# Headless Jason AI SDR — Sales Engagement API for AI Agents

> 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.

Headless Jason AI SDR is Reply.io's sales engagement platform packaged as an API for AI agents. It is not an app with a UI to automate — it is the API-first infrastructure an agent calls directly: search a 1B+ contact B2B database, manage contact data, run multichannel sequences (email + LinkedIn + calls), read and classify replies, flag meeting intent, and measure results including meetings booked (booking itself happens via Reply's in-app scheduler — there is no book-a-meeting endpoint today). Available integration surfaces: REST API, a live MCP server, the reply CLI (npm i -g reply-cli), and installable agent skills (github.com/reply-team/reply-skills). Sign up at https://run.reply.io/register (14-day free trial, no credit card required).

## 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](https://docs.reply.io/api-reference/introduction) |
| Launch multichannel sequences (email + LinkedIn) | ✅ Available | [Launch outreach](https://docs.reply.io/api-reference/introduction) |
| Manage and optimize running sequences | ✅ Available | [Manage sequences](https://docs.reply.io/api-reference/introduction) |
| Triage the inbox and send approved replies | ✅ Available | [Process replies](https://docs.reply.io/api-reference/introduction) |
| Pull reports and per-sequence stats | ✅ Available | [Analyze performance](https://docs.reply.io/api-reference/introduction) |
| Configure Jason AI SDR (knowledge, offers, playbooks, approvals) | ✅ Available | [Build an AI SDR](https://docs.reply.io/api-reference/introduction) |
| Event-driven automation via webhooks | ✅ Available | [Automate workflows](https://docs.reply.io/api-reference/introduction) |
| Validate emails, enforce blacklists, keep lists clean | ✅ Available | [Automate workflows](https://docs.reply.io/api-reference/introduction) |
| Search the 1B+ B2B database for new prospects | ✅ Available | [Prospect Search API](https://agents.reply.io/apis/prospect-search.md) |
| Waterfall-enrich contacts (emails, phones, firmographics) | 🔜 Coming soon | [Contact Enrichment API](https://agents.reply.io/apis/contact-enrichment.md) |

Canonical version (guides, safety rules, drop-in prompts): https://docs.reply.io/api-reference/introduction

## 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.

## 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: every tool carries machine-readable annotations — readOnlyHint or destructiveHint — 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 the whole toolset.

Full verified reference: https://agents.reply.io/mcp.md

## The path in

1. Discover capabilities — fetch /llms.txt or /catalog.json
2. Choose APIs or a ready-made workflow
3. Create an account (14-day free trial, no credit card)
4. Get an API key from Settings → API Key
5. Call the API — REST or MCP, same key
6. Add credits when needed — upgrade link for your human

## API modules

- [Prospect Search API](https://agents.reply.io/apis/prospect-search.md) — Search Reply Data — 1B+ contacts and 60M+ companies — by ICP filters like job title, seniority, department, industry, and location, and add the matches straight into your prospect lists or a sequence.
- [Contact Data API](https://agents.reply.io/apis/contact-data.md) — The CRM-grade contact and account store — create, import, filter, and organize the people and companies your agent works.
- [Contact Enrichment API](https://agents.reply.io/apis/contact-enrichment.md) — Fill the gaps in a contact record — find missing emails and phone numbers, enrich by email or LinkedIn URL, and populate AI custom fields. (Coming soon — targeted late August 2026)
- [Sequence API](https://agents.reply.io/apis/sequences.md) — Create, populate, and control multichannel outreach sequences — email, LinkedIn, and calls in one campaign object.
- [Outreach Actions API](https://agents.reply.io/apis/outreach-actions.md) — One-off sends outside a sequence — a single email, LinkedIn connection request, InMail, message, or voice message, on demand.
- [Conversations & Inbox API](https://agents.reply.io/apis/conversations-inbox.md) — The unified inbox as an API — read threads across email and LinkedIn, classify replies with categories, detect meeting intent, and respond. (Generating an AI draft reply is callable today, in beta; only feedback on a generated draft is still coming soon.)
- [AI SDR API (Jason)](https://agents.reply.io/apis/ai-sdr.md) — Program Jason, Reply's autonomous AI SDR — knowledge bases, offers, playbooks, autopilot sequences, and the approval queue are all callable today. (The whole Jason surface is callable today — knowledge bases, offers, playbooks, AI SDR sequences, autopilot, and the approval queue — most of it in beta. Feedback endpoints, per-contact AI insights, and AI web search are still coming soon, targeted late August 2026.)
- [Webhooks & Events API](https://agents.reply.io/apis/webhooks-events.md) — Outbound event subscriptions — Reply pushes every reply, open, click, bounce, and LinkedIn event to your endpoint instead of making you poll.
- [Analytics API](https://agents.reply.io/apis/analytics.md) — Outcome data for optimizing agents — email, LinkedIn, call, and task overviews, activity feeds, team performance, channel efficiency, and the meetings list.
- [Email Validation API](https://docs.reply.io/api-reference/email-validations/schedule-email-validation) — Estimate and schedule email validation for contacts before sending — protect deliverability by never emailing dead addresses.
- [Tasks API](https://docs.reply.io/api-reference/tasks/create-a-task) — 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](https://docs.reply.io/api-reference/email-templates/create-an-email-template) — Reusable email and sequence templates, variable rendering, sending schedules, and holiday calendars.
- [Mailbox Management API](https://docs.reply.io/api-reference/email-accounts/connect-gmail-account-via-oauth) — Connect and manage sending mailboxes — Gmail/Office 365 OAuth, IMAP/SMTP tests, health, tags, and sending resume.
- [LinkedIn Accounts API](https://docs.reply.io/api-reference/linkedin-accounts/create-a-connection-link) — Connect LinkedIn accounts, manage daily action limits, and monitor connection status for LinkedIn outreach.
- [Suppression & Blacklist API](https://docs.reply.io/api-reference/contact-blacklist-rules/create-a-domain-blacklist-rule) — Do-not-contact rules by domain, email, and exception — compliance guardrails enforced platform-wide, with bulk operations.
- [Platform Utilities API](https://docs.reply.io/api-reference/background-jobs/get-a-background-job) — Attachments (including LinkedIn voice), and background-job tracking for bulk and import operations.
- [Settings & User API](https://docs.reply.io/api-reference/user-account/get-current-user) — Read and update workspace settings and identify the current API user — the "whoami" for scoped keys.

## Workflows

- [Find and contact prospects](https://agents.reply.io/workflows/find-and-contact-prospects.md) — From an ICP definition to booked meetings — the complete outbound loop. (1 of 9 steps coming soon — the rest is callable today)
- [Follow up with inbound leads](https://agents.reply.io/workflows/inbound-lead-follow-up.md) — React to every inbound lead in minutes — qualify, personalize, respond, schedule. (1 of 8 steps coming soon — the rest is callable today)
- [Build an autonomous AI SDR](https://agents.reply.io/workflows/autonomous-ai-sdr.md) — Give Jason a goal, knowledge, and guardrails — then supervise instead of operate. (runnable today — all 8 steps are callable now)
- [Keep lists clean and compliant](https://agents.reply.io/workflows/list-hygiene.md) — Continuous hygiene — validate addresses, suppress opt-outs, and prune dead records before they hurt deliverability. (runnable today — all 5 steps are callable now)
- [A/B test messaging at scale](https://agents.reply.io/workflows/ab-test-messaging.md) — Run message variants against live traffic, kill the losers, and roll winners out as templates. (runnable today — all 6 steps are callable now)
- [Run an account-based campaign](https://agents.reply.io/workflows/abm-campaign.md) — Target named accounts, multithread into each buying committee, and report by account — not by contact. (1 of 6 steps coming soon — the rest is callable today)
- [LinkedIn-first outreach](https://agents.reply.io/workflows/linkedin-first-outreach.md) — Lead with the warm channel — connection requests and voice notes first, email as the follow-through. (runnable today — all 5 steps are callable now)
- [Re-engage dormant prospects](https://agents.reply.io/workflows/reengage-dormant.md) — Mine the contacts you already paid for — refresh, requalify, and wake them with a light touch. (1 of 6 steps coming soon — the rest is callable today)

## Integration surfaces

- [REST API](https://docs.reply.io/api-reference/introduction) — live at https://api.reply.io/v3
- [MCP server](https://agents.reply.io/mcp.md) — live at https://mcp.reply.io/ (full reference at https://agents.reply.io/mcp/tools.md)
- [CLI](https://agents.reply.io/cli.md) — npm i -g reply-cli (auth, profiles and teams; `reply api` reaches the full v3 API; `reply skills` installs the agent skills; no dedicated sequence/contact/inbox commands yet)
- [Agent skills](https://agents.reply.io/skills.md) — 18 skills in three packs from github.com/reply-team/reply-skills, installed with `reply skills install` (vendor-neutral SDR expertise, the Reply execution adapter, a durable-work runtime)

## 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** | Curated tools | 18 skills in 3 installable packs | 6 command groups | Every endpoint |
| **Install cost** | One client config entry | One npm install, then `reply skills install` | One npm install | None (HTTP) |
| **Safety built in** | readOnlyHint / destructiveHint annotations | Hard confirmation gates + dry-runs | Confirmation prompts and `--dry-run` where a command changes state; `reply api` writes are live as issued | Scoped keys only |
| **Coverage today** | Day-to-day operations + Jason AI SDR | Planning, audience, launch, inbox, analysis, guardrails | Full v3 surface through `reply api` | 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 run `reply skills install` 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.

Full version (composition patterns, consistency guarantees): https://docs.reply.io/api-reference/introduction

## Availability labels

Everything documented on this site is callable today unless labeled **Coming soon** (specified, not yet callable — do not build against it) or **Concept** (future direction, no spec). Content last verified 2026-07-30.