Search the registry

CoinGecko

1.0.0

CoinGecko

MCP

Crypto prices, market caps, and historical data via CoinGecko's official server. Free tier is rate-limited; fine for research.

Research a question across arXiv and the web, then write a cited report.

Higgsfield

1.0.0

Higgsfield

MCP

30+ image and video models (Sora, Veo, Kling, Seedance) through one endpoint — research, prompt-optimize, and generate creative assets. Use the official connector, not session-scraping forks.

YouTube

1.0.0

anaisbetts

MCP

Video search and transcript extraction — great for research and repurposing content. Transcript availability depends on the video having captions.

Search arXiv papers by keyword, author, category, or ID.

Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.

Use when performing security research, red-teaming, or threat modeling. 753+ structured cybersecurity skills mapped to MITRE ATT&CK tactics and techniques.

Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.

Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Extract text from PDFs/scans (pymupdf, marker-pdf).

Use when orchestrating multi-agent workflows: deep research, planning with consensus, verified execution, triage, or autopilot. Suite of driver skills for Hermes-native multi-agent coordination.

Query Polymarket: markets, prices, orderbooks, history.

Write ML papers for NeurIPS/ICML/ICLR: design→submit.

Throwaway experiments to validate an idea before build.