# GitDealFlow MCP server

Track startup engineering acceleration from public GitHub data before funding rounds

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-kindrat86-gitdealflow
- Website: https://gitdealflow.com

## Install
- Endpoint: https://gitdealflow.com/api/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://gitdealflow.com/api/mcp

## Tools
- get_trending_startups (Trending Startups) - Top 20 startups by engineering acceleration across all 20 sectors for the current weekly period. Read-only, idempotent. Endpoint: https://gitdealflow.com/api/mcp
- search_startups_by_sector (Search Startups by Sector) - Every tracked startup within a sector, ranked by engineering acceleration. Sector slug must be one of 20 enumerated values. Endpoint: https://gitdealflow.com/api/mcp
- get_startup_signal (Get Startup Signal) - Full engineering-acceleration profile for a single tracked startup, by display name or GitHub org slug. Case-insensitive, normalization-tolerant. Endpoint: https://gitdealflow.com/api/mcp
- get_signals_summary (Dataset Summary) - Period, sector and startup counts, last refresh, citation, and direct URLs to every machine-readable format. Endpoint: https://gitdealflow.com/api/mcp
- get_diligence_dossier (Company Diligence Dossier) - Public-source diligence dossier for a company or entity in one cited object: who acquired it (M&A history), which funds publicly backed it, and its published engineering-acceleration signal. Use mid-diligence for 'who acquired X', 'which funds backed Y', 'what's the signal on Z'. Sources are press-release / SEC-filing / both-sides-disclosed only; returns found:false (an expected outcome, not an error) with honest notes when the entity is outside the tracked corpus — never guesses. Endpoint: https://gitdealflow.com/api/mcp
- get_scout_receipts (Scout Score for GitHub User) - Compute a Scout Score (0-100) for a GitHub user from their public starring history. Cross-references starred repos against ~75 validated unicorns and grades how many they starred *before* the validation event. Returns score, rank (curious/scout/sharp/elite/oracle), top early calls, personality summary, and a shareable card URL. Endpoint: https://gitdealflow.com/api/mcp
- get_methodology (Methodology Documentation) - Full methodology document covering data sources, metric computation, signal classification thresholds, refresh cadence, and known limitations. Endpoint: https://gitdealflow.com/api/mcp
- get_deep_signal (Get Deep Signal (paid)) - PAID per-request — €0.19/call, 100 credits = €19 at https://signals.gitdealflow.com/agents/credits. Returns enriched signal beyond the free get_startup_signal: composite score (0-100), velocity/growth/novelty sub-scores, in-sector rank + percentile, plain-English investment thesis, top-3 sector comparables, and multi-period history. Requires Authorization: Bearer gdf_v2.cus_xxx.<hmac>. 1 credit consumed only on a successful match; misses are FREE. Credits never expire. Endpoint: https://gitdealflow.com/api/mcp
- share_result (Share This Result (compose tweet/social)) - Generate a ready-to-share social-media post (tweet, Bluesky, Mastodon, LinkedIn, Telegram) about a result the user just received from another VC Deal Flow Signal tool, plus the install command for the MCP server. Returns the post body, character counts per platform, and one-click intent URLs to compose the post in each network.

WHEN TO USE:
- The user just got a `get_trending_startups` / `search_startups_by_sector` / `get_startup_signal` / `get_deep_signal` result and says 'share this', 'tweet this', 'post this', or 'how do I tell people about this?'.
- The user is writing a thread/post about startup engineering signals and wants the canonical install command + share copy.

DO NOT USE FOR:
- Posting on the user's behalf — this tool only composes the text + intent URLs. The user must click and confirm in the destination network.
- Generating fake or speculative results — pass real data the agent received from another tool call.

BEHAVIOR (two-step approval flow, see `approval_token`):
- Step 1: call this tool with `summary` only. The server replies with an error (-32602) containing a `/share-approve?summary=...` URL the user must open.
- Step 2: the user reads the proposed summary on that page, clicks Approve, and pastes the resulting 10-minute token back into the chat. Retry the tool with `approval_token` filled in and the SAME `summary` verbatim.
- The token is bound to a hash of `summary`; if the agent rewrites the summary between approval and the retry, the call is rejected.
- Composes platform-specific posts (Twitter ≤275 chars, Bluesky ≤295, Mastodon ≤495, LinkedIn ≤695, Telegram ≤995) with a consistent hook + insight + install URL.
- Returns intent URLs (e.g. https://x.com/intent/post?text=...) so the user/agent can open the destination network with the post pre-filled.
- Always includes the canonical install command `npx @gitdealflow/mcp-signal` and the SSRN paper link for credibility.

PARAMETERS:
- `summary` (string, required, 10-200 chars) — the one-line takeaway to share.
- `approval_token` (string, required after first call) — the 10-minute token returned by the /share-approve page.
- `network` (string, optional) — 'twitter' | 'bluesky' | 'mastodon' | 'linkedin' | 'telegram' | 'all' (default: 'all').
- `mention_handle` (boolean, optional, default false) — include @data_nerd attribution (twitter/bluesky/mastodon only). Endpoint: https://gitdealflow.com/api/mcp
- predict_funding (Predict Funding Likelihood (with provenance)) - Transparent, scored funding-likelihood claim for one tracked startup, with the full evidence chain and citable provenance. Instead of an opaque number, returns the score, every component that produced it, a confidence level, honest caveats, and links to the methodology + SSRN paper so the derivation can be cited.

IS a deterministic heuristic over public GitHub engineering-acceleration signals; IS NOT an ML black box, a guarantee of any financing event, or based on private/cap-table data. The disclaimer is returned in every response.

SCORING (also returned in evidence.scoreBreakdown): velocity ≤40 (saturates +300%), contributorGrowth ≤25 (saturates +200%), newRepos ≤15 (saturates 10), signalType ≤20 (Deploy frequency spike 20 / Engineering hiring burst 17 / Infrastructure buildout 14 / Framework migration 8). Total 0-100 → >=70 high, 45-69 elevated, 25-44 moderate, <25 low.

PARAMETERS: { name } — display name or GitHub org slug (case-insensitive). On no match returns { found: false, suggestion } (expected, not an error). Endpoint: https://gitdealflow.com/api/mcp
- shortlist_signals (Shortlist Strongest Signals) - Return a ranked shortlist of the strongest engineering-acceleration signals matching a set of filters — the whole sourcing workflow in ONE call (e.g. 'the 5 strongest signals in fintech in the EU'). Scans the full tracked universe, scores each with the transparent engine (same scoring as predict_funding), filters, sorts by accelerationScore desc, returns the top `limit`.

GEOGRAPHY IS REGION-LEVEL ONLY — values are US / EU / UK / APAC / LATAM / Canada / Unknown. City/country aliases ('NYC', 'New York', 'London', 'Berlin', 'Singapore') normalize up to the enclosing region and the response `notes` says so. There is no city-level filtering.

PARAMETERS (all optional): sector (one of 20 slugs), geography (region token or alias), signalType (exact label), minAccelerationScore (0-100), minVelocityChangePct (integer percent), limit (1-25, default 5). Endpoint: https://gitdealflow.com/api/mcp
- compare_signals (Compare Signals Head-to-Head) - Score and rank 2-5 named startups side by side, returning each one's acceleration score, evidence, and raise-likelihood band plus a single recommendation for which warrants deeper diligence. Same transparent scoring as predict_funding / shortlist_signals.

Names that don't resolve are returned in `notFound` (expected, not an error). The recommendation is computed only over resolved companies; if fewer than 2 resolve it explains that no comparison was possible.

PARAMETERS: { names: string[] } — 2 to 5 display names or GitHub org slugs (case-insensitive). Endpoint: https://gitdealflow.com/api/mcp

## Resources
- signal://trending - Top 20 startups across all sectors for the current weekly period. MIME type: application/json
- signal://summary - Period, sector and startup counts, last refresh, format URLs. MIME type: application/json
- signal://methodology - Full methodology document. MIME type: text/markdown

## Prompts
- weekly_digest - Monday-morning Signal Digest from the current top-20 trending startups.
- sector_deep_dive - Sector intelligence brief — top movers, dark horses, thesis follow-ups. Arguments: sector
- find_dark_horse - Surface one under-the-radar startup with sustained acceleration below the median visibility threshold. Arguments: sector
- compare_startups - Head-to-head investor comparison of two named startups. Arguments: name_a, name_b
- acceleration_memo - One-page deal memo grounded in the live signal profile of a named startup. Arguments: name
- sourcing_session - Run a full sourcing session in one pass — the corp-dev / scout workflow. Shortlists the strongest engineering-acceleration signals (optionally by sector/region), then attaches a transparent, citable funding-likelihood read to each pick. Pulls live data via shortlist_signals + predict_funding. Arguments: sector, geography, count
- diligence_brief - Assemble a cited one-page diligence brief for a named company: public-source dossier (M&A, backers, signal), a transparent funding-likelihood read with its evidence chain, and the methodology behind the score. Pulls live data via get_diligence_dossier + predict_funding + get_methodology. Arguments: name

## Metadata
- Owner: io.github.kindrat86
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 19, 2026
- Source: https://registry.modelcontextprotocol.io