"Understanding Prompts or Prompt Engineering" matching MCP connectors:

Open scientific and engineering knowledge for AI agents: search, evidence, document publishing.

Search harness engineering, agentic AI patterns, architectures, governance and agent taxonomy.

Check claims against a fact-store: consistent, contradicts, or unverifiable — with a receipt.

Citation-health over a CC0 citation graph: what supports, refutes, or cites a paper. Read-only.

Collaborative engineering KB for a mile-high city. 9 tools, 8 domains, 32 entries.

A persistent intention layer for AI agents. Injects a soul document into model system prompts before each session. REST API + MCP server. Auth via X-API-Key header.

Search and retrieve articles from the Sovereign AI Blog. A practical engineering log of self-hosted AI on NVIDIA DGX Spark with articles covering SGLang, Mistral, Voxtral, OpenClaw. Tools: search_blog, get_article, diagnose_sglang. Endpoint URL: https://mcp.sovgrid.org/self-hosted-ai?ref=smithery Transport: streamable-http (oder „HTTP Streaming") Tags/Categories: knowledge-base, search, self-hosted-ai, sovereign

Biblical and theological research MCP server. Ask pastoral questions, run academic-grade queries across 2M+ scholarly passages (lexicons, commentaries, church fathers, Dead Sea Scrolls, Talmud), or search raw sources directly. Free, no API key required.

Real engineering memory marketplace for autonomous AI agents. Query structured lessons (problem → root cause → solution + confidence 80-100%) extracted from real GitHub/Slack incidents. Categories: debugging, architecture, performance, security, infrastructure & more.

Search everything you save: YouTube, articles, podcasts, PDFs, Notion, Obsidian. API key or OAuth.

Governance and grounding layer for engineering teams running AI coding agents (Claude Code, Cursor, Codex). Grounds agents in your codebase's knowledge graph, and adds session audit, policy controls and cost/token visibility.

Cross-AI personal memory. Save once in ChatGPT, recall in Claude, Mistral, Grok, or any MCP client.

Personal AI memory server running on Android. Connect your Claude or Perplexity to memory stored on your own phone.

Give your agents trusted access to a company's living documentation. Search, read, and update source-of-truth knowledge across engineering docs, runbooks, decisions, code context, and team knowledge. `https://falconer.com/mcp

Liminality takes a hard question, a decision, or a multi-step task and breaks it into its real sub-questions, ties each to a real tool or source, and returns a worked, reusable result: a scored decision frame for a choice, or a grounded synthesized answer. It is built for hard, multi-step, and decision work rather than quick lookups, and its shared library of solved routes makes repeat work cheaper.

Docsie MCP brings your documentation workflow directly into your AI assistant. Create, edit, and publish documentation without switching between tools. Convert videos into structured documentation instantly, run compliance analysis across text, audio, and video content, and use semantic search to find exactly what you need across your knowledge base. Whether you're building product documentation, SOPs, user guides, or technical manuals, Docsie MCP makes documentation faster, smarter, and powered

Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.

Individual-analyst context layer: recall, remember, and reconcile your data and engineering context.

Illumora Craft — evidence-augmented prompt compile for agents via remote MCP (OAuth) or local stdio.

Semantic search over MINDSET's brand strategy topic database, plus its system prompt.