Agents onboard themselves here.

# 1. sign yourself up (no browser, no email loop)
curl -X POST https://3bi.ai/api/public/v1/signup \
  -H "content-type: application/json" \
  -d '{"label":"my-agent"}'

# 2. discover
curl https://3bi.ai/api/public/v1/tools

# 3. call a live tool (read-only tools need no confirmation)
curl -X POST https://3bi.ai/api/public/v1/tools/fetch_url \
  -H "Authorization: Bearer $RELAY_KEY" \
  -H "content-type: application/json" \
  -d '{"url":"https://example.com"}'

How it works

1. Step 1

   Sign yourself up

   One unauthenticated POST returns a bearer key and 500 free credits. No browser, no email loop.

   POST /api/public/v1/signup
2. Step 2

   Discover the catalog

   Typed JSON Schema arguments and results, published as OpenAPI 3.1, an agent manifest and MCP.

   GET /api/public/v1/tools
3. Step 3

   Call and get metered

   Successful calls debit credits. Side-effecting tools return 428 with a preview until a human-approved token is presented.

   POST /api/public/v1/tools/{name}

Built for callers with no hands

Starter tool catalog

Prices are per successful call. Side-effecting tools are marked and gated. Live tools do real work and cost credits; every sandbox_* tool is free and returns fixture data, so agents can rehearse the full flow before spending anything.

• fetch_url

  Fetch a public web page or JSON endpoint over HTTPS and return its readable text content plus metadata. Real network call, not a simulation. Read-only.

  2 cr

• crawl_site

  Crawl a public site starting from one https:// URL and return readable text for that page plus up to nine same-origin pages it links to. Real network calls. Read-only.

  6 cr

• extract_structured

  Extract named fields as JSON from a public URL or supplied text, using a server-side model. Returns one value per requested field, or null when absent. Read-only.

  8 cr

• search_web

  Search the public web and return ranked results with titles, snippets, and source URLs. Uses a server-side search API. Read-only.

  4 cr

• search_knowledge_base

  Search this workspace's uploaded documents using semantic similarity. Returns the most relevant text chunks with document titles and source URLs. Read-only.

  3 cr

• execute_codeconfirm

  Run Python or JavaScript code in a sandboxed E2B environment and return stdout, stderr, and the exit code. Files are ephemeral, but code can make external network requests with side effects. Requires the configured side-effect confirmation flow.

  8 cr

• browse_page

  Open a URL in a remote Browserbase browser and return the rendered page as markdown text, including title, status code, and content type. Runs in Browserbase's cloud so it works from serverless runtimes.

  10 cr

• sandbox_search_knowledge_base

  Sandbox: searches a fixed set of fixture documents and returns simulated matches. Free — use it to exercise the API, not for real knowledge.

  0 cr

• sandbox_lookup_crm_contact

  Sandbox: returns a fixture CRM contact by email. Free — no real CRM is queried.

  0 cr

• sandbox_list_records

  Sandbox: lists fixture records (contacts, invoices, tickets) with paging and filtering. Free — no real data.

  0 cr

• sandbox_send_emailconfirm

  Sandbox: simulates sending an email and returns a fake message id. Nothing is delivered. Free, and still side-effecting so you can exercise the confirmation flow.

  0 cr

• sandbox_update_crm_recordconfirm

  Sandbox: simulates updating a CRM record. Nothing is written. Free, and still side-effecting so you can exercise the confirmation flow.

  0 cr

• sandbox_create_paymentconfirm

  Sandbox: simulates creating a payment charge. No money moves. Free, and still side-effecting so you can exercise the confirmation flow.

  0 cr

• sandbox_delete_recordconfirm

  Sandbox: simulates deleting a record. Nothing is deleted. Free, and still side-effecting so you can exercise the confirmation flow.

  0 cr

• gmail_sendconfirm

  Send an email through the workspace's connected Google account. Uses the managed OAuth connection — the agent never sees credentials. Requires the workspace to connect Google first (POST /api/public/v1/oauth/google/authorize). Side-effecting: requires confirmation.

  6 cr

• slack_post_messageconfirm

  Post a message to a Slack channel as the workspace's connected Slack identity. Uses the managed OAuth connection — the agent never sees credentials. Requires the workspace to connect Slack first (POST /api/public/v1/oauth/slack/authorize). Side-effecting: requires confirmation.

  4 cr

• github_create_issueconfirm

  Create an issue in a GitHub repository as the workspace's connected GitHub identity. Uses the managed OAuth connection — the agent never sees credentials. Requires the workspace to connect GitHub first (POST /api/public/v1/oauth/github/authorize). Side-effecting: requires confirmation.

  4 cr