Sales Engagement API for AI Agents
Headless Jason AI SDR
The complete sales execution layer for AI agents, by Reply.io. Research prospects, send multichannel outreach, manage conversations, and turn replies into meetings — one platform, one account, one integration. Jason, unbundled into APIs.
The catalog
Every SDR capability, as a module
Research & Data
Find companies and people, manage contact records, enrich missing data.
Prospect Search API
Search Reply Data — 1B+ contacts and 60M+ companies — by ICP filters like job title, seniority, department, industry, and location, and turn the matches into a prospect list.
Contact Data API
The CRM-grade contact and account store — create, import, filter, and organize the people and companies your agent works.
Contact Enrichment API
Fill the gaps in a contact record — find missing emails and phone numbers, enrich by email or LinkedIn URL, and populate AI custom fields.
Email Validation API
Estimate and schedule email validation for contacts before sending — protect deliverability by never emailing dead addresses.
Outreach
Create multichannel sequences and send email and LinkedIn touches.
Sequence API
Create, populate, and control multichannel outreach sequences — email, LinkedIn, and calls in one campaign object.
Outreach Actions API
One-off sends outside a sequence — a single email, LinkedIn connection request, InMail, message, or voice message, on demand.
Tasks API
Create, assign, and complete manual touch tasks — calls, LinkedIn actions, and custom to-dos — for the humans and agents on your team.
Templates & Schedules API
Reusable email and sequence templates, variable rendering, sending schedules, and holiday calendars.
Conversations
Read replies, classify intent, respond, and detect meeting interest.
AI SDR Autopilot
Give Jason, the AI SDR, goals and knowledge — let it run outreach for you.
Automation
React to events with webhooks and orchestrate long-running jobs.
Analytics
Measure sends, opens, replies, meetings, and team performance.
Platform
Mailboxes, LinkedIn accounts, validation, suppression, and settings.
Mailbox Management API
Connect and manage sending mailboxes — Gmail/Office 365 OAuth, IMAP/SMTP tests, health, tags, and sending resume.
LinkedIn Accounts API
Connect LinkedIn accounts, manage daily action limits, and monitor connection status for LinkedIn outreach.
Suppression & Blacklist API
Do-not-contact rules by domain, email, and exception — compliance guardrails enforced platform-wide, with bulk operations.
Platform Utilities API
Attachments (including LinkedIn voice), and background-job tracking for bulk and import operations.
Settings & User API
Read and update workspace settings and identify the current API user — the "whoami" for scoped keys.
The outcome map
What AI agents can do with Reply
Reply.io is a sales-engagement platform an AI agent can operate end to end: find and manage contacts, launch multichannel outreach, triage and answer replies, pull performance data, and program Jason — Reply's AI SDR — as a supervised autopilot. Everything runs behind one scoped API key across four access layers.
| Outcome | Status | Where to start |
|---|---|---|
| Import and manage contacts, lists, accounts | ✅ Available | Create and import contacts |
| Launch multichannel sequences (email + LinkedIn) | ✅ Available | Launch outreach |
| Manage and optimize running sequences | ✅ Available | Manage sequences |
| Triage the inbox and send approved replies | ✅ Available | Process replies |
| Pull reports and per-sequence stats | ✅ Available | Analyze performance |
| Configure Jason AI SDR (knowledge, offers, playbooks, approvals) | ✅ Available | Build an AI SDR |
| Event-driven automation via webhooks | ✅ Available | Automate workflows |
| Validate emails, enforce blacklists, keep lists clean | ✅ Available | Automate workflows |
| Search the 1B+ B2B database for new prospects | Coming soon | Find prospects |
| Waterfall-enrich contacts (emails, phones, firmographics) | Coming soon | Find prospects |
Canonical version with guides, safety rules, and drop-in prompts: docs.reply.io/agents/overview.
Why build here
One integration instead of five vendors
- A prospect database (1B+ contacts), an email finder, a sequencer, a mailbox layer, an inbox, and meeting booking — normally five or six separate vendors, contracts, and auth systems. Here it is one API surface.
- One API key with scoped permissions (contacts:read, sequences:operate, …) covers every module.
- One usage meter is the goal: a unified credit system across data, enrichment, and outreach is proposed (Coming soon — see Pricing). Today usage runs on Reply subscriptions plus Live Data credits — still one vendor, one bill.
- Modules are designed to chain: the output of Prospect Search is the input of Contact Data; a Webhook event is the trigger for the Conversations API. Composition is the product.
Agent-grade by design
An API surface that speaks agent
This is not a human API with agents bolted on. The live MCP server was built for models calling tools — every design choice below is verified against the running server, not a promise.
- Self-describing safety: all 70 tools carry machine-readable annotations — readOnlyHint (31) or destructiveHint (39) — so an agent can auto-gate risky calls before its human ever has to.
- Fail-fast contracts: schemas reject unknown arguments (additionalProperties: false) and refuse empty strings or arrays for required fields. Mistakes surface at validation, not mid-outreach.
- Structured errors, not prose: every failure returns a stable ErrorCode plus a human message, and each tool documents its own failure modes — including what is safe to retry.
- Resolve-before-mutate by contract: mutations demand exact IDs from resolver tools; tool descriptions instruct models to never invent them. Batch calls return per-item results so agents report what actually happened.
- Uniform pagination on the MCP surface: top/skip in, Items + HasMore out — one loop pattern across all 70 tools.
Full verified reference — schemas, annotations, envelopes, error codes — on the MCP page.
The path in
From discovery to running outreach
- Discover capabilities — fetch /llms.txt or /catalog.json
- Choose APIs or a ready-made workflow
- Create an account (14-day free trial, no credit card)
- Get an API key from Settings → API Key
- Call the API — REST or MCP, same key
- Add credits when needed — upgrade link for your human
Full lifecycle with per-step availability — including the simulated self-serve demo — on Get started.
Ways in
Four integration surfaces, one platform
REST API
The full catalog at api.reply.io/v3 — scoped keys, OpenAPI, problem+json errors.
MCP server
Live at mcp.reply.io — 70 tools for Claude, Cursor, and any MCP client.
CLI
npm i -g reply-cli — contacts, sequences, inbox, and reports as shell commands with JSON output.
Agent skills
One installable skill teaching agents the core outreach workflows, executed via the CLI.
Which one fits
Choose your interface
MCP, Skills, CLI, and API are not separate products — they are four ways to access the same Reply.io platform. Same account, same API key, same object model, same rate limits.
| MCP | Skills | CLI | API | |
|---|---|---|---|---|
| Best for | Agents in MCP clients (Claude, Cursor) | Coding agents that need procedure, not just tools | Shell scripts, CI, coding agents | Production integrations, webhooks, bulk |
| Granularity | 70 curated tools | 4 multi-step workflows (v1) | ~17 command groups | Every endpoint |
| Install cost | One client config entry | CLI + one git clone | One npm install | None (HTTP) |
| Safety built in | readOnlyHint / destructiveHint annotations | Hard confirmation gates + dry-runs | --dry-run, --yes, TTY prompts | Scoped keys only |
| Coverage today | Day-to-day operations + Jason AI SDR | Core outreach loop | Core outreach loop (v0.2) | Full surface |
Decision rules
- Your agent runs in an MCP client (Claude, Cursor, Make, n8n) → use MCP. Richest interactive surface, and the only one with per-tool safety annotations the client can gate on automatically.
- Your agent has a shell (Claude Code, Codex, CI pipelines) → use the CLI, and add the Skill so it follows proven procedure — dry-runs, verification steps, and confirmation gates included.
- You're building a production integration — webhooks, bulk imports, background jobs, or anything not exposed as a tool or command → use the REST API.
- You want Jason (AI SDR) programmable — approval queues, knowledge bases, offers, playbooks → MCP has the richest Jason toolset today; the REST API covers the knowledge/offer/playbook layer.
The layers compose — skill drives CLI, MCP for interactive work, REST for bulk. Full version: docs.reply.io/agents/choose-your-interface.
Recipes
Combinations do jobs
Find and contact prospects
From an ICP definition to booked meetings — the complete outbound loop.
Follow up with inbound leads
React to every inbound lead in minutes — qualify, personalize, respond, schedule.
Build an autonomous AI SDR
Give Jason a goal, knowledge, and guardrails — then supervise instead of operate.
Keep lists clean and compliant
Continuous hygiene — validate addresses, suppress opt-outs, and prune dead records before they hurt deliverability.
A/B test messaging at scale
Run message variants against live traffic, kill the losers, and roll winners out as templates.
Run an account-based campaign
Target named accounts, multithread into each buying committee, and report by account — not by contact.
LinkedIn-first outreach
Lead with the warm channel — connection requests and voice notes first, email as the follow-through.
Re-engage dormant prospects
Mine the contacts you already paid for — refresh, requalify, and wake them with a light touch.
Honesty
Unlabeled means callable today
Everything documented on this site works now via the Reply.io API unless it carries one of two labels:
| Coming soon | Specified and designed, but not yet callable. Do not build against it yet. |
| Concept | Illustrative future direction. No specification exists yet. |
This is a product concept built on a real platform. Nothing future is presented as operational — see About for the rules.