Integration

VC Deal Flow Signal integration

VC Deal Flow Signal (GitDealFlow) tracks public GitHub engineering activity (commit velocity, contributor growth, new repositories) across hundreds of startups to surface the ones accelerating before they raise. An agent can read the current period's trending startups and sector rankings, look up one startup's signal, get a cited diligence dossier (acquisitions, backing funds), score a GitHub user's early-starring record, read prediction markets, and search or question the vendor's Q&A corpus, FAQ, methodology and glossary. The paid deep-signal routes (credit-pack key, x402 and Solana payments) and their credit check, the CSV, NDJSON, citation-text and SVG badge downloads, the experimental scout prediction, the bulk Q&A dump, the pricing table, the vendor's own agent catalogs and marketing data, and the versioned aliases of the same files are not exposed. No authentication: the free routes are rate-limited per IP (60 requests per minute by default).

Connect VC Deal Flow Signal How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in VC Deal Flow Signal.Built from the 12 VC Deal Flow Signal tools below, on the connection you add once.

What you can do with VC Deal Flow Signal

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.

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

Answer, 2 operations

get_answerGet answerGETAnswers a question about startup deal flow and engineering signals with the single best match from the vendor's Q&A corpus: the answer text, citations and a canonical URL. See _meta.confidence. Use search_answers for ranked candidates.
search_answersSearch answersGETReturns ranked candidate answers to a question from the vendor's Q&A corpus (agent queries and FAQs), each with its confidence; results is empty when nothing matches. For one best answer use get_answer.

Signal, 2 operations

get_signalsGet signalsGETReturns the current period's full startup signal snapshot: top-20 trending startups and per-sector rankings (commit velocity, contributor growth, signal type). Large answer; for one company use get_startup_signal.
get_startup_signalGet startup signalGETLooks up one startup's engineering signal by name or GitHub org (case-insensitive fuzzy match). Read status: no_data means the company is not tracked (see cta). 30 requests per minute per IP.

Content, 1 operation

search_contentSearch contentGETSearches the vendor's site content (startups, sectors, blog posts, comparisons, answers, FAQs, research findings) by keyword overlap and returns ranked URLs with snippets. Filter with type.

Diligence dossier, 1 operation

get_diligence_dossierGet diligence dossierGETReturns a cited public-source diligence dossier for a company: who acquired it, acquisitions it made, funds that publicly backed it, and its published signal. dossier.found false (HTTP 404) when outside the tracked corpus.

Faq, 1 operation

list_faqList faqGETReturns the vendor's curated FAQ corpus on startup deal flow, engineering signals and its methodology (mainEntity: question and accepted answer pairs with stable URLs, safe to cite).

Glossary, 1 operation

list_glossary_termsList glossary termsGETReturns the vendor's glossary (schema.org DefinedTermSet) of the terms used across signals, sectors and methodology (commit velocity, signal types, funding stages and more), each with a definition.

Market, 1 operation

get_marketGet marketGETReturns an open prediction market by slug: the question, resolver, source of truth and ranked candidate startups with their signal data and implied probability. An unknown slug answers 404 with the list of available slugs.

Methodology, 1 operation

get_methodologyGet methodologyGETReturns how the signals are computed: the 6-step pipeline (collect, filter, normalise, accelerate, classify, rank) as a schema.org HowTo, with links to the published paper.

Period, 1 operation

list_periodsList periodsGETLists the data periods (quarters) with the number of active sectors and tracked startups in each, the current period, and the download formats of the dataset. Use it to find a period slug.

Scout score, 1 operation

get_scout_scoreGet scout scoreGETComputes the Scout Score (0 to 100) of a GitHub user: how many validated unicorns they starred before the funding, $1B or acquisition event. 10 requests per minute per IP.

Use VC Deal Flow Signal from Claude Code, Cursor or Codex

Connect VC Deal Flow Signal in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its VC Deal Flow Signal 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 VC Deal Flow Signal

Create your workspace
Sign up free. Nothing to install.
Connect VC Deal Flow Signal once
VC Deal Flow Signal needs no credential, so its tools work immediately.
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.