Peptide Library
Peptide research profiles, evidence by tier, comparisons and educational content. No dosing.
Que pouvez-vous faire avec Peptide Library ?
- Give doses, regimens, cycles, reconstitution or injection instructions.
- List vendors, prices or purchase links.
- Read or change any account or personal data.
- Rank peptides or invent studies or citations.
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
claude mcp add --transport http peptide-library 'https://peptidelibrary.app/mcp'
{
"mcpServers": {
"peptide-library": {
"type": "http",
"url": "https://peptidelibrary.app/mcp"
}
}
}
Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
Sommaire
Peptide Library MCP Server
A remote Model Context Protocol server providing structured peptide research information, educational comparison tools, and research resources for compatible AI assistants.
Website: https://peptidelibrary.app
Server URL: https://peptidelibrary.app/mcp
Documentation: https://peptidelibrary.app/developers/mcp
The server is hosted by Peptide Library. It is free, anonymous and read-only: no account, no API key and nothing to install. This repository holds its public documentation, client configuration examples and registry metadata; the server itself runs from Peptide Library's private codebase.
What it does
| Tool | Description |
|---|---|
search_peptides | Fuzzy search by name, synonym or alias, with research-category and research-area filters and pagination |
get_peptide_details | Research profile: classification, mechanism and targets, evidence by tier (regulatory label, controlled human trials, other human studies, animal and in-vitro research) with cited sources, safety, FDA/WADA status, review dates |
compare_peptides | Side-by-side comparison of 2 or 3 profiles on structured fields; never ranks |
search_research | Search Peptide Library's FAQ, per-peptide FAQs, articles and courses, with links |
get_peptide_categories | Research categories with descriptions, counts and member profiles |
get_research_trends | This week's most-researched peptides in the community, as percentages |
convert_units | mg ↔ mcg, and IU only with a peptide's documented IU-per-mg factor |
solution_concentration | Amount ÷ volume as mg/mL, mcg/mL (IU/mL with a documented factor) |
blend_concentrations | Per-component concentration and share in one volume |
cost_per_amount | Total cost and cost per mg/mcg/IU from a price you enter |
Resources: peptidelibrary://categories, peptidelibrary://evidence-levels, peptidelibrary://methodology, peptidelibrary://glossary, peptidelibrary://disclaimer, peptidelibrary://peptide/{id}.
Prompts: compare_peptide_research, summarize_peptide_evidence, explain_mechanism, find_research_topics, understand_research_limitations.
Every result includes the Peptide Library URL it came from and a research-use disclaimer. Fields the library doesn't have are returned as not_documented.
What it will not do
- Give doses, regimens, cycles, reconstitution or injection instructions.
- List vendors, prices or purchase links.
- Read or change any account or personal data.
- Rank peptides or invent studies or citations.
Research and educational use only. Not medical advice. Peptide Library does not sell peptides.
Connect
Claude (claude.ai and Claude Desktop)
Customize → Connectors → Add custom connector → name Peptide Library, URL https://peptidelibrary.app/mcp. On Team and Enterprise plans an owner adds it under Organization settings → Connectors. Free plans allow one custom connector.
Claude Code
claude mcp add --transport http peptide-library https://peptidelibrary.app/mcp
ChatGPT
Where your plan or workspace allows custom MCP servers: Plugins → + → Add custom MCP server → URL https://peptidelibrary.app/mcp, Authentication No authentication → Create as a plugin. Then type @ in a chat to use it. See examples/chatgpt.md.
Cursor
~/.cursor/mcp.json (or .cursor/mcp.json in a project): examples/cursor-mcp.json
{ "mcpServers": { "peptide-library": { "url": "https://peptidelibrary.app/mcp" } } }
VS Code
.vscode/mcp.json: examples/vscode-mcp.json
Cline
Cline → MCP Servers → Configure MCP Servers, then add the entry from llms-install.md
("type": "streamableHttp", "url": "https://peptidelibrary.app/mcp"). Agents installing the server can
follow that file directly.
Any MCP client
Streamable HTTP at https://peptidelibrary.app/mcp, no authentication. Generic config: examples/mcp.json.
MCP Inspector
npx -y @modelcontextprotocol/inspector --cli https://peptidelibrary.app/mcp --transport http --method tools/list
Example questions
- What does the research say about BPC-157, and how much of it is in humans?
- Compare semaglutide and tirzepatide: mechanism, evidence and regulatory status.
- Which peptides in the library are studied for cognition?
- What is the FDA and WADA status of bremelanotide (PT-141)?
- If 10 mg is dissolved in 2 mL, what is the concentration in mcg/mL?
Endpoint details
- Transport: Streamable HTTP (POST), stateless. Protocol revision 2026-07-28 and 2025-era clients (2024-11-05 to 2025-11-25).
- Authentication: none; every tool is read-only (
readOnlyHint: true). - Limits: about 300 requests per minute per IP, 64 KB per request, 25 results per page.
- Health check:
GET https://peptidelibrary.app/mcp/health.
Privacy
No account and no personal data. Peptide Library keeps daily counts of requests, tool calls, errors and the client name your assistant reports; it does not store tool arguments, results or IP addresses. The hosting provider processes IPs to apply rate limits. Full policy: https://peptidelibrary.app/privacy#mcp-server
Data
Profiles follow Peptide Library's editorial policy and methodology: claims cite PubMed, DOI, trial registries and FDA or WADA records, and evidence is labelled by kind.
REST API
The same research data (plus the vendor directory and prices, with a free key) is available as a REST API for apps and scripts: https://api.peptidelibrary.app/v1, with an OpenAPI 3.1 spec, Postman collection and TypeScript and Python SDKs. Docs: https://peptidelibrary.app/developers · Repo: https://github.com/ryandelauz/peptide-library-api
Links
- Website: https://peptidelibrary.app
- Developer API: https://peptidelibrary.app/developers
- iOS app: https://apps.apple.com/us/app/peptide-library-peptide-log/id6755092737
- Android app: https://play.google.com/store/apps/details?id=com.peptidelibrary.app
- Support: https://peptidelibrary.app/support · support@peptidelibrary.app
- Security: SECURITY.md
License
Documentation and examples in this repository: MIT. The hosted service and Peptide Library content are subject to the terms of service.
Questions fréquentes
Qu'est-ce que Peptide Library ?
Peptide research profiles, evidence by tier, comparisons and educational content. No dosing.
Comment installer Peptide Library ?
Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http peptide-library 'https://peptidelibrary.app/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour Peptide Library ?
Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.
Peptide Library est-il open source ?
Oui. Son code est sur GitHub sous licence MIT.
Qui maintient Peptide Library ?
Il est publié par ryandelauz. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.