Pubcrawl vs Mirobody

A side-by-side look at the Pubcrawl and Mirobody MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Pubcrawl logoPubcrawlBiology & Bioinformatics · Local subprocess (stdio)PubMed literature search and US/UK drug labelling for AI assistants.49FairAuth: no auth requiredMirobody logoMirobodyBiology & BioinformaticsTurn scattered health data into answers you can trace. Self-hosted AI health data engine for lab reports, wearables and genetics, with a built-in MCP server. Run it with Docker and one LLM key, or keep every model local on llama.cpp.51GoodAuth: not declared

Verdict: choose Pubcrawl for biology & bioinformatics work as a local process; choose Mirobody for biology & bioinformatics. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Pubcrawl logoChoose Pubcrawl when

  • You need dedicated capabilities in the Biology & Bioinformatics domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: No auth required.
Explore Pubcrawl

Mirobody logoChoose Mirobody when

  • You need dedicated capabilities in the Biology & Bioinformatics domain.
Explore Mirobody

Feature & specification comparison

Rows where the two servers differ are marked.

SpecPubcrawl logoPubcrawlMirobody logoMirobody
CategoryBiology & BioinformaticsBiology & Bioinformatics
Quality signal49/100 · Fair51/100 · Good
Install commandConfirmedNot confirmed yet
TransportLocal subprocess (stdio)—
AuthNo auth requiredNot declared
PricingFreeBYOK (pay the provider)
Required env varsNone listedNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars151,388
Directory activity 4 views 0 installs 0 upvotes 2 views 0 installs 0 upvotes
ToolsNot listedNot listed

Tools & capabilities

Pubcrawl tools

No tool names declared yet. Check the project README from the listing page.

Mirobody 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.

Pubcrawl

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "pubcrawl": {
      "command": "npx",
      "args": [
        "-y",
        "@pharmatools/pubcrawl"
      ]
    }
  }
}

Mirobody

No confirmed install command for Mirobody yet — follow the setup steps linked from its listing page rather than a guessed package name.

Frequently asked questions

Pubcrawl is categorized under Biology & Bioinformatics and uses a local stdio subprocess. Mirobody belongs to Biology & Bioinformatics and uses an install path we have not confirmed yet. Pick Pubcrawl for biology & bioinformatics work and Mirobody 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. Mirobody has no confirmed install command yet — follow its own setup instructions.

Pubcrawl is listed as free. Auth: no auth required. Mirobody is bring-your-own-key: usage is billed by the API provider you supply a key for. 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 pubcrawl and mirobody as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Pubcrawl has a quality signal of 49/100 (Fair) with 4 views, 0 installs and 15 GitHub stars. Mirobody has 51/100 (Good) with 2 views, 0 installs and 1,388 GitHub stars.