Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
PaperVantage
MCP serversSearch distilled arXiv papers, full-text chunks, figures, citations, and reading lists.
-
massive-context-mcp
MCP serversHandles 10M+ token contexts with chunking, sub-queries, and local Ollama inference.
massive-context-mcp@3.0.1 -
rag
MCP serversMCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
FieldCure.Mcp.Rag@2.5.1 -
rag-mcp
MCP serversMinimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.
jaimenbell-rag-mcp@0.1.0 -
doc-extract-mcp
MCP serversDocument tooling for AI agents: PDF/text reading, chunking, schema-validated JSON output.
-
Lifestyle Medicine Knowledge
MCP serversSemantic search over a 200-chunk ACLM lifestyle medicine knowledge base.
-
Perfonext Build MCP
MCP serversMCP server for Next.js build stats, chunk attribution, and bundle optimization advice.
@perfonext/build-mcp@0.6.2 -
Unstructured Transform
MCP serversTurn documents into structured, AI-ready data by parsing, enriching, chunking, and embedding.
-
Renyi
MCP serversCheck, format, run and test Renyi programs; the project map with effects, diffs and chunks.
renyi@0.4.0 -
Web2MD
MCP serversTurn any web page into clean Markdown, text or token-bounded RAG chunks (via RapidAPI).
web2md-rag-mcp@0.1.0 -
agent-app-ingestion
AI repositoriesData ingestion service for the Agent Landing Zone. Processes PDFs, images, spreadsheets, transcripts and SharePoint content into grounding knowledge for agents, with smart chunking and multimodal embeddings.
git clone https://github.com/Azure/agent-app-ingestion.git -
stagenth · file-relay
MCP serversCloud file relay: chunked uploads, folders, share links, inline text reads, ZIP packing.
-
MidOS - MCP Community Library
MCP serversCurated knowledge for AI agents — 19K chunks, 121 skills, semantic search via MCP
midos-mcp@2026.2.23.1 -
context-cloud
MCP serversPersistent AI memory with shared team workspaces, typed knowledge chunks, and cross-tool support.
@contextcloud/mcp-client@0.1.8 -
RAG Documentation Scraper
MCP serversCrawl any documentation site and return heading-bounded, LLM-ready chunks with source metadata.
rag-docs-scraper-mcp-server@1.0.0 -
codearia-sieve
MCP serversWeb pages into decision-ready state: dates, numbers with units, budgeted chunks. No model, no key.
codearia-sieve@0.2.2 -
CocoIndex Code
MCP serversSemantic code search over a local repository, with AST-based chunks and incremental re-indexing.
cocoindex-code@0.2.43 -
unstructured
AI repositoriesConvert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.
git clone https://github.com/Unstructured-IO/unstructured.git -
stagenth · 文档解析
MCP serversParse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.
-
Ragfeed
MCP serversWeb pages, PDFs and search results as LLM-ready Markdown or chunks. Firecrawl-compatible, EU-hosted.
-
Ultra-low-latency incremental line validator with chunk boundary reassembly and schema auditing
https://github.com/Alpha-Park/genpark-streaming-ndjson-jsonl-schema-validator-skill/releases/download/v1.0.1/genpark-streaming-ndjson-jsonl-schema-validator-skill.mcpb -
Kizuki RAG Ingest
MCP serversYouTube transcripts (chunks, phrase search, most replayed moments), PDFs and web pages as Markdown.
-
doc-to-markdown
MCP serversPDF, Word, PowerPoint, Excel, HTML, EPUB to Markdown: OCR, page ranges, tables, RAG chunking
-
YouTube Transcripts & Subtitles
MCP serversBulk YouTube transcripts from videos, channels, playlists or search: text, RAG chunks, SRT, VTT.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.