Tokentrust vs Server Everything

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

Tokentrust logoTokentrustConversational AI · Local subprocess (stdio)Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.44FairAuth: not declaredServer Everything logoServer EverythingOther Tools and Integrations · Local subprocess (stdio)MCP server that exercises all the features of the MCP protocol55GoodAuth: no auth required

Verdict: choose Tokentrust for conversational ai work as a local process; choose Server Everything for other tools and integrations as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Tokentrust logoChoose Tokentrust when

  • You need dedicated capabilities in the Conversational AI domain.
  • You prefer a local stdio subprocess transport.
Explore Tokentrust

Server Everything logoChoose Server Everything when

  • You need dedicated capabilities in the Other Tools and Integrations domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: No auth required.
Explore Server Everything

Feature & specification comparison

Rows where the two servers differ are marked.

SpecTokentrust logoTokentrustServer Everything logoServer Everything
CategoryConversational AIOther Tools and Integrations
Quality signal44/100 · Fair55/100 · Good
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthNot declaredNo auth required
PricingNot declaredFree
Required env varsNone listedNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars091,486
Directory activity 4 views 0 installs 0 upvotes 9 views 0 installs 0 upvotes
ToolsNot listedNot listed

Tools & capabilities

Tokentrust tools

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

Server Everything 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.

Tokentrust

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "tokentrust": {
      "command": "npx",
      "args": [
        "-y",
        "tokentrust-cli"
      ]
    }
  }
}

Server Everything

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

Frequently asked questions

Tokentrust is categorized under Conversational AI and uses a local stdio subprocess. Server Everything belongs to Other Tools and Integrations and uses a local stdio subprocess. Pick Tokentrust for conversational ai work and Server Everything for other tools and integrations.

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.

Tokentrust has no declared pricing — check the project's own site. Server Everything is listed as free. Auth: no auth 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 tokentrust and modelcontextprotocol-server-everything as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Tokentrust has a quality signal of 44/100 (Fair) with 4 views, 0 installs and 0 GitHub stars. Server Everything has 55/100 (Good) with 9 views, 0 installs and 91,486 GitHub stars.