Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
85
A2A live JSON-RPC A2A 0.2.1 vlaunchfiles_a2a_v1 x402 micropay

Launchfiles A2A

launchfiles.app · Launchfiles

Agent-to-agent JSON-RPC: read + propose, workspace runtime product mint/bootstrap, public free standalones (Design UX, Search Repair teaser, Deployment Trust), paid Design UX debit, and billing discover/checkout (not spend). Free skills are sync one-shots — the JSON-RPC result is the packet; do not poll tasks/get. Public discovery is not authority. Raw secrets rejected. No publish, deploy, or approve. A2A taskStore is in-process non-durable memory (not a durable task DB). Durable mission work lives in mission_sessions. Calling convention: JSON-RPC 2.0 over HTTP POST to /api/a2a. message/send needs params.skill (a skill id from this card) — a standard A2A Message without params.skill is rejected, so this is not a drop-in standard A2A Message client.

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain launchfiles.app via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership
🔔 Watch this agent. Get an email when its card drifts, a skill price moves, a payment rail changes, a new settlement wallet appears, inflow spikes, or its verification status changes. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
Trust score
50/100
grade D · 9 criteria
Uptime
not measured
no direct probes in 30d
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
changed
0 snapshots tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

D
Conformance score: 50/100
D-grade: significant issues, auth-gated, partially broken, or stale.
click to expand breakdown ▾ click to collapse breakdown ▴
pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
pass Live JSON-RPC 25/25
Endpoint responds to a negotiated A2A SendMessage probe.
partial Protocol version 5/10
Declares pre-1.0 A2A 0.2.1 (Google preview). Upgrade to v1.x for full points.
How to earn +5 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` (Major.Minor, no patch number — §3.6) to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.
Docs →
info JWS signature 0/10
Card is unsigned (most published agents are).
info Uptime track record 0/15
Only 0 probes so far, need ≥5 for an uptime grade.
fail Skill declaration 0/10
No skills declared in card. Hard to route to.
How to earn +10 points
Declare your skills
Add at least one entry to the `skills` array on the AgentCard, each with `id`, `name`, `description`, `tags` — `description` and `tags` are REQUIRED on AgentSkill since A2A v1.0, and tags are what discovery filters match on. We canonicalise these into the global skill taxonomy on next probe.
Docs →
partial Verified Identity 5/10
Provider declared: Launchfiles (https://launchfiles.app/). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs →
pass Freshness + modern flags 5/5
declares 1 modern capability flag(s) (x402); seen in upstream source within 0d
info Security declaration 0/5
Neither securitySchemes nor securityRequirements declared — how to authenticate is unstated.
⚠ Card drift detected. This agent's agent-card.json changed within the last 7 days. We track these so downstream callers can react.

Activity (audit trail)

last 24h · 0 invocations Public aggregate · no PII recorded

Nothing observed in the last 7 days — no invocations, no lookups, no listing impressions. Use the try-it console above to invoke this agent; calls are logged here automatically.

Uptime
not measured
0 direct probes · 30d
Response
—
no direct probe retained
Skills
30
declared
Streaming
—
SSE-capable

Try it

Send a message to this agent live. Your prompt is proxied through Agenstry.

calling agent…

Health · last 0 probes

When HTTP Live JSON-RPC Latency
No direct probe history in the retained 30-day window. Upstream catalogue observations do not count as uptime probes.

Similar agents embedding-nearest

A2A Trust Plane
Multi-agent continuity for small teams. Preserve interrupted work, revalidate authority, resume with another provider, prevent duplicate act
The 825 · q 78%
Agent Card Validator MCP
Pay-per-call MCP that audits + lints any x402/A2A service's discovery surfaces (agent-card.json, ai-plugin.json, openapi.yaml, mcp.json, age
agent-card-validator-mcp.mtree.workers.dev · q 73%
KushBitx AgentProof live
Public service discovery and integration guidance for AgentProof Base security APIs and SpendGuard spending policies. A2A messages provide d
KushBitx · q 100%
A2AWire Trust Layer live
The trust layer for autonomous agent-to-agent commerce: escrow-backed USDC settlement on Base L2, identity/reputation, and discovery. Expose
Z37 · q 87%
Agent Ready Kit live
Make any website agent-ready in minutes. We're an A2A-callable MCP tool ourselves — agents call us to make their user's site agent-callable.
Agent Ready Kit · q 100%
Tools for Agents
HTTP tool platform for AI agents: web extract, search, documents, GPU embeddings/OCR, RAG pipelines, tool chains, and Agent Advisor. 13 A2A
Tools for Agents · q 90%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime A2A protocol version
Markdown / HTML snippets
[![Agenstry grade](https://agenstry.com/badge/launchfiles.app.svg)](https://agenstry.com/agents/launchfiles.app)
[![Verified Business](https://agenstry.com/badge/launchfiles.app/identity.svg)](https://agenstry.com/agents/launchfiles.app)
[![Uptime](https://agenstry.com/badge/launchfiles.app/uptime.svg)](https://agenstry.com/agents/launchfiles.app)
[![A2A version](https://agenstry.com/badge/launchfiles.app/protocol.svg)](https://agenstry.com/agents/launchfiles.app)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "name": "Launchfiles A2A",
  "url": "https://launchfiles.app/api/a2a",
  "description": "Agent-to-agent JSON-RPC: read + propose, workspace runtime product mint/bootstrap, public free standalones (Design UX, Search Repair teaser, Deployment Trust), paid Design UX debit, and billing discover/checkout (not spend). Free skills are sync one-shots \u2014 the JSON-RPC result is the packet; do not poll tasks/get. Public discovery is not authority. Raw secrets rejected. No publish, deploy, or approve. A2A taskStore is in-process non-durable memory (not a durable task DB). Durable mission work lives in mission_sessions. Calling convention: JSON-RPC 2.0 over HTTP POST to /api/a2a. message/send needs params.skill (a skill id from this card) \u2014 a standard A2A Message without params.skill is rejected, so this is not a drop-in standard A2A Message client.",
  "version": "launchfiles_a2a_v1",
  "documentationUrl": "https://launchfiles.app/use-from-agent#connect",
  "iconUrl": "https://launchfiles.app/brand/launchfile-app-icon-512.png",
  "defaultInputModes": [
    "application/json",
    "text/plain"
  ],
  "defaultOutputModes": [
    "application/json"
  ],
  "skills": [
    {
      "id": "catalog",
      "name": "List connection tools",
      "description": "Discovery catalog for MCP/A2A clients.",
      "tags": [
        "discovery"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "workspaces.list",
      "name": "List workspaces",
      "description": "List workspaces this actor is a member of. Empty is honest. Auth required.",
      "tags": [
        "workspace",
        "read"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "workspaces.create",
      "name": "Create workspace",
      "description": "Create a workspace and grant the caller owner. Never seeds default. Auth required.",
      "tags": [
        "workspace",
        "write_metadata"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "workspaces.bind",
      "name": "Bind workspace",
      "description": "Bind this session to a workspace the actor can access. Auth required.",
      "tags": [
        "workspace",
        "bind"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "workspaces.unbind",
      "name": "Unbind workspace",
      "description": "Clear the in-process workspace bind for this session. Auth required.",
      "tags": [
        "workspace",
        "bind"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "session.get",
      "name": "Get agent session",
      "description": "Read identity, bound workspace, and entitled tools. Auth required.",
      "tags": [
        "workspace",
        "session",
        "read"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "connections.get",
      "name": "Get connection state",
      "description": "Read product connection readiness, handoff JSON, and surface catalog.",
      "tags": [
        "connections",
        "read"
      ],
      "examples": [
        "{\"productSlug\":\"citadel\"}"
      ],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "connections.save",
      "name": "Save connection metadata",
      "description": "Persist public locators and credential references for a surface (no raw secrets).",
      "tags": [
        "connections",
        "write_metadata"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "connections.scan",
      "name": "Run read-only social recon",
      "description": "Invoke configured n8n recon for enabled surfaces.",
      "tags": [
        "connections",
        "recon",
        "read"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "products.list",
      "name": "List products",
      "description": "List adapter and workspace-minted runtime products.",
      "tags": [
        "products",
        "case_b",
        "read"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "products.create",
      "name": "Mint runtime product",
      "description": "Create a workspace runtime product with empty connectors and restrictive claim ceiling. No publish.",
      "tags": [
        "products",
        "case_b",
        "write_metadata"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "products.completeness",
      "name": "Get product completeness",
      "description": "Read L0/L1 completeness and claim ceiling for a product.",
      "tags": [
        "products",
        "case_b",
        "read"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "products.bootstrap_truth",
      "name": "Run bootstrap product truth",
      "description": "Locked bootstrap_product_truth_v1 artifact (known/unknown/gaps). Requires L1. No public copy.",
      "tags": [
        "products",
        "case_b",
        "bootstrap"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "products.attach_adapter",
      "name": "Attach depth pack",
      "description": "Bind a registered depth pack onto a runtime product. Same slug. Founder intake wins. No remint.",
      "tags": [
        "products",
        "case_b",
        "attach",
        "write_metadata"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "propose.signal",
      "name": "Propose signal",
      "description": "Propose a signal object only \u2014 never executes. Returns proposal_id + receipt.",
      "tags": [
        "propose",
        "read_propose"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "propose.work_order",
      "name": "Propose work order",
      "description": "Propose a scoped work order \u2014 never starts execution without founder path.",
      "tags": [
        "propose",
        "read_propose"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "mission.status",
      "name": "Mission status (read)",
      "description": "Read mission/session status when authorized.",
      "tags": [
        "mission",
        "read"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "design_ux_radar.run_free",
      "name": "Design UX Radar free preview",
      "description": "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. Rate-limited. Mirrors /cro free path. Optional leave-behind fields (client_ref, brand_name, logo_url, primary_color, hide_lf_chrome) stay on the agent JSON. client_ref is echoed for the caller's own DB; Launchfiles does not list runs by client. hide_lf_chrome needs an authenticated lf_agent_ key or the response returns wl_entitlement needs_auth.",
      "tags": [
        "standalone",
        "free",
        "design_ux_radar",
        "public_standalone"
      ],
      "examples": [
        "{\"url\":\"https://example.com\",\"device\":\"mobile\"}"
      ],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "search_repair_radar.run_free",
      "name": "Search Repair Radar free teaser",
      "description": "Public free Search Repair teaser. Owned adapter GSC properties use the product bind (no access_token). Other sites need a GSC token or return needs_auth + connect URL. Preview only \u2014 never the $29/mo paid packet.",
      "tags": [
        "standalone",
        "free",
        "search_repair_radar",
        "public_standalone"
      ],
      "examples": [
        "{\"gsc_site_url\":\"sc-domain:example.com\",\"access_token\":\"<gsc_oauth_access_token>\"}"
      ],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "deployment_trust_radar.run_free",
      "name": "Deployment Trust Radar free packet",
      "description": "Public free Deployment Trust Radar packet (free-full demand probe; no paid tier). Requires url, use_case_plain, autonomy, data_sensitivity.",
      "tags": [
        "standalone",
        "free",
        "deployment_trust_radar",
        "public_standalone"
      ],
      "examples": [
        "{\"url\":\"https://example.com\",\"use_case_plain\":\"Draft support replies with human approval before send\",\"autonomy\":\"draft_with_approval\",\"data_sensitivity\":\"pii\"}"
      ],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "keyword_planner.research",
      "name": "Keyword Planner research",
      "description": "Read-only Google Ads Keyword Planner for one agnostic study. Requires registered or founder auth. $0 Ads. Params: study_id and seeds (string array). seed_keywords, keywords, and query are UNKNOWN_BODY_KEY. study_id without seeds is SEEDS_REQUIRED. sold_job_seeds require gap_scan_id or gap_scan (hunt_gap_scan_v1, ready_for_measure, or blocked category taken / wrong job keyword) or return GAP_SCAN_REQUIRED. Optional commodity_seeds stamp GO/HOLD/KILL. Volume GO plus an occupied shelf or a wrong job keyword is HOLD. Nothing is published or spent.",
      "tags": [
        "research",
        "keyword_planner",
        "read_only",
        "registered_agent"
      ],
      "examples": [
        "{\"study_id\":\"example_study\",\"seeds\":[\"example pricing calculator\"],\"sold_job_seeds\":[\"example pricing calculator\"],\"commodity_seeds\":[\"example service\"],\"gap_scan_id\":\"hgs_example\"}"
      ],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "hunt_gap_scan.run",
      "name": "Hunt gap scan",
      "description": "Gap-first hunt receipt. Requires registered or founder auth. competitor_urls (1\u20135 http(s) URLs), optional category_hint and pain_source_urls. Returns hunt_gap_scan_v1, including trends as a labeled skip (SOURCE_MISSING, google_trends_live). No series. Pain without a URL is rejected. A page that sells bill, quote, or scheduling is category taken, not an empty ready wedge. Chromium failure is PARTIAL. Does not invent MSV or a UX score. $0 Ads. Nothing is published.",
      "tags": [
        "research",
        "hunt_gap_scan",
        "read_only",
        "registered_agent"
      ],
      "examples": [
        "{\"competitor_urls\":[\"https://example.com/incumbent\"],\"category_hint\":\"quoting software\",\"pain_source_urls\":[\"https://example.com/review\"]}"
      ],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "design_ux_radar.run_paid",
      "name": "Design UX Radar paid full run",
      "description": "Paid standalone full run. Paid tier is not open to the public yet. Requires agent API key (lf_agent_) + credits when that tier is open. Debits ledger before intelligence. Never free unlock.",
      "tags": [
        "standalone",
        "paid",
        "design_ux_radar",
        "paid_agent"
      ],
      "examples": [
        "{\"url\":\"https://example.com\"}"
      ],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "billing.providers.list",
      "name": "List billing providers",
      "description": "Discover-only: list enabled checkout rails. Not spend.",
      "tags": [
        "billing",
        "discover"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "billing.checkout.create",
      "name": "Create billing checkout",
      "description": "Discover-only: return a checkout URL or x402 challenge. Not spend.",
      "tags": [
        "billing",
        "discover"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "billing.checkout.poll",
      "name": "Poll billing checkout",
      "description": "Discover-only: poll until settled. Returns key once and page_draft_long unlock_token. Not spend.",
      "tags": [
        "billing",
        "discover"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "page_draft.run_paid",
      "name": "Page Draft paid long",
      "description": "Paid Page Draft after settled page_draft_long checkout, or a founder-issued developer key (no Stripe). Pass unlock_token or an HMAC-verified developer key. length=short is allowed for a developer key. Nothing is published.",
      "tags": [
        "standalone",
        "paid",
        "page_draft",
        "paid_agent"
      ],
      "examples": [
        "{\"topic\":\"Why the first screen must say the job\",\"url\":\"https://example.com\"}"
      ],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "page_draft.run_short",
      "name": "Writer short draft",
      "description": "Writer-short draft (~400 words). A founder-issued developer key gets full product access \u2014 no Stripe Writer checkout. Same writer door as the web buyer. Nothing is published.",
      "tags": [
        "standalone",
        "paid",
        "page_draft",
        "writer_short",
        "paid_agent"
      ],
      "examples": [
        "{\"topic\":\"Three X drafts that name the job\",\"url\":\"https://launchfiles.app\"}"
      ],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "agent_key.request",
      "name": "Request agent API key",
      "description": "Email a one-time mint link to an allowlisted or approved-waitlist address. Returns poll_token. Other addresses are rejected. Optional partner_id must be allowlisted or the call returns UNKNOWN_PARTNER and sends no mail. No founder UI.",
      "tags": [
        "auth",
        "discover",
        "agent_key"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    },
    {
      "id": "agent_key.poll",
      "name": "Poll agent API key",
      "description": "After the mint link is opened, return lf_agent_ once to the requester. Second poll redacts the secret.",
      "tags": [
        "auth",
        "discover",
        "agent_key"
      ],
      "examples": [],
      "inputModes": [],
      "outputModes": []
    }
  ],
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": true,
    "extensions": null
  },
  "protocolVersion": "0.2.1",
  "provider": {
    "organization": "Launchfiles",
    "url": "https://launchfiles.app/"
  }
}