Protein Atlas vs Togomcp
A side-by-side look at the Protein Atlas and Togomcp MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
T
TogomcpBiology & BioinformaticsMCP server for life-science knowledge graphs36FairAuth: api key requiredVerdict: choose Protein Atlas for biology & bioinformatics work as a local process; choose Togomcp for biology & bioinformatics. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Protein Atlas when
- You need dedicated capabilities in the Biology & Bioinformatics domain.
- You prefer a local stdio subprocess transport.
- You want tools like
search_genes, get_protein, top_tissues.
TChoose Togomcp when
- You need dedicated capabilities in the Biology & Bioinformatics domain.
- Its auth model fits you: API key required.
- You have the keys it needs:
NCBI_API_KEY.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | T Togomcp | |
|---|---|---|
| Category | Biology & Bioinformatics | Biology & Bioinformatics |
| Quality signal | 51/100 · Good | 36/100 · Fair |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | Not declared | API key required |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | NCBI_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 19 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 3 | Not listed |
| Full listing | View Protein Atlas | View Togomcp |
Tools & capabilities
Protein Atlas tools 3
search_genesSearch the Human Protein Atlas for human genes/proteins by gene symbol or keyword. Returns each gene with its Ensembl gene id (needed by get_protein and top_tissues), synonyms, and description. Keyless.get_proteinGet a trimmed Human Protein Atlas profile for one protein by Ensembl gene id (e.g. "ENSG00000146648"): gene, description, protein class, biological process, molecular function, RNA tissue specificity/distribution, subcellular location, and disease involvement. Use search_genes to find the Ensembl i…top_tissuesList a protein's top-expressing human tissues by RNA expression (nTPM), highest first, for one Ensembl gene id. Use search_genes to find the Ensembl id. Keyless.
Togomcp tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Protein Atlas
{
"mcpServers": {
"protein-atlas": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-protein-atlas"
]
}
}
}
Togomcp
No confirmed install command for Togomcp yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
Protein Atlas is categorized under Biology & Bioinformatics and uses a local stdio subprocess. Togomcp belongs to Biology & Bioinformatics and uses an install path we have not confirmed yet. Pick Protein Atlas for biology & bioinformatics work and Togomcp for biology & bioinformatics.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Togomcp has no confirmed install command yet — follow its own setup instructions.
Protein Atlas has no declared pricing — check the project's own site. Togomcp has no declared pricing — check the project's own site. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add protein-atlas and togomcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Protein Atlas has a quality signal of 51/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Togomcp has 36/100 (Fair) with 0 views, 0 installs and 19 GitHub stars.