bryan-protocol-mcp
Indexes YouTube videos, livestreams, and Shorts from Bryan Johnson's and Kate Tolo's channels, providing full-text search over transcript segments and timestamped ?t=...s links to the exact moment a topic was discussed.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@bryan-protocol-mcp Does Bryan still take rapamycin?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
bryan-protocol-mcp
A searchable ground-truth database and Model Context Protocol (MCP) server for Bryan Johnson's Blueprint Protocol.
Live Web App: https://bryan-protocol-mcp.netlify.app
Public Streamable HTTP MCP:
https://bryan-protocol-mcp.netlify.app/mcp
It indexes his official protocol pages, Blueprint blog posts, YouTube videos/livestreams, and full-length podcast appearances into a local SQLite FTS5 archive, alongside a curated stance matrix tracking what he actively does, what he stopped doing, and what he avoids.
Runs on Python 3.10+ stdlib and SQLite FTS5 with zero external runtime dependencies.
Why build this?
Several RAG demos and static trackers exist around Blueprint (such as BlueprintAI, agent-bryan, OpenLongevity, and nutrimetrics), mostly built as standalone web chatbots over a single snapshot of the site.
This repo focuses on being a clean, citation-first MCP data source for tools like Claude Desktop, Cursor, or VS Code, with three goals:
Tiered source priority: Official
protocol.bryanjohnson.comrules take precedence over older podcast clips or exploratory experiments.Tracking what changed or stopped: Explicit entries for things Bryan dropped or avoids (like stopping rapamycin in Sept 2024, stopping HGH after 100 days, skipping cold plunges, avoiding caffeinated coffee, and his nuanced take on cold-pressed vs. high-heat seed oils).
Timestamped primary citations: Every video and podcast match includes a
?t=...sYouTube link to the exact moment he said it.
Related MCP server: loci-mcp
Dataset
Everything is pre-indexed in data/bryan_protocol.db (643 documents, 13,765 timestamped segments, 35 structured stances):
Tier | Source Type | Count | Notes |
Tier 1 |
| 29 | Current sections from |
Tier 1 |
| 1 | Kate Tolo's official profile and $2.6M Female Protocol summary ( |
Tier 2 |
| 95 | 77 articles from |
Tier 2 |
| 82 | 50 Blueprint catalog products and 32 Immortals Rx/biomarker offerings |
Tier 2 |
| 38 |
|
Tier 2 |
| 20 | Full-text essays from |
Tier 2 |
| 285 | 139 videos, 9 livestreams, and 137 Shorts from |
Tier 2 |
| 64 | 5 videos and 59 Shorts from |
Tier 3 |
| 29 | Full-length appearances including More Plates More Dates (4h14m), ZOE, NYT Interesting Times, ARK Invest, WIRED, Friends Keep Secrets, Live Well Be Well (Kate Tolo), Colin & Samir (Kate Tolo), Modern Wisdom, Rich Roll, Theo Von #644, Diary of a CEO (x2), Lex Fridman #186, Impact Theory (x3), FULL SEND, Jubilee, Doctor Mike, FLAGRANT, IMPAULSIVE, Jay Shetty, Mark Hyman, The Knowledge Project, Tim Ferriss, Piers Morgan, Axios |
Stances |
| 35 | Active, stopped, avoided, conditional, and experimental positions (Bryan + Kate Tolo / Female Protocol) with dates and links |
Quick Start
Run locally from the CLI
git clone https://github.com/MihailoPesic/bryan-protocol-mcp.git
cd bryan-protocol-mcp
PYTHONPATH=src python3 -m bryan_protocol_mcp stats
PYTHONPATH=src python3 -m bryan_protocol_mcp query "Does Bryan still take rapamycin?"
PYTHONPATH=src python3 -m bryan_protocol_mcp query "Should I cold plunge or drink coffee?"Use with an MCP client (Claude Desktop, Cursor, VS Code)
Add the server to your MCP config (see mcp_config_examples.json):
{
"mcpServers": {
"bryan-protocol": {
"command": "python3",
"args": ["-m", "bryan_protocol_mcp", "serve"],
"env": {
"PYTHONPATH": "/path/to/bryan-protocol-mcp/src"
}
}
}
}Or install in editable mode so bryan-protocol-mcp is on your PATH:
pip install -e .
bryan-protocol-mcp serveOptional HTTP JSON-RPC server (Python)
PYTHONPATH=src python3 -m bryan_protocol_mcp serve --transport http --host 127.0.0.1 --port 8000Public Web UI & Hosted Streamable HTTP MCP (Netlify)
In addition to the local Python stdio server, this repo includes a React + Tailwind CSS frontend (web/) and serverless Streamable HTTP MCP endpoint (netlify/functions/mcp.mts) ready to deploy on Netlify:
GET /: Searchable reference index with shareable?q=...verdict links, a "Stopped & Avoided" changelog, timestamped video/podcast jump links, and a slide-over source reader.POST /mcp: Public Streamable HTTP MCP server built on@modelcontextprotocol/sdk(WebStandardStreamableHTTPServerTransport), backed by a compressed 2.1 MB archive bundle (netlify/functions/data/archive.json.gz).GET /api/query,/api/stances,/api/overview,/api/document,/api/sources: JSON endpoints powering the web UI.
Deploy straight to Netlify by linking the GitHub repository (build command python3 scripts/build_web_bundle.py && npm run build:web, publish directory dist).
Available MCP Tools & Resources
Tools
what_would_bryan_do: Pulls matching stances (active,stopped,avoid), Tier 1 official protocol pages, Tier 2 articles/videos, and Tier 3 podcast quotes with timestamps.check_stance_and_changes: Checks whether Bryan uses, stopped, or avoids a specific compound, food, or habit along with chronological mentions.get_official_protocol: Searches Tier 1protocol.bryanjohnson.comsections directly.search_archive: Full-text BM25 search across documents and transcript segments (filterable bytierandsource_type).get_document: Retrieves full text and optional timestamped segments for any document ID.list_sources: Paginated listing of indexed documents and podcasts.get_protocol_overview: Returns database counts, build timestamp, and Tier 1 page index.
Resources & Prompts
bryan://protocol/index: Official protocol index and counts.bryan://protocol/stances: Full JSON stance matrix.Prompt
evaluate_against_blueprint: Evaluates a food, habit, or supplement against cited Blueprint sources.
Updating the Archive
The scrapers run using Python's standard library (WordPress REST API, Shopify sitemap/JSON-LD, and YouTube Innertube endpoints):
# Refresh official pages, articles, @BryanJohnson videos, and external podcasts
PYTHONPATH=src python3 -m bryan_protocol_mcp ingest --all
# Rebuild SQLite FTS5 and the Netlify bundle after editing data/stances.json or data/external_podcasts.json
PYTHONPATH=src python3 -m bryan_protocol_mcp build-db
python3 scripts/build_web_bundle.pyTo index additional YouTube interviews or podcast appearances, add their video IDs to data/external_podcasts.json and run ingest --youtube.
Tests
python3 -m unittest discover -s tests -v
node --test tests/node_engine.test.mjsDisclaimer
Independent archive of Bryan Johnson's publicly shared Blueprint protocols, articles, videos, and interviews. Not affiliated with Bryan Johnson or Blueprint, and not medical advice.
Available Tools
7 toolscheck_stance_and_changesA
Check whether Bryan actively uses/does something, stopped doing it, or strictly avoids it, including rationale and chronological mentions across videos and articles.
Inputs: topic (required).
get_documentA
Fetch the full text (and optionally timestamped segments) of any document ID returned by search or list_sources.
Inputs: doc_id (required), max_chars, include_segments.
get_official_protocolB
Look up authoritative Tier 1 sections from protocol.bryanjohnson.com for a given topic (e.g. sleep, nutrition, exercise, skin, oral care, hair, biomarkers, rx).
Inputs: topic (required), limit, include_full_content.
get_protocol_overviewA
Get database stats, source tiers, last-ingested metadata, and the index of all official Tier 1 protocol.bryanjohnson.com sections.
Inputs: no named parameters.
list_sourcesC
List ingested documents, articles, videos, and podcasts with pagination and optional tier/source_type filters.
Inputs: tier, limit, offset, source_type.
search_archiveC
Full-text BM25 search across all official protocol pages, Blueprint blog articles, @BryanJohnson videos/streams, and external podcast transcripts.
Inputs: query (required), tier, limit, source_type.
what_would_bryan_doA
Retrieve a tiered Ground Truth Dossier (explicit stances, Tier 1 protocol pages, Tier 2 Bryan videos/articles, Tier 3 external podcast timestamped quotes) to answer what Bryan Johnson would or wouldn't do in a scenario.
Inputs: question (required), max_per_tier, include_transcripts.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Several tools target overlapping questions about Bryan's positions: what_would_bryan_do, check_stance_and_changes, get_official_protocol, and search_archive can all plausibly answer 'what does Bryan think about X'. The descriptions differentiate them somewhat (scenario dossier vs. chronological stance tracking vs. Tier 1 only vs. broad search), but an agent could still misselect among the four.
Most names follow a clean verb_noun snake_case pattern (get_protocol_overview, get_official_protocol, check_stance_and_changes, search_archive, get_document, list_sources). The outlier is the question-style 'what_would_bryan_do', which breaks convention but is memorable and domain-appropriate.
Seven tools is well within the ideal 3-15 range for a knowledge-retrieval server. Each tool has a plausible distinct role (overview, targeted lookup, scenario dossier, stance tracking, search, fetch, list), so nothing feels padded.
The surface covers the core lifecycle of a RAG-style knowledge server: discover (overview/list_sources), search (search_archive), and fetch (get_document), plus specialized protocol/stance lookups. Minor gaps exist (e.g., no explicit topic/section enumeration tool beyond the overview, no related-documents or cross-source comparison), but agents can work around these via search_archive and get_document.
Maintenance
Related MCP Connectors
Search 36M+ PubMed biomedical articles and ClinicalTrials.gov studies.
Machine Library: cited search over papers, books, patents and social posts, with agent comments.
Search and cite research claims with their evidence and reliability scores; publish claimsets.
Search distilled arXiv papers, full-text chunks, figures, citations, and reading lists.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables local read-only search and retrieval of approved, current evidence via hybrid lexical and dense methods, with tools to get exact source spans, answer from cited passages, and create and verify recheckable evidence packets.MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP hosts to query locally indexed notes, docs, chat logs, and other files via hybrid vector/BM25 retrieval with section-level citations. Exposes tools, resources, and prompts for searching and asking over the indexed content.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP hosts to search a locally indexed second brain built from scattered notes, docs, PDFs, and chat exports, returning hybrid vector-plus-keyword results with section-level citations rather than whole files.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP hosts to search and ask questions across a local hybrid-retrieval index of scattered notes, documents, PDFs, and chat logs, returning section-level citations and agent-usable tools, resources, and prompts.-