Curo Peptide Research MCP
# Curo Peptide Research MCP: PepBank Studies, Peptide Lookup and Lab Reports (COAs)
[](https://lobehub.com/mcp/curo-you-peptides-peptide-research-mcp)
[](https://glama.ai/mcp/connectors/you.curo/peptide-research)
[](https://skills.sh/curo-you-peptides/peptide-research-mcp)
Peptide research for your AI: PepBank study findings plus the curo.you peptide catalog and lot COAs.
Curo MCP connects your AI to peptide research and to Curo (https://curo.you). Add it to Claude, ChatGPT, Gemini, Grok, Perplexity or another MCP app. Your AI can then answer peptide questions from PepBank (https://pepbank.io), a free peptide research database, with study summaries, findings and a link to each source. It can also look up peptides in the Curo catalog (https://curo.you/product-catalog), with the third-party lab report for each lot (https://curo.you/coa), prices, stock and shipping. Server address: https://mcp.curo.you. Setup guide: https://curo.you/mcp.
## Server address
```
https://mcp.curo.you
```
Transport: Streamable HTTP. The server runs at this address. `https://mcp.curo.you/mcp` reaches the same server. This repository holds its listing files.
## Add it to your AI app
Claude: open Customize, then Connectors. Select Add custom connector. Name it Curo and enter `https://mcp.curo.you`.
ChatGPT: open Plugins. Select +, then Add custom MCP server. Name it Curo and enter `https://mcp.curo.you`.
Claude Code:
```
claude mcp add --transport http curo https://mcp.curo.you
```
Codex (`config.toml`):
```toml
[mcp_servers.curo]
url = "https://mcp.curo.you"
```
Gemini CLI (`settings.json`):
```json
{ "mcpServers": { "curo": { "httpUrl": "https://mcp.curo.you" } } }
```
Steps for Gemini, Grok, Perplexity, Muse and other apps: https://curo.you/mcp
## Command line and local server (npm)
The `curo-peptides` package runs the same server over stdio for apps that need a local server, and answers from the terminal:
```
npx curo-peptides research BPC-157
npx curo-peptides search tendon healing
npx curo-peptides products
npx curo-peptides coa <lot number>
```
Local server config for MCP apps:
```json
{ "mcpServers": { "curo": { "command": "npx", "args": ["-y", "curo-peptides"] } } }
```
## Tools
| Tool | What it does |
|---|---|
| `peptide_research` | Reads the PepBank summary, main findings, sources and credit for one peptide |
| `search_research` | Searches PepBank study findings, with sources and credit for each result |
| `search_products` | Finds Curo products by name, or lists all products |
| `get_product` | Reads product variants, prices, stock and lot reports |
| `get_coa` | Reads the lab reports for a lot number or a product |
| `get_store_info` | Reads shipping, returns, contact and research-use policies |
| `build_cart` | Makes a cart link. You check out and pay on curo.you |
## Prompts and resources
| Name | Type | What it does |
|---|---|---|
| `research_peptide` | Prompt | Asks what the research says about one peptide |
| `lab_report` | Prompt | Asks for the lab report (COA) of one lot |
| `curo://store-info` | Resource | Shipping, returns, contact and research-use policies |
## Plugin package
This repository is also a plugin package that connects the server and adds one skill, `skills/curo-peptide-research/SKILL.md`.
- `plugin.json` and `mcp.json`: Agent Plugins format (Hermes Agent)
- `.claude-plugin/plugin.json` and `.mcp.json`: Claude Code plugin format
- `.cursor-plugin/plugin.json`: Cursor plugin format
- `openclaw.plugin.json`: OpenClaw (ClawHub)
Install the skill with the `skills` CLI:
```
npx skills add curo-you-peptides/peptide-research-mcp
```
## Questions to try
- What does the research say about TB-500?
- Show me the lab report for my lot number.
- Which Curo peptides are in stock right now?
- How long does shipping take?
## Links
- Curo: https://curo.you
- Peptide catalog: https://curo.you/product-catalog
- Lab reports (COAs): https://curo.you/coa
- PepBank: https://pepbank.io
- Official MCP Registry entry: [`you.curo/peptide-research`](https://registry.modelcontextprotocol.io/?q=you.curo)
Curo products are for laboratory research use only. Nothing here is medical advice.
TDQS
Scored across 7 tools
Each tool targets a distinct resource+action, and the descriptions actively route the agent (search_products → get_product → get_coa, peptide_research vs search_research). The only real overlap is that get_product embeds per-lot COA data while get_coa fetches reports by lot number, so an agent could plausibly pick either for a testing question; the descriptions mitigate this by telling you to use get_coa when a lot number is given.
Six of seven names follow a clear verb_noun pattern (get_store_info, search_products, get_product, build_cart, get_coa, search_research). peptide_research is the lone noun-first outlier, a minor deviation that is still readable and semantically sensible.
Seven tools is well-scoped for a storefront-plus-research server: two discovery tools, two detail tools, one cart tool, one policy tool and one research lookup. Nothing looks redundant or padded, and no obvious capability is missing a tool slot.
The surface covers the full browse→inspect→verify→buy path plus policy and research lookups, with no dead ends for the stated scope (it explicitly does not place orders or take payment). Minor gaps: there is no direct lookup of a product by name without search_products, no way to list or search COAs without a lot/product, and no order-status or shipping-cost estimate.