Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/josefdc/Uniprot-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/josefdc/uniprot-mcp/uniprot-mcp)<a href="https://agentmods.dev/mcp/josefdc/uniprot-mcp/uniprot-mcp"><img src="https://agentmods.dev/badge/mcp/josefdc/uniprot-mcp/uniprot-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/josefdc/uniprot-mcp/uniprot-mcp"><img src="https://agentmods.dev/badge/mcp/josefdc/uniprot-mcp/uniprot-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
uniprot-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- uniprot-mcp — 100% identical, 0 lines differ
What it actually says
{
"uniprot-mcp": {
"command": "uvx",
"args": [
"uniprot-mcp"
],
"env": {}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 9 lines scan A 43fdf56ef0dc
uniprot-mcp is an MCP server published in the GitHub repository josefdc/Uniprot-MCP (2 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
uniprot
UniProt MCP — protein sequence + function database. Remote server at gateway.pipeworx.io.
github-tool
Commandline search tool for github. Runs locally from the github-tool Python package.
github-actions-mcp-server
MCP server "github-actions-mcp-server" as configured in onemarc/github-actions-mcp-server. Runs locally from the github-actions-mcp-server npm package.
uniprot-mcp
Model Context Protocol server that surfaces UniProtKB data as MCP resources, tools, and prompts. Runs locally from the uniprot-mcp Python package.
strata
MCP server for progressive tool usage at any scale (see https://klavis.ai). Remote server at strata.klavis.ai.
solana-mcp-vybe
MCP server "solana-mcp-vybe", hosted remotely at mcp.vybenetwork.xyz, as configured in vybenetwork/solana-mcp-vybe.