Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Studies and clinical trials for BPC-157, retatrutide, tirzepatide and 160+ peptides, with sources.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://pepbank.io/mcpRun this in your terminal
claude mcp add --transport http pepbank https://pepbank.io/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"pepbank": {
"url": "https://pepbank.io/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"pepbank": {
"type": "http",
"url": "https://pepbank.io/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://pepbank.io/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
resolve_peptideReturn peptide IDs and name matches for a name, alias or code. Use this before other calls when the name is unclear. Use search_peptides instead to browse or filter many peptides. Matching order: exact alias, normalized alias, trigram similarity, then edit distance. Normalization
get_peptide_briefFor a dose question, use studied_doses together with get_community_practice. Return a precomputed summary of one peptide: identity, sequence, checked findings by evidence class, trials, key findings with citations, coverage and notices. regulatory gives approval by place and use,
get_community_practiceReturn what community sources report about how people use one peptide: uses, regimens (route, amount, how often, how long), reported side effects, cautions and regulatory status notes such as US compounding policy, each line with its sources. Community-reported, not tested in tri
search_peptidesReturn peptides with identity and evidence counts. Use this to browse or filter by text, category, kind, evidence level, registry level or the curated launch list. Use resolve_peptide instead for one unclear name, or get_peptide_brief for one peptide summary. evidence_level comes
search_findingsReturn checked findings with exact total_count and source sentences in included.passages. Each finding is one claim from one paper. Use this for specific outcomes, with filters for peptide, evidence class, design, claim type, peptide role, direction, outcome group, body system an
search_publicationsReturn stored papers with citation identifiers and extraction status. Use this for paper discovery, publication dates or unchecked coverage. Use search_findings instead for checked claims and source sentences, or get_peptide_brief for a peptide overview. extraction_status identif
search_trialsReturn registered clinical trials with registry status, phase, posted-results status and peptide role. Use this for clinical development and trial records. Use search_findings instead for checked study results, or get_record for one full trial. The default role=tests lists and co
search_live_sourcesReturn live, unchecked papers from Europe PMC. Use this for gaps in database coverage or an explicit live literature search. Use search_publications instead for stored papers, or search_findings for checked claims. Live results have a separate unchecked label.
get_recordReturn one full peptide, publication, finding or trial record by PEP-, PUB-, FND- or TRL- ID. A peptide slug, PMID or NCT number also works. Use this for known records or fields omitted from compact results. Use resolve_peptide instead for an unclear name, or search_publications
get_evidence_mapReturn checked finding counts for one peptide by outcome group, evidence class and direction, plus year, design and safety counts. Use this to inspect evidence coverage and gaps. Use search_findings instead for individual claims and source sentences, or compare_peptides for sever
compare_peptidesReturn identity, evidence counts, outcome groups and top findings for 2 to 5 peptides, plus shared outcome groups. Use this for a comparison in one call. Use get_peptide_brief instead for a detailed summary of one peptide. The result compares evidence without ranking peptides as
get_changesReturn record change events in sequence order. Use this to synchronize data after since_seq, with 0 for full history. Without since_seq, the response gives the newest page. next_since_seq supplies the continuation position. Use get_freshness instead for source import times, or ge
replay_queryReturn a saved search at its original data_seq, with the first page and result_set_hash comparison. Use this to check whether a recorded query reproduces identical data. Use search_findings with as_of_seq instead for a new search at an earlier sequence, or get_record with as_of_s
get_freshnessReturn source import and extraction times from stored study results. Use this to inspect data freshness. Use get_changes instead for record events, or get_my_usage for caller quotas. lag_hours measures time since success, not upstream backlog. source_latest_known is not reported
get_my_usageReturn the caller's plan, grants, quotas and usage in the current windows. Use this to inspect access limits and remaining allowances. Use get_freshness instead for source import times, or get_changes for record updates. This tool reports account access, not evidence coverage.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain pepbank.io (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 1828 ms (HTTP 200)
No sign-in needed
Read 15 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.5.3) reached the registry yesterday.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Look up what studies found about more than 160 peptides, such as BPC-157, semaglutide and GHK-Cu. Each result links to its paper and says if it came from people, animals or cells.
PepBank MCP connects your AI to PepBank, a database of peptide research. Add it to Claude, ChatGPT, Cursor or another MCP app. Your AI can then find a peptide by name and read a summary of its evidence. It can also search study findings and clinical trials, and compare up to five peptides. Each finding links to the sentence in the paper that supports it and cites its PMID or DOI. Developer guide: pepbank.io/developers.
https://pepbank.io/mcp
Transport: Streamable HTTP. The server runs at this address. This repository holds its listing files. The server code is not in it.
Claude: open Customize, then Connectors. Select Add custom connector. Name it PepBank and enter https://pepbank.io/mcp.
ChatGPT: turn on Developer mode in Settings, under Security and login. Open Plugins and select +, then Add custom MCP server. Name it PepBank and enter https://pepbank.io/mcp.
Grok: open grok.com/connectors. Select New Connector, then Custom. Enter https://pepbank.io/mcp.
Claude Code:
claude mcp add --transport http pepbank https://pepbank.io/mcp
Codex (config.toml):
[mcp_servers.pepbank]
url = "https://pepbank.io/mcp"
Cursor (~/.cursor/mcp.json):
{ "mcpServers": { "pepbank": { "url": "https://pepbank.io/mcp" } } }
VS Code (.vscode/mcp.json):
{ "servers": { "pepbank": { "type": "http", "url": "https://pepbank.io/mcp" } } }
Gemini CLI (settings.json):
{ "mcpServers": { "pepbank": { "httpUrl": "https://pepbank.io/mcp" } } }
Other apps: add https://pepbank.io/mcp as a remote server with Streamable HTTP.
The pepbank package runs the same server over stdio for apps that need a local server, and answers from the terminal:
npx pepbank brief BPC-157
npx pepbank search tendon healing npx pepbank trials GHK-Cu
Local server config for MCP apps:
{ "mcpServers": { "pepbank": { "command": "npx", "args": ["-y", "pepbank"] } } }
| Tool | What it does |
|---|---|
resolve_peptide | Finds the peptide that a name, alias or code means |
get_peptide_brief | Reads the evidence summary for one peptide, with key findings, trials, studied doses and approval status |
get_community_practice | Reads what community sources report about how people use one peptide: uses, doses, side effects and cautions, each with its sources. Trials did not test these reports |
search_peptides | Lists peptides and filters them by name, category or evidence level |
search_findings | Searches study findings, with the source sentence and the PMID or DOI for each |
search_publications | Finds papers and shows which ones have checked findings |
search_trials | Finds registered clinical trials, with status, phase and posted results. The list view shows up to 100 trials per page |
search_live_sources | Searches Europe PMC for papers that PepBank does not cover yet. These results are not checked |
get_record | Reads one full peptide, paper, finding or trial record |
get_evidence_map | Counts the findings for one peptide by outcome, evidence class and direction |
compare_peptides | Compares the evidence for 2 to 5 peptides |
get_changes | Lists data changes since a data version |
replay_query | Runs a saved search again on the data version it first used |
get_freshness | Shows when each source was last imported |
get_my_usage | Shows your daily limits and how much of them you used |
| Name | Type | What it does |
|---|---|---|
evidence_summary | Prompt | Summarizes the evidence for one peptide, with sources and coverage limits |
compare_evidence | Prompt | Compares the evidence for 2 to 5 peptides |
pepbank://guide | Resource | Explains evidence classes, coverage, data versions, citations and limits |
This repository is also a plugin package that connects the server and adds one skill, skills/pepbank-peptide-research/SKILL.md.
plugin.json and mcp.json: Agent Plugins format (Hermes).claude-plugin/plugin.json and .mcp.json: Claude Code plugin format.cursor-plugin/plugin.json: Cursor plugin formatopenclaw.plugin.json: OpenClaw (ClawHub)Install the skill with the skills CLI:
npx skills add pepbank/peptide-research-mcp
PepBank data is under CC BY 4.0. When you show it, credit it as "Data from PepBank" with a link to pepbank.io. Each tool result gives a credit line to use. The files in this repository are under the MIT License.
io.pepbank/pepbankMira Labs LLC runs PepBank. This is not medical advice.