"Sublime Text" matching MCP connectors:

Full-text financial reports (US, China, Japan, Korea, Taiwan, UK) as clean Markdown for RAG agents.

Local ML: speech to text (SRT/VTT), text embeddings, reranking, similarity, entities, zero-shot.

Public read-only recipe library for AI agents. Search 29 Hebrew workflow recipes and retrieve exact full text with list_recipes and get_recipe. Six recipes have full English companions; other English fields are labeled summaries. Streamable HTTP, no API key. Docs: https://ofershap.github.io/agent-success-hub/mcp-connect.md . Official registry: io.github.ofershap/recipe-library.

Read-only Hebrew AI-agent recipe library with search and full-text retrieval.

x402 PDF text, pages, and metadata for AI/RAG. $0.0015 per successful PDF.

x402 clean article text and metadata for AI/RAG. $0.002 per successful article.

Observe MCP tools, verify repeated reads, then try bounded exact reuse for free.

Any URL to clean text, markdown, or JSON for LLM/RAG pipelines.

TestGraph is a shared structured knowledge and review graph for AI agents. Its MCP server lets ChatGPT, Claude and other AI clients store, retrieve and collaboratively refine reviews, entities, relationships and semantic classifications, providing persistent knowledge that can be reused across models and conversations.

LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.

Free mechanical checks for AI text: unnamed counts, dangling references, bad arithmetic, misquotes.

Manage AI support chatbots: train on webpages and text, search knowledge, view leads and questions.

Extract text, tables and RAG chunks from public PDF URLs; pay-per-event via your Apify account.

Search screen text, audio transcriptions, app data and memories already synced to your Screenpipe account. Offers synced-devices and search-synced-content with read-only OAuth (data-sync:read). Requires Data Sync to be available and enabled. Local-only recordings are excluded; connecting does not enable uploads. Requested results go to your connected AI provider. Submitted by the Screenpipe team.

Bulk YouTube transcripts from videos, channels, playlists or search: text, RAG chunks, SRT, VTT.

past.dev is a memory layer for AI agents. You send timestamped text and get back the facts that are current, with dated sources and the history behind them, so an agent knows what changed and what it replaced. Ranked first on BEAM at every history size from 100K to 10M tokens, with the method and the evaluation harness published.

Convert PDF URLs to clean Markdown and text for RAG and LLM input. Pay per PDF on Apify.

Map text into knowledge graphs to create a structured representation of conceptual relations and t…

Rafter holds a team's durable knowledge — skills, agents and memory files, each versioned — and serves it to AI tools over MCP. Agents search across the team's artifacts before answering questions about how the team works or what was decided, fetch full artifact text along with its citation edges (cites, cited_by, links) to explore related material, and write new learnings back as memory. Also covers workspace, team and membership management.

Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.