Skip to content
Launchfiles logo

Launchfiles MCP server

Which MCP servers are Launchfiles's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-27

← Back to Launchfiles

Whose server it is
  • Registry nameapp.launchfiles/launchfilesverified in the MCP registry

The registry name sits under launchfiles.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools13
  • Server calls itselflaunchfiles-agent
  • Server version0.2.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 107 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 9 of 13 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer150 ms
  • Space in an agent's context≈ 2,917 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsC · 72 of 100
  • Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 9 of 13
  • Not saying whether it only reads or can destroy: 13 of 13

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers13 tools · read 2026-10-27
  • launchfiles_standalone_design_ux_radar_free

    Public free Design UX Radar preview for one URL. Scores come from fixed rules; a small language model writes the next-step text. Paid tier is not open to the public yet. Does not edit or publish the site. Rate-limited. Optional partner…

  • launchfiles_standalone_search_repair_radar_free

    Public free Search Repair Radar teaser. Preview only — never unlocks the $29/mo paid repair packet. Owned product properties that already declare Search Console on their adapter use that bind (no access_token). Other sites need a Google…

  • launchfiles_standalone_deployment_trust_radar_free

    Public free Deployment Trust Radar packet (free-full demand probe; no paid tier). Requires deployment URL, use-case description, autonomy level, and data sensitivity. Rate-limited.

  • launchfiles_billing_list_providers

    List payment providers available for agent checkout (id, enabled, mode, rails). Discover-only; does not spend or mutate ledger.

  • launchfiles_billing_create_checkout

    Create provider-agnostic agent checkout. Returns payment_url and/or x402 challenge plus poll_url. Poll until paid to receive agent_api_key once. Does not debit credits or publish.

  • launchfiles_billing_poll_checkout

    Poll an agent checkout until settled. When paid, returns agent_api_key once and, for page_draft_long, an unlock_token. Does not spend.

  • launchfiles_request_agent_key

    Primary agentic mint. Emails a one-time approve link to an allowlisted or approved-waitlist address. Returns poll_token. Does not mint a key until the link is opened. Rejects other addresses. Optional partner_id mints an lf_agent_ key…

  • launchfiles_poll_agent_key

    Collect the lf_agent_ key once after the approve link is opened. Pending until then. Second poll redacts the secret.

  • launchfiles_standalone_page_draft_paid

    Paid Page Draft after a settled page_draft_long checkout, or a founder-issued developer key (no Stripe). Same writer door as the web buyer. Pass unlock_token from billing poll, or Authorization: Bearer with the developer key, plus a brief…

  • launchfiles_standalone_page_draft_short

    Writer-short draft (~400 words). A founder-issued developer key gets full product access — no Stripe Writer checkout. Same writer door as the web buyer. Send the developer key as Authorization: Bearer (hosted MCP also accepts x-api-key or…

  • get_vertical_redesign_spec

    Retrieves the autonomous vertical redesign specification, locked theme token pack, and pre-generation domain lock for a vertical SaaS product.

  • validate_copy_manifest

    Validates and sanitizes a copy manifest against GATE-10 (leaked engineering/db jargon ban), GATE-11 (AI slop and Unicode star ban), and GATE-12 (repetitive sentence ban).

  • run_ux_radar_proof

    Runs the 15-gate Blueprint UX Radar verification, self-healing routing analysis, and generates a 4-part Launchfiles Proof Packet for a target URL or vertical workbench.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "launchfiles": {
      "type": "http",
      "url": "https://launchfiles.app/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http launchfiles https://launchfiles.app/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://launchfiles.app/api/mcp as a custom connector in the settings.

OpenAPI spec

13 paths, read 2026-10-27. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.