of one step
reply_get_sequence_stats	read	Email + LinkedIn metrics for one sequence
reply_compare_sequence_performance	read	Side-by-side metrics for up to 25 sequences

Sequences — control & configuration

Tool	Type	Purpose
reply_start_sequence	write · gate	Start or resume a sequence
reply_pause_sequence	write	Pause a sequence
reply_add_contact_to_sequence	write · gate	Enroll up to 100 contacts
reply_change_status_in_sequence	write	Set one contact’s per-sequence status
reply_assign_email_account_to_sequence	write	Link a mailbox
reply_assign_linkedin_account_to_sequence	write	Link a LinkedIn account
reply_assign_schedule_to_sequence	write	Set the sending schedule
reply_attach_offer_to_sequence	write	Attach an offer (AI SDR)
reply_attach_playbook_to_sequence	write	Attach a playbook (AI SDR)
reply_attach_knowledge_base_to_sequence	write	Attach a knowledge base (AI SDR)
reply_set_sequence_reply_mode	write · gate	Jason Review ↔ Autonomous mode

Contacts

Tool	Type	Purpose
reply_search_contacts	read	Look up by exact email or LinkedIn URL
reply_filter_contacts	read	Filter by list/sequence/free-text
reply_create_contact	write	Create a contact
reply_update_contact	write	Patch contact fields
reply_get_contact_activity	read	Activity history for one contact
reply_mark_contacts_as_replied	write	Mark up to 100 contacts as replied
reply_change_contact_owner	write · gate	Reassign contacts to another user
reply_blacklist_contact	write · gate	Blacklist an email or whole domain

Inbox & conversations

Tool	Type	Purpose
reply_get_inbox_emails	read	List inbox threads with previews
reply_send_inbox_reply	write · gate	Send a reply on a thread
reply_change_inbox_category	write	Assign/clear a thread category

Jason AI SDR — approvals & autopilot

Tool	Type	Purpose
reply_list_pending_approvals	read	The draft approval queue
reply_approve_message	write · gate	Approve one draft — sends immediately
reply_bulk_approve_messages	write · gate	Approve up to 100 drafts (atomic)
reply_reject_message	write · gate	Reject a draft AND remove the contact from the sequence
reply_regenerate_message	write	Ask Jason to rewrite a pending draft

Jason AI SDR — knowledge bases

Tool	Type	Purpose
reply_list_knowledge_bases	read	List knowledge bases
reply_get_knowledge_base	read	One knowledge base in full
reply_create_knowledge_base	write	Create a knowledge base
reply_update_knowledge_base	write	Rename / edit instructions
reply_add_knowledge_base_source	write	Add a URL source
reply_delete_knowledge_base_source	write	Remove a URL source

Jason AI SDR — reply handlers

Tool	Type	Purpose
reply_list_reply_handlers	read	List reply handlers in a knowledge base
reply_get_reply_handler	read	One reply handler in full
reply_create_reply_handler	write	Add a handler (question type → instructions)
reply_update_reply_handler	write	Patch a handler
reply_delete_reply_handler	write	Remove a handler

Jason AI SDR — reengagement cards

Tool	Type	Purpose
reply_list_reengagement_cards	read	List win-back cards
reply_get_reengagement_card	read	One card in full
reply_create_reengagement_card	write	Add a card (with send-after days)
reply_update_reengagement_card	write	Patch a card
reply_delete_reengagement_card	write	Remove a card

Jason AI SDR — offers

Tool	Type	Purpose
reply_list_offers	read	List offers (id + name)
reply_get_offer	read	Full offer content (ICP, value props, CTAs)
reply_create_offer	write	Create an offer
reply_update_offer	write	Patch an offer
reply_generate_offer_from_website	read	Draft offer fields from a website (doesn’t save)

Jason AI SDR — playbooks

Tool	Type	Purpose
reply_list_playbooks	read	List playbooks
reply_get_playbook	read	One playbook incl. instruction body
reply_create_playbook	write	Create a playbook
reply_update_playbook	write	Patch a playbook
reply_duplicate_playbook	write	Duplicate a playbook

Tasks

Tool	Type	Purpose
reply_list_my_tasks	read	List tasks, filterable
reply_create_task	write	Create a standalone task
reply_complete_task	write	Mark a task completed

Workspace resolvers & accounts

Tool	Type	Purpose
reply_list_email_accounts	read	Mailboxes with status and limits
reply_list_linkedin_accounts	read	Connected LinkedIn accounts
reply_list_schedules	read	Sending schedules
reply_search_lists	read	Resolve a list name to its ListId
reply_search_team_members	read	Resolve a teammate to their UserId

Help & meta

Tool	Type	Purpose
reply_search_knowledge_base	read	Search the Reply Help Center
reply_get_knowledge_base_article	read	Read a Help Center article
reply_get_app_map	read	App areas with in-app navigation
reply_report_unsupported_request	read	Log a missing capability for the product team

The full technical reference lives on docs.reply.io

This page is the high-level surface map. For implementation details:

• Connect — client configs, handshake, auth details, rate limits
• Tool contract & errors — schema rules, pagination, response envelopes, error codes, the safe-retry matrix
• Building agents — design principles, high-stakes gating, a drop-in system prompt
• Workflow recipes — launch a sequence safely, supervise Jason, reply to a thread, and more
• Tool reference — all 70 tools with per-argument documentation

The always-current runtime source is the server itself: call tools/list and trust what it returns.