mcpField
S
settlegrid-discovery

settlegrid-discovery

Local
github.com/lexwhitingDeveloper Tools1Updated 4d ago

About settlegrid-discovery

@settlegrid/discovery is an MCP server for AI agents that need to find monetized tools listed on the SettleGrid marketplace. It supports searching and browsing categories, tool details, pricing, and developer profiles.

Key features

  1. 01Search tools by text and category
  2. 02Get details by tool slug
  3. 03List categories and counts
  4. 04View developer profiles and tools

Use cases

  1. 01Find marketplace tools matching a query
  2. 02Check a tool’s pricing and methods
  3. 03Browse tools by category
  4. 04Inspect a developer’s published tools

MCP support

It exposes marketplace discovery tools to MCP clients, including search, tool details, category listings, and developer profiles. Configure the SettleGrid API base URL with SETTLEGRID_API_URL.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"lexwhiting-settlegrid-discovery": {
"command": "npx",
"args": [
"-y",
"@settlegrid/discovery"
],
"env": {
"SETTLEGRID_API_URL": "<SETTLEGRID_API_URL>"
}
}
}
}
Run commandnpx -y @settlegrid/discovery
Environment variables to set
SETTLEGRID_API_URLSettleGrid API base URL (default: https://settlegrid.ai)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@settlegrid/discovery1.0.1

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
limitintegerNoMaximum number of results to return (1-100, default 20)
querystringNoFree-text search query
categorystringNoFilter by tool category (e.g. finance, weather, ai)

Details

From the project README

@settlegrid/discovery

An MCP (Model Context Protocol) server that lets AI agents discover monetized tools on the SettleGrid marketplace. Instead of hard-coding tool URLs or relying on third-party directories, agents connect to this server and search, browse, and inspect tools programmatically — making SettleGrid the canonical discovery layer for the AI economy.

Quick start

With npx (no install)
npx @settlegrid/discovery
Install globally
npm install -g @settlegrid/discovery
settlegrid-discovery
From source (this repo)
cd packages/discovery-server
npm install
npm run dev    # tsx, auto-reloads
npm run build  # compile to dist/
npm start      # run compiled output

Configuration

VariableDefaultDescription
SETTLEGRID_API_URLhttps://settlegrid.aiBase URL of the SettleGrid API

Available tools

search_tools

Search for monetized AI tools on the marketplace.

ParameterTypeRequiredDescription
querystringnoFree-text search query
categorystringnoFilter by category
limitnumbernoMax results, 1-100 (default 20)

Returns an array of { name, slug, description, category, pricing, version, url }.

get_tool

Get full details for a specific tool by slug.

ParameterTypeRequiredDescription
slugstringyesTool slug identifier

Returns { name, slug, description, category, pricing, version, methods, quickStart, url }.

list_categories

List every tool category with counts. No parameters.

Returns an array of { name, count }.

get_developer

Get a developer's public profile and their published tools.

ParameterTypeRequiredDescription
slugstringyesDeveloper profile slug

Returns { name, bio, tools[], reputation }.

Add to Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "settlegrid-discovery": {
      "command": "npx",
      "args": ["-y", "@settlegrid/discovery"]
    }
  }
}

To point at a local or staging API:

{
  "mcpServers": {
    "settlegrid-discovery": {
      "command": "npx",
      "args": ["-y", "@settlegrid/discovery"],
      "env": {
        "SETTLEGRID_API_URL": "http://localhost:3005"
      }
    }
  }
}

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.