Integration

Runfra integration

Runfra (runfra.com) is an asynchronous batch image generation API: an agent submits one prompt (with several candidates scored and filtered, the best one picked as Top Pick) or a list of prompts (one image per prompt) on SDXL, FLUX Schnell or RunFra Pro (flux-dev), waits for the job and gets the image URLs, then can read the job, its candidates and its lineage, record a preferred candidate and read the public credit prices. Every image is billed in prepaid credits by model and resolution. Image-to-image jobs and the reference-image upload are left out because the vendor's reference contradicts itself on whether an API key may start them; account routes (credits, settings, API keys, billing), upscale, mockup, print export and Studio routes need a short-lived dashboard sign-in token and are not exposed; vision analysis, AI task routing, prompt expansion, quality-rubric and vision-review routes are absent from the public API reference and are not exposed either. Authentication is an API key (rfa_...) from Dashboard, API keys, sent in the X-API-Key header.

Connect Runfra How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Runfra.Built from the 7 Runfra tools below, on the connection you add once.

What you can do with Runfra

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Image candidate, 2 operations

list_job_candidatesList job candidatesGETAgents: ask firstLists every candidate image generated for a job, rejected ones included, with its URL, quality, ranking and aesthetic scores, pass flag, rejection reasons, seed and prompt.
select_job_candidateSelect job candidatePOSTAgents: ask firstRecords the user's preferred candidate for a finished job, by its 0-based index in the job's candidates. Answers 409 while the job is not finished or has no accepted candidate.

Image job, 2 operations

generate_imagesGenerate imagesPOSTAgents: ask firstStarts a BILLED image job: pass exactly one of prompt (batch_size candidates, Top Pick in best_result_url) or items (one image per prompt, in items[].result_url). Waits for the job and returns the finished result; gives up after 10 minutes.
get_jobGet jobGETAgents: ask firstReturns a job's full record: status, progress, selection_finalized, the Top Pick and preview URLs, accepted and failed counts, credits consumed and refunded, ETA, file retention state and per-item results.

Image job lineage, 1 operation

get_job_lineageGet job lineageGETAgents: ask firstReturns the job a job was derived from (Run Again, Tweak Settings or More Like This in the dashboard) and the jobs derived from it. Jobs created through the API are originals: source_job_id and parent are null.

Image job result, 1 operation

get_job_resultGet job resultGETAgents: ask firstReads a job's result: status (queued or running while in progress; succeeded, failed or cancelled at the end), best_result_url and result_urls (prompt jobs), items[].result_url (multi-prompt jobs), quality and timing.

Pricing, 1 operation

get_pricingGet pricingGETAgents: ask firstReturns Runfra's public prices: credit packs (price, credits, per-credit price), credits per image for each model and resolution, upscale costs, Studio packs and pricing notes. No account data.

Use Runfra from Claude Code, Cursor or Codex

Connect Runfra in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Runfra operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Runfra

Create your workspace
Sign up free. Nothing to install.
Connect Runfra once
Add your Runfra connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.