MCP server for web research, academic papers, Twitter/X, YouTube, and file ingestion. Eight tools for AI assistants — all via the MCP stdio protocol. Includes credential vault for institutional…
Maibaamcrawler is an MCP project maintained in the mabaam/maibaamcrawler repository. The maintainer describes its purpose as “MCP server for web research, academic papers, Twitter/X, YouTube, and file ingestion. Eight tools for AI assistants — all via the MCP stdio protocol. Includes…”. Read the project documentation for the complete scope.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| web_search | |
| fetch_url | |
| research | Compound pipeline: query rewrite → search → parallel fetch → summarize → synthesize |
| youtube_essence | |
| deep_ingest | |
| academic_lookup | |
| twitter_extract | |
| vault_status | |
| summarize | Use Ollama to summarize results (requires running Ollama) |
| auto_fetch_top | Also fetch and return the full content of the top result |
| Token-efficient | Default 15K chars (~4K tokens), adjustable via max_chars |
| Transcript | Auto-subtitles or Whisper transcription (local, private) |
| Summary | AI summary via Ollama |
| Chapters | Timestamped segments |
| Quotes | Notable quotations (deep mode) |
| Via PyPDF2 (optional dependency) | |
| Office | .docx, .xlsx, .pptx (optional dependencies) |
| Images | OCR via Ollama vision model (optional) |
| DOI | 10.xxxx/... → Crossref metadata + publisher redirect |
| ArXiv | 2301.12345 → abstract + PDF |
| PubMed | PMID → E-utilities metadata → DOI chain |
| URL | Publisher page detection |
| Depth | Pages |
| quick | 2 |
| standard | 5 |
| deep | 10 |
Inspect PostgreSQL schemas and run read-only queries with the archived MCP reference server. Review its maintenance status before choosing it.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
Enables programmatic access to the IACR Cryptology ePrint Archive for efficient retrieval of cryptographic research papers.
Manage educational context based on courses, assignments, and exams using a knowledge graph.
MCP server with tools to search, fetch, analyze, and report on scientific papers and datasets.
Scholarly search: OpenAlex, Crossref, arXiv, OpenCitations and PubMed in one endpoint.