multiplist-mcp-server
Multiplist is an IP vault with citations, acting as an interoperable source of truth for agents. It extracts decisions, frameworks, and key passages from docs and AI conversations with character‑level provenance, so every claim traces back to exactly what you said—across 19 curated chat‑native tools in six categories: Capture, Extraction, Custom Skills, Discovery, Research, and Annotation.
README
@multiplist/mcp-server
IP Vault with Citations — extract decisions, frameworks, and insights from your AI conversations with full provenance. Every claim traces back to exactly what you said.
Your AI conversations are intellectual property. Multiplist treats them that way.
Connect via MCP
Multiplist works as an MCP server. Connect from Claude Desktop, Claude Code, or any MCP-compatible client.
Endpoint: https://multiplist.ai/mcp
Transport: StreamableHTTP + OAuth 2.1 with PKCE
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"multiplist": {
"command": "npx",
"args": ["-y", "@multiplist/mcp-server"],
"env": {
"MULTIPLIST_API_KEY": "your-key-here"
}
}
}
}
Or connect directly via the hosted endpoint:
{
"mcpServers": {
"multiplist": {
"type": "streamable-http",
"url": "https://multiplist.ai/mcp"
}
}
}
19 Curated Tools
| Category | Tools | What They Do |
|---|---|---|
| Capture | create_source, update_source, delete_source | Save conversations to your vault |
| Extraction | trigger_extraction, batch_extract, batch_status | Extract structured meaning |
| Custom Skills | create_skill, list_skills, get_skill, match_skills | Define domain-specific extraction |
| Discovery | get_source, search_vault, search_sources, get_vault_summary, get_vault_gaps | Search and retrieve with citations |
| Research | request_brief, get_brief_status | Synthesize across your vault |
| Annotate | add_annotation, add_marginalia | Write corrections and evolution notes |
What Multiplist Extracts
Nine categories of structured meaning from any conversation or document:
- Decisions — commitments, with reasoning
- Frameworks — named models and structured approaches
- Actions — next steps, with ownership
- Questions — open threads and unresolved tensions
- Definitions — terms with precise meaning in context
- Emergence — new concepts forming in real time
- Golden Passages — language worth preserving verbatim
- Exemplars — concrete examples worth referencing later
- Offers — AI suggestions and proposed next steps
Each seed traces back to exact character positions in the original source.
Custom Extraction Skills
The differentiator: you define what matters in your domain.
A coach creates a "Client Breakthroughs" skill. A developer creates an "Architecture Signals" skill. A researcher creates a "Research Distillation" skill.
Skills tell Multiplist what to look for in your specific content type. The vault learns the shape of your work.
Get Started
- Sign up at multiplist.ai
- Generate an API key in Settings
- Connect via MCP (see above)
- Say "save this conversation to my vault"
Skills Library
See github.com/multiplist/skills for pre-built skills and the Seed Doc Renderer, Archivist Research, and Custom Extraction Skills integrations.
License
MIT — multiplist.ai
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.