MODEL CONTEXT PROTOCOL

Connect Claude. Ship from chat.

QuikRun's MCP server gives any MCP client a set of tools to write, run, test, and schedule snippets, then hand back a live URL without leaving your editor.

Start free

MCP is on the free tier.

What you get

MCP (Model Context Protocol) is an open standard that lets AI clients call external tools. QuikRun implements an MCP server so your agent can build and deploy real endpoints for you.

You describe the outcome in chat; the agent calls QuikRun tools to write the code, run its tests against fixtures, deploy it to the edge, and return the URL, all reviewable before it ships.

Add it to your client

One HTTP transport, every MCP client. Pick yours:

Claude
claude mcp add --transport http quikrun https://mcp.quik.run
Cursor
// .cursor/mcp.json
{
  "mcpServers": {
    "quikrun": { "url": "https://mcp.quik.run" }
  }
}
VS Code
code --add-mcp '{"name":"quikrun","url":"https://mcp.quik.run"}'
Windsurf
// ~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "quikrun": { "serverUrl": "https://mcp.quik.run" }
  }
}
Zed
// settings.json → context_servers
"quikrun": {
  "source": "custom",
  "url": "https://mcp.quik.run"
}

Ask your agent

Once QuikRun is connected, say things like:

›Create a cron that emails me yesterday's signups every morning at 8.
›Build a webhook that posts failed Stripe charges to #payments in Slack.
›Make a page that shows today's F1 standings and deploy it.
›Turn this Python script into an endpoint and run its tests.
›Add a weekday 9am schedule to my signup-digest snippet.
›Show me the last 10 runs of refund-alerts with timings.

Tools your agent gets

create_snippet
(prompt, language?) → { url, diff }

Writes and deploys a snippet from a description. Returns the live URL and the diff to review.

run_tests
(id) → { passed, cases }

Runs the snippet's tests against recorded fixtures and returns per-case results.

set_schedule
(id, schedule) → { ok, cron }

Turns a plain-language schedule into a cron and attaches it to the snippet.

get_logs
(id, limit?) → { runs }

Returns recent runs with timings, status codes, and captured output.

list_snippets
() → { snippets }

Lists your snippets with their URLs and current status.

get_snippet
(id) → { code, url, meta }

Fetches a snippet's source and metadata so the agent can edit it.

In practice

YOU

Create a cron that emails me yesterday's signups every morning at 8.

CLAUDE
▸ quikrun.create_snippet · signup-digest: ok · 0.9 s
▸ quikrun.set_schedule · "0 8 * * *": ok
▸ quikrun.run_tests · 3/3 PASSED

Done. signup-digest queries yesterday's signups and emails you a summary every morning at 08:00 UTC. It's live now:

quik.run/r/signup-digest

Give your agent a runtime.

Connect QuikRun's MCP server and ship from any chat. The first prompt is free.

Start freeRead the MCP docs