Discover a capability or a raw endpoint, inspect its price, run it. Every page here is also plain markdown for agents. To see what the calls are for first, start with the tools or a ready-made workflow.
Get a key in a minute. Sign up on the dashboard (password, Google, GitHub or an emailed code), verify your email, and your workspace gets $1 of credit that runs real calls. Mint an rg_live_ key under API keys, or skip keys entirely and connect over MCP with OAuth.
One key, one wallet, and the discover, inspect, run loop behind every call.
A first REST call in five minutes: signup, inspect, run, wallet.
The plain-text CLI that mirrors the API one-to-one, built for agents.
Add lead enrichment, SEO, social and outbound tools to Claude Code, Codex, Cursor or any agent with one SKILL.md (Agent Skills) instead of writing API wrappers: discover, inspect and run, with the spending rules built in.
Connect the RouterGrowth MCP server to Claude Code, claude.ai, ChatGPT, Cursor, VS Code or your own agent on the Claude or OpenAI API: SERP, backlink and keyword data, B2B contact and company enrichment, social scraping and outbound as native tools on one balance.
The RouterGrowth connector in the Claude Connectors Directory: company, contact, SEO, AI visibility and social research plus outreach from your own accounts in claude.ai, one tool per operation, with costs, examples and troubleshooting.
Use employer domains, title filters and current-role evidence to build a better people list, then find emails only for the profiles you need.
Connect WhatsApp or Gmail, send messages and email, read replies, and manage connected accounts.
Base URL, authentication, environments, the error envelope and idempotency.
POST /v1/discover: search capabilities and raw endpoints by job description. Free, never runs a paid call.
POST /v1/inspect: a capability's schema, providers and exact price, or a raw endpoint's contract and cost model.
POST /v1/run: execute a capability with routing and failover, or a raw endpoint under max_cost.
Provider + endpoint addressing for the long tail: the provider's own request and payload, settled on the provider's measured cost after the run.
GET /v1/runs: list, fetch and cancel runs; every attempt and charge on record.
POST /v1/watch: save a query, refresh it weekly and get back only the new and changed records.
Replies, bounces, LinkedIn messages and dropped sessions as signed webhooks, or as one stream on GET /v1/events.
Workspace tables: lists every agent shares between sessions, merged by identity, with a suppression list and a repeat-send guard on every send, and enrichments saved into rows never bought twice.
Balance, transactions, top-ups, auto top-up and referrals on one prepaid wallet.
Mint, list and revoke keys. Keys are hashed at rest and shown once.
Stable error codes, HTTP statuses, the error envelope and retry guidance.
POST /feedback: your agent reports a missing capability, a bug or a misleading doc from the call site, free and without a key, on the open Agent Feedback Protocol.
The install-once interface file: MCP tools, CLI and HTTP contract, spending rules, and which workflow skill to load. Tell your agent to set it up.
Open-source GTM jobs an agent runs end to end: hiring-signal outbound, cold email, LinkedIn, AI visibility audits and more, with a human gate before anything sends.
Index of every docs page as markdown: append .md to any docs URL for the raw page, no scraping needed.
The interactive OpenAPI reference ships with the hosted API at /api-reference. Questions: hello@routergrowth.com.