SanYu Research Engine vs io.github.nickjlamb/pubcrawl
SanYu Research Engine is an MCP server published by kfx2026. Marketplaces we read that list it: 1 (Official MCP Registry). io.github.nickjlamb/pubcrawl is an MCP server published by nickjlamb. Marketplaces we read that list it: 2 (Official MCP Registry, npm registry (MCP servers)). As of our marketplace pass on 2026-11-09. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace | ||
|---|---|---|
| Official MCP Registry | Listed Version: 1.2.0 Forks (GitHub): 0 Stars (GitHub): 0 Not marked · First seen |
Listed Version: 2.8.0 Downloads/month (npm): 485 Downloads/week (npm): 113 Forks (GitHub): 3 Stars (GitHub): 15 Not marked · First seen |
| npm registry (MCP servers) | Not listed | Listed Version: 2.8.0 Downloads/month (npm): 485 Downloads/week (npm): 113 Forks (GitHub): 3 Stars (GitHub): 15 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | SanYu Research Engine | io.github.nickjlamb/pubcrawl |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 2 (better) |
| Stars (GitHub) (differs) | 0 (worse) | 15 (better) |
| Forks (GitHub) (differs) | 0 (worse) | 3 (better) |
| Last release (differs) | 2026-11-08 (better) | 2026-11-03 (worse) |
| Where it runs (differs) | Remote server (sanyu.wentangkeji.com/api/mcp) | On your machine (@pharmatools/pubcrawl) |
| Transport (differs) | Streamable HTTP | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 1, secrets among them: 1 |
| Licence (differs) | Not stated | MIT |
| Repository (differs) | github.com/kfx2026/sanyu-research-mcp | github.com/nickjlamb/pubcrawl |
| Changes in the last 7 days (differs) | 6 | 2 |
| First seen (differs) | 2026-11-06 | 2026-10-11 |
| Endpoint at the last check (differs) | Status out of date: last check 30 h ago returned HTTP 200 | no remote endpoint we check |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
SanYu Research Engine
145 tools: 106 deterministic engines (stats, survival, bioinfo, primers) + 39 AI writers.
io.github.nickjlamb/pubcrawl
PubMed & Europe PMC literature search, US/UK drug labelling, and clinical trials for AI assistants.
How to run each
SanYu Research Engine As a remote MCP server
claude mcp add --transport http sanyu-research https://sanyu.wentangkeji.com/api/mcp
io.github.nickjlamb/pubcrawl As a local MCP server: npm package
claude mcp add --env "NCBI_API_KEY=<YOUR_NCBI_API_KEY>" --transport stdio pubcrawl -- npx -y @pharmatools/pubcrawl
Requires: NCBI_API_KEY (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only SanYu Research Engine has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of SanYu Research Engine publish no settings it asks for, so we do not compare settings.
What it can do: SanYu Research Engine · What it can do: io.github.nickjlamb/pubcrawl · Compare two other plugins
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Package data comes from the public npm registry (registry.npmjs.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.