GitDealFlow — GitHub signals for startup investors
48 toolsSTDIOregistry active
Summary
Pulls engineering velocity signals from a curated set of 85+ startups across 20 sectors, surfacing commit activity, contributor growth, and repo expansion as early traction indicators. You get five read-only tools: query trending startups globally, filter by sector (AI/ML, fintech, climate tech, etc.), look up a specific startup's signal profile, grab a dataset summary, or fetch the methodology. All data comes live from a public API updated weekly. Useful when you're sourcing deals and want GitHub activity as a leading indicator before cap tables and pitch decks arrive. The same dataset powers a prediction game and two Chrome extensions for Crunchbase and GitHub if you want the signals in other contexts.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Tools
Public tool metadata for what this MCP can expose to an agent.
8 tools
get_trending_startupsTop 20 startups by engineering acceleration across all 20 sectors for the current weekly period. Read-only, idempotent.
Top 20 startups by engineering acceleration across all 20 sectors for the current weekly period. Read-only, idempotent.
No parameter schema in public metadata yet.
search_startups_by_sectorEvery tracked startup within a sector, ranked by engineering acceleration. Sector slug must be one of 20 enumerated values.1 params
Every tracked startup within a sector, ranked by engineering acceleration. Sector slug must be one of 20 enumerated values.
Parameters* required
sectorstringSector slug from the enumerated list. Map fuzzy user input to the closest slug (e.g. 'AI' → 'ai-ml', 'crypto' → 'web3', 'cyber' → 'cybersecurity', 'SaaS' → 'enterprise-saas').one of
ai-ml · fintech · cybersecurity · developer-tools · healthcare · climate-techget_startup_signalFull engineering-acceleration profile for a single tracked startup, by display name or GitHub org slug. Case-insensitive, normalization-tolerant.1 params
Full engineering-acceleration profile for a single tracked startup, by display name or GitHub org slug. Case-insensitive, normalization-tolerant.
Parameters* required
namestringStartup display name OR GitHub org name. Case-insensitive; punctuation and whitespace are ignored during matching.
get_signals_summaryPeriod, sector and startup counts, last refresh, citation, and direct URLs to every machine-readable format.
Period, sector and startup counts, last refresh, citation, and direct URLs to every machine-readable format.
No parameter schema in public metadata yet.
get_scout_receiptsCompute 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 c...1 params
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 c...
Parameters* required
github_usernamestringGitHub username, 1-39 chars, alphanumeric + single hyphens.
get_methodologyFull methodology document covering data sources, metric computation, signal classification thresholds, refresh cadence, and known limitations.
Full methodology document covering data sources, metric computation, signal classification thresholds, refresh cadence, and known limitations.
No parameter schema in public metadata yet.
get_deep_signalPAID 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 th...1 params
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 th...
Parameters* required
namestringStartup display name or GitHub org slug.
share_resultGenerate 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-cl...3 params
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-cl...
Parameters* required
mention_handlebooleanInclude @data_nerd attribution. Only applied to twitter/bluesky/mastodon.default: false
networkstringTarget network. 'all' returns one post per network.one of
twitter · bluesky · mastodon · linkedin · telegram · alldefault: allsummarystringOne-line takeaway (10-200 chars) the user wants to share.
VC Deal Flow Signal — MCP Server
Search startup engineering acceleration signals directly from your AI assistant.
Glama A-Tier (4.9 / 5.0). 13 tools — 10 free, no API key. One-line install for Claude Desktop, Claude Code, Cursor, Cline, and Continue via
npx -y @gitdealflow/mcp-signal.
Tracks commit velocity, contributor growth, and repository expansion across 15 sectors and 350+ startups. Built for angels, scouts, and technical operators looking for traction signals before they show up in traditional deal flow.
Install
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"vc-deal-flow-signal": {
"command": "npx",
"args": ["-y", "@gitdealflow/mcp-signal"]
}
}
}
Or for Claude Code (.mcp.json in project root):
{
"mcpServers": {
"vc-deal-flow-signal": {
"command": "npx",
"args": ["-y", "@gitdealflow/mcp-signal"]
}
}
}
Tools
All tools are read-only, idempotent, and fetch live data from the public API (no auth required). Responses include both human-readable text and structured JSON (structuredContent) matching each tool's outputSchema.
Free tools (10) — no API key, no account:
| Tool | Input | Returns |
|---|---|---|
get_trending_startups | — | Top 20 startups ranked by engineering acceleration across all sectors. |
search_startups_by_sector | sector (enum of 15 slugs) | All tracked startups in the sector, ranked by acceleration. |
get_startup_signal | name (case-insensitive) | Full signal profile for one startup: velocity, contributors, repos, classification. |
get_signals_summary | — | Dataset snapshot — period, counts, refresh date, format URLs, citation. |
get_methodology | — | How signals are sourced, computed, and classified, with known limitations. |
shortlist_signals | filters (sector, stage, geography, signal type) | Ranked shortlist of the strongest engineering-acceleration signals matching your filters. |
compare_signals | 2–5 startup names | Side-by-side acceleration scores, evidence, and raise-likelihood for the named startups. |
predict_funding | name | Transparent, scored funding-likelihood claim with the full evidence chain, citable. |
get_diligence_dossier | company/entity name | Public-source diligence dossier in one cited object — M&A history, funding, key facts. |
get_scout_receipts | GitHub username | Scout Score (0–100) computed from public starring history, cross-referenced against tracked startups. |
Paid agent tools (3) — €0.10 per call, credits at signals.gitdealflow.com/agents/credits:
| Tool | Returns |
|---|---|
research_company | Enriched dossier for one tracked startup: full signal row, sector rank, top-5 sector peers, citation. |
compose_thesis | Structured investment thesis: snapshot, signal type, sector rank, data-derived strengths, peer comparables. |
deep_dive_scan | Multi-cohort sector scan: tracked/breakout/cooling counts, top-10 by velocity, breakout and cold lists. |
The hosted remote endpoint (https://signals.gitdealflow.com/api/mcp/rpc, streamable-http) additionally exposes share_result (free) and get_deep_signal (€0.19/call).
Supported sectors: healthcare, edtech, ecommerce-infrastructure, supply-chain, web3, enterprise-saas, data-infrastructure, robotics, legal-tech, hr-tech, proptech, agtech, gaming, space-tech, social-community.
Data
All data is sourced live from the deal flow data API public API. No API key required. Updated weekly on Mondays.
- Live CSV: https://signals.gitdealflow.com/api/signals.csv
- Live JSON: https://signals.gitdealflow.com/api/signals.json
- Stable CC BY 4.0 research snapshot: https://huggingface.co/datasets/the-data-nerd/vc-deal-flow-signal
- DOI-stamped release: https://doi.org/10.5281/zenodo.19650920
- Free field guide: Seven Signals explains the method, limits, and replication path in 104 pages.
Complementary: the Scout Game
If you want to put your own eye on the line, there's a prediction game on top of the same dataset at signals.gitdealflow.com/predict. Call which tracked startups raise a round in the next 6 months, earn points when your calls resolve, climb a public rank ladder from Curious to Oracle. Free tier: 3 predictions per month. Paid: 10 per month. Leaderboard: signals.gitdealflow.com/leaderboard.
Complementary: two Chrome extensions
Same dataset, different surfaces. Install one or both:
- VC Deal Flow Signal — Crunchbase + Wellfound badge: a green "Accelerating" engineering-acceleration badge appears inline on any Crunchbase or Wellfound startup profile where the GitHub data is interesting. For investors who research deals in browser tabs.
- VC GitHub Lookup — Startup Signals on Hover (NEW, May 2026): hover any GitHub repo or org link to see commit velocity (14d), velocity change vs prior period, contributor count and growth, signal type, and stage estimate. Chip injected on direct repo and org page loads. Toolbar opens a manual lookup form for any GitHub URL. For developer-investors who live on GitHub.
Both are free in perpetuity. Manifest V3, no analytics, no account.
Links
- Website: https://gitdealflow.com
- Dashboard: https://signals.gitdealflow.com
- Scout Game: https://signals.gitdealflow.com/predict
- Leaderboard: https://signals.gitdealflow.com/leaderboard
- Chrome extension #1 (Crunchbase + Wellfound badge): https://chromewebstore.google.com/detail/hehkgipiamajnnlpkfhpeoeaoaogmknn
- Chrome extension #2 (VC GitHub Lookup — hover): https://chromewebstore.google.com/detail/vc-github-lookup-%E2%80%94-startu/plgngijmloeljfkenecdkhiblcfcbblm
- JSON API: https://signals.gitdealflow.com/api/signals.json
- Twitter/X: https://x.com/data_nerd
License
MIT
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Categories
Registryactive
Package@gitdealflow/mcp-signal
TransportSTDIO
UpdatedMay 30, 2026
