Jacobian vs Random MCP

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

Jacobian logoJacobianData Science Tools · Local subprocess (stdio)Executable mathematics and independent verification for AI agents.49FairAuth: not declaredRandom MCP logoRandom MCPData Science Tools · Remote HTTP/SSEGenerate random values and probability distribution samples.36FairAuth: not declared

Verdict: choose Jacobian for data science tools work as a local process; choose Random MCP for data science tools over a hosted endpoint. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Jacobian logoChoose Jacobian when

  • You need dedicated capabilities in the Data Science Tools domain.
  • You prefer a local stdio subprocess transport.
Explore Jacobian

Random MCP logoChoose Random MCP when

  • You need dedicated capabilities in the Data Science Tools domain.
  • You prefer a remote HTTP/SSE transport.
  • You have the keys it needs: GITHUB_CLIENT_ID, GITHUB_CLIENT_SECRET, COOKIE_ENCRYPTION_KEY.
Explore Random MCP

Feature & specification comparison

Rows where the two servers differ are marked.

SpecJacobian logoJacobianRandom MCP logoRandom MCP
CategoryData Science ToolsData Science Tools
Quality signal49/100 · Fair36/100 · Fair
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Remote HTTP/SSE
AuthNot declaredNot declared
PricingNot declaredNot declared
Required env varsNone listedGITHUB_CLIENT_IDGITHUB_CLIENT_SECRETCOOKIE_ENCRYPTION_KEY
Verified ownerCommunity listingCommunity listing
GitHub stars3180
Directory activity 1 views 0 installs 0 upvotes 1 views 0 installs 0 upvotes
ToolsNot listedNot listed

Tools & capabilities

Jacobian tools

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

Random MCP 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.

Jacobian

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

Random MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "random-mcp": {
      "url": "https://random-mcp.eldesh-tools.workers.dev/mcp"
    }
  }
}

Frequently asked questions

Jacobian is categorized under Data Science Tools and uses a local stdio subprocess. Random MCP belongs to Data Science Tools and uses a remote HTTP/SSE transport. Pick Jacobian for data science tools work and Random MCP for data science tools.

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.

Jacobian has no declared pricing — check the project's own site. Random MCP has no declared pricing — check the project's own site. 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 jacobian and random-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Jacobian has a quality signal of 49/100 (Fair) with 1 views, 0 installs and 318 GitHub stars. Random MCP has 36/100 (Fair) with 1 views, 0 installs and 0 GitHub stars.