
second-brain MCP
Built for anyone drowning in saved papers and scattered notes. Saves any arXiv link or PDF, auto-upgrades abstracts to full HTML, OCRs every figure with Claude Vision, then indexes everything in DuckDB with semantic embeddings. Search across figure panels by gene name or p-value, not just document titles. Auto-wikilinks new notes to related content already in your vault. Implements Ebbinghaus scoring to compress stale notes into PNG snapshots at 60-90% token reduction while keeping frequently accessed material at full fidelity. Exposes get_context, search_figures, search_notes, save_article, and update_goals over stdio. Pure Markdown vault, so you can sync via iCloud or git and switch agents anytime. Runs nomic-embed-text locally via llama-server with BM25 fallback.
- GitHub stars
- 2
- tools
- 12
- transport
- STDIO
- last updated
- May 29, 2026
Tools
12 toolsPublic tool metadata for what this MCP can expose to an agent.
auth_contextRead the authenticated caller's canonical UUID, role, and RBAC state
Read the authenticated caller's canonical UUID, role, and RBAC state
No parameter schema in public metadata yet.
get_contextSession start — goals + top-ranked notes + auto-rules
Session start — goals + top-ranked notes + auto-rules
No parameter schema in public metadata yet.
save_articleURL / PDF → Markdown + figures + embeddings
URL / PDF → Markdown + figures + embeddings
No parameter schema in public metadata yet.
search_notesHybrid BM25 + semantic search (note text / figure content)
Hybrid BM25 + semantic search (note text / figure content)
No parameter schema in public metadata yet.
search_figuresHybrid BM25 + semantic search (note text / figure content)
Hybrid BM25 + semantic search (note text / figure content)
No parameter schema in public metadata yet.
search_articlesStructured author, ORCID, DOI/PMID/PMCID and year search for papers
Structured author, ORCID, DOI/PMID/PMCID and year search for papers
No parameter schema in public metadata yet.
audit_article_recordsBounded, read-only article housekeeping and social-source freshness report
Bounded, read-only article housekeeping and social-source freshness report
No parameter schema in public metadata yet.
new_noteCreate & edit notes (auto-filed, auto-indexed, auto-linked)
Create & edit notes (auto-filed, auto-indexed, auto-linked)
No parameter schema in public metadata yet.
update_noteCreate & edit notes (auto-filed, auto-indexed, auto-linked)
Create & edit notes (auto-filed, auto-indexed, auto-linked)
No parameter schema in public metadata yet.
append_to_noteCreate & edit notes (auto-filed, auto-indexed, auto-linked)
Create & edit notes (auto-filed, auto-indexed, auto-linked)
No parameter schema in public metadata yet.
vault_sleepCompress old, low-activity notes
Compress old, low-activity notes
No parameter schema in public metadata yet.
get_agent_instructionsServe the full filing SOP (AGENTS.md) to remote agents
Serve the full filing SOP (AGENTS.md) to remote agents
No parameter schema in public metadata yet.
Sponsors
Readme
second-brain MCP Server
A self-maintaining personal knowledge base for AI agents — a plain-Markdown vault, powered by MCP.
📖 English · 繁體中文
A local knowledge base your AI agent can read, write, and maintain on its own. Save a paper or note with one command — second-brain converts it to Markdown, OCRs every figure, embeds it for semantic search, and auto-links it to related notes. Notes you stop reading compress themselves over time, so recall stays cheap as the vault grows.
Everything is plain Markdown — sync via Google Drive / iCloud / git, switch agents anytime, zero lock-in.
Highlights
Details
- Repository
- github.com/ddmanyes/second-brain-mcp
- Categories
- AI & LLM Tools, Documents & Knowledge, Search & Web Crawling
- Package
mcp-second-brain- Transport
- STDIO
- Registry
- MCP registry, active