# Reply API Documentation: 3.0

## 3.0

- [3.0 / API Reference (394 pages)](https://docs.reply.io/_llms/3-0/api-reference.md): Documentation for 3.0 / API Reference.

### Guides

#### Add contacts to pipeline

- [Find your ideal prospects](https://docs.reply.io/guides/find-ideal-prospects.md): From an ICP definition to a saved, deduplicated prospect list — what works today and what's coming.
- [Import and clean contacts](https://docs.reply.io/guides/import-contacts.md): CSV in, deduplicated contacts out — mapped, verified, and organized into a list ready for outreach.
- [Launch multichannel outreach](https://docs.reply.io/guides/launch-outreach.md): From a contact list to a running multichannel sequence — accounts checked, contacts enrolled, start confirmed.
- [Improve sequences every cycle](https://docs.reply.io/guides/improve-sequences.md): Operate running sequences — A/B variants, per-step stats, pausing losers, promoting winners.

#### Operate and scale

- [Convert replies into meetings](https://docs.reply.io/guides/convert-replies-to-meetings.md): Triage the inbox, surface interested prospects, and send approved replies — event-driven or conversational.
- [Decide what to scale or fix](https://docs.reply.io/guides/analyze-performance.md): Turn raw reporting data into decisions — what to scale, pause, or rewrite.
- [Build a supervised AI SDR](https://docs.reply.io/guides/build-an-ai-sdr.md): Give Jason a goal, knowledge, and guardrails — then supervise through approval gates instead of operating by hand.
- [Automate outbound end-to-end](https://docs.reply.io/guides/automate-outbound.md): Event-driven and scheduled automation — webhooks for real-time reactions, CLI + cron for recurring hygiene.

### MCP

#### Get started

- [Reply MCP overview](https://docs.reply.io/mcp/overview.md): The official, live Reply.io MCP server — 70 tools for sequences, contacts, inbox, tasks, and the Jason AI SDR autopilot.
- [Connect](https://docs.reply.io/mcp/connect.md): Connect Reply MCP to Claude, Cursor, or any MCP client in two steps: create a scoped API key, then point your client at mcp.reply.io.

#### For agents

- [Tool contract & errors](https://docs.reply.io/mcp/tool-contract.md): The rules every Reply MCP tool enforces — schemas, pagination, response envelopes, error codes, and retries.
- [Building agents](https://docs.reply.io/mcp/agent-guide.md): Design principles, high-stakes gating, and a drop-in system prompt for agents that use Reply MCP.
- [Workflow recipes](https://docs.reply.io/mcp/recipes.md): Concrete Reply MCP call graphs — resolve IDs, configure, confirm high-stakes steps, verify.
- [Tool reference](https://docs.reply.io/mcp/tools.md): The full catalog of all 70 Reply MCP tools, grouped by domain, with safety annotations.

### Skills

#### Get started

- [Reply Skills](https://docs.reply.io/skills/overview.md): Outbound expertise as markdown skills — three installable packs that teach your agent what to run, in what order, and with which guardrails.

#### Reference

- [Skill catalog](https://docs.reply.io/skills/catalog.md): All 18 Reply skills by pack — what each one does, when it triggers, its maturity, and the skills it builds on.

### CLI

#### Get started

- [Reply CLI](https://docs.reply.io/cli/overview.md): The Reply.io command line — sign in once, then run any v3 API call as yourself from your terminal, your scripts, or CI.

#### Reference

- [Using the CLI from agents & scripts](https://docs.reply.io/cli/agents.md): The reply CLI's machine contract — JSON output, exit codes, the two error shapes, retries, impersonation headers, and composition patterns.

## OpenAPI Specs

- [bundled](/api-reference/bundled.yaml)