AI agents and MCP

Camplax is built for agents, not just people. An agent that can create a project in one call does not need a Vercel account and a Supabase account — it needs one endpoint: the Camplax MCP server.

https://camplax.dev/mcp        (also mounted at /v1/mcp)

It speaks stateless streamable HTTP — one JSON-RPC 2.0 message per POST — and accepts MCP protocol 2025-06-18 or 2025-03-26. Run camplax mcp to print the setup for your client, or wire most clients in one line:

npx add-mcp https://camplax.dev/mcp

add-mcp writes the config entry for Claude Code, Cursor, Codex, VS Code and the rest. Clients that know OAuth will sign you in through the browser; for token auth add --header "Authorization: Bearer $CAMPLAX_TOKEN".

Two ways to authenticate

Which path you use depends on who is driving:

Path	Credential	For
Bearer token	cx_cli_… from camplax login, or a cx_live_… project key	coding agents, CI, anything non-interactive
OAuth 2.1 + PKCE	cxm_… access token minted by a browser consent flow	chat clients — Claude Desktop, ChatGPT, remote connectors

Bearer — coding agents

camplax login opens a browser once and writes a cx_cli_… token into the CLI config; in CI set CAMPLAX_TOKEN directly. No browser or CLI on the machine? Mint the same token in the console — Account → Access tokens → New token — which calls POST /v1/cli/tokens under a console session; the secret is shown once. Then point the agent at the endpoint with the token as a header:

# Claude Code
claude mcp add --transport http camplax https://camplax.dev/mcp \
  --header "Authorization: Bearer $CAMPLAX_TOKEN"

// Cursor — .cursor/mcp.json
{
  "mcpServers": {
    "camplax": {
      "url": "https://camplax.dev/mcp",
      "headers": { "Authorization": "Bearer ${env:CAMPLAX_TOKEN}" }
    }
  }
}

A project API key also works as the bearer, scoped to one project: it can deploy and read that project — deploy needs the deploy scope — but it cannot create_project, import_project or probe_project. Those need a user credential.

Codex auto-discovers .agents/skills/camplax/SKILL.md; the same skill is published by the MCP endpoint as a resource.

OAuth — chat clients

Chat clients sign in with your Camplax account instead of a pasted token. Add https://camplax.dev/mcp as a connector; the client discovers the OAuth server, opens a browser, you approve access, and it holds an cxm_… token. Same endpoint, same tools.

Discovery documents live at:

https://camplax.dev/.well-known/oauth-authorization-server
https://camplax.dev/.well-known/oauth-authorization-server/mcp
https://camplax.dev/.well-known/oauth-protected-resource
https://camplax.dev/.well-known/oauth-protected-resource/mcp
https://camplax.dev/.well-known/mcp.json

The flow, if your client does not automate it:

1. Register (RFC 7591): POST /oauth/register with redirect_uris, optional client_name, grant_types, scope. Only authorization_code/refresh_token, response type code, auth method none, scope mcp are accepted; redirect_uris must be https:// or a loopback http://localhost. Response 201 carries client_id — there is no client secret. Registration is also optional in the other direction: a client_id may simply be an https:// URL hosting a Client ID Metadata Document — the server fetches it (one bounded request, cached briefly), requires the document's client_id to equal the URL, and treats its redirect_uris as the allowlist. Discovery advertises client_id_metadata_document_supported; a pre-registered client always wins over a URL-shaped one.
2. Authorize: GET /oauth/authorize?client_id=…&redirect_uri=…&response_type=code&code_challenge=…&code_challenge_method=S256&scope=mcp — S256 is the only PKCE method. Signed-out users are bounced through console sign-in first; then a consent page names the client and the redirect origin. Approving redirects back with a code.
3. Token: POST /oauth/token (JSON or form) with grant_type=authorization_code, code, client_id, code_verifier, redirect_uri. Response: access_token (cxm_…), refresh_token (cxr_…), token_type: "Bearer", expires_in, scope.

The lifetimes and rules that matter:

Item	Value
Authorization code TTL	10 minutes, single use
Access token TTL	1 hour
Refresh token TTL	30 days
Refresh rotation	every use mints a new pair; replaying an old refresh token revokes the grant
Scope	mcp only — one scope, the whole surface

Token responses are Cache-Control: no-store. The unauthenticated /mcp request returns 401 with a WWW-Authenticate pointer to the protected-resource document, which is how clients find all of this on their own.

Scope the connection to one project

Two query params turn the shared endpoint into a per-project connector — the same pattern Supabase uses for its scoped MCP:

https://camplax.dev/mcp?project=my-app
https://camplax.dev/mcp?project=my-app&read_only=1

• project=<slug> binds the connection. list_projects returns only that project, every tool that takes slug defaults to it, and any other slug is rejected with a project_scope error. The slug must resolve to a project the credential can already see — anything else is a flat 404, so the parameter cannot probe for project names.
• read_only makes the connection a viewer — presence turns it on; only an explicit read_only=0 (or false/no/off) turns it back off. Every tool not annotated read-only — create_project, import_project, deploy, probe_project — fails with a read_only error. The tools are not merely hidden; the calls fail closed.

Use it when an agent only ever works on one app, or when a third-party agent should see but never touch: a bound, read-only connector cannot reach your other projects and cannot change this one.

The tools

Eight verbs cover context, shipping, migration and live verification. The catalog stays small on purpose — agents burn tokens on a 40-tool catalog and then call the wrong one.

Tool	Arguments	What it does
whoami	—	Which identity is connected: session, CLI token, OAuth token or API key, and its scopes
list_projects	—	The projects this identity can see
project_context	slug	Repo, build config, release evidence, permissions, secret names — never values
create_project	name, slug, optional templateId	Provision a new app; starts in provisioning
import_project	name, slug, optional siteUrl, sourceDatabaseUrl, githubRepo	Migrate a Vercel + Supabase app; the old site stays up
deploy	slug, optional branch, sourceKey	Queue a production deploy; sourceKey (from PUT /v1/projects/:slug/source) ships an uploaded folder instead of a repo. Poll project_status
project_status	slug	Provisioning, migration or deploy progress
probe_project	slug, optional only	Bounded live checks per feature — pass, fail or skip

A ready deploy is production evidence only when project_context.release.live is true — queued, building and deploying mean work in progress, not deployed.

No repo connected? project_context.nextAction will say so. Two ways to ship anyway: the owner connects GitHub once, or the agent deploys the local folder directly — run camplax deploy --local from the project directory (it packs, uploads and queues in one step), or do it by hand: PUT /v1/projects/:slug/source with a gzipped tar body, then deploy with the returned sourceKey.

Rate limits

Two buckets gate the endpoint, both 120 requests per minute: one per client IP (before auth, so forged bearers are cheap to refuse) and one per identity after it. OAuth endpoints have their own — 20 client registrations per IP per hour, 60 token calls per IP per minute. A 429 carries Retry-After.

What agents cannot do

Deliberately absent from the MCP: billing, creating API keys, deleting projects, and reading secret values. project_context returns secret names and presence only. There is no workaround, and that is the point — an agent can ship and verify an app without ever holding a secret or spending money.

Reading the docs

• /llms.txt — the short agent briefing.
• /llms-full.txt — every docs page in one file.
• Every docs page has a markdown mirror: /docs/getting-started.md for /docs/getting-started.html, and so on.

When MCP is unavailable, the same verbs exist on the CLI with --json — camplax deploy --json, camplax import --name <slug> --site <url> --db <postgres-url> --json, camplax probe --json. Never scrape the console HTML.