Walmart Connect Advertising APIs

<!-- mcp-name: io.github.alyiox/mcp-walmart-ads -->

MCP server for Walmart Connect Ads APIs — Sponsored Search and Display.

Exposes spec-driven discovery (list_endpoints, describe_endpoint), a generic API proxy (call_endpoint), a runtime spec refresher (refresh_specs), and a display-snapshot downloader (download_display_snapshot). The AI agent discovers endpoints from bundled OpenAPI specs then calls them; the server handles RSA-SHA256 signing and auth headers automatically.

Features

• Spec-driven discovery — list/describe endpoints from bundled OpenAPI specs, refreshable at runtime
• Any endpoint — call by operation id or raw method+path (raw path reaches unpublished endpoints); no code changes when APIs evolve
• Supports both Sponsored Search and Display API families
• Multi-region, multi-environment (production + staging) via config file
• Per-request RSA-SHA256 signing with automatic header construction
• Large responses truncated with full data available via MCP resource URI
• Bundled OpenAPI specs (refreshable at runtime) give the agent endpoint schemas on demand

Requirements

• Python 3.13+
• Walmart Connect Partner Network credentials (consumer ID, RSA key pair, bearer token)

Quick start

Set up your config (see Configuration), then run the server:

# Run directly with uvx (no clone needed)
npx -y @modelcontextprotocol/inspector uvx mcp-walmart-ads

# Or run from source
git clone https://github.com/alyiox/mcp-walmart-ads.git
cd mcp-walmart-ads
uv sync
npx -y @modelcontextprotocol/inspector uv run mcp-walmart-ads

Configuration

The config file lives under your home directory at ~/.config/mcp-walmart-ads/config.json.

Windows note: ~ maps to %USERPROFILE% (typically C:\Users\<you>), so the full path is %USERPROFILE%\.config\mcp-walmart-ads\config.json.

1. Create the config directory and copy the example

# Unix-like (macOS, Linux, WSL, …)
mkdir -p ~/.config/mcp-walmart-ads/keys/us
cp config.example.json ~/.config/mcp-walmart-ads/config.json

# Windows (PowerShell)
New-Item -ItemType Directory -Force "$env:USERPROFILE\.config\mcp-walmart-ads\keys\us"
Copy-Item config.example.json "$env:USERPROFILE\.config\mcp-walmart-ads\config.json"

2. Edit `~/.config/mcp-walmart-ads/config.json`

{
  "response_cache_ttl": 3600,
  "truncate_threshold": 51200,
  "regions": {
    "US": {
      "production": {
        "consumer_id": "your-consumer-id",
        "private_key": "./keys/us/prod.pem",
        "private_key_version": "1",
        "bearer_token": "your-bearer-token",
        "base_urls": {
          "search": "https://developer.api.walmart.com/api-proxy/service/WPA/Api/v1",
          "display": "https://developer.api.walmart.com/api-proxy/service/display/api/v1"
        }
      },
      "staging": {
        "consumer_id": "your-staging-consumer-id",
        "private_key": "./keys/us/staging.pem",
        "private_key_version": "1",
        "bearer_token": "your-staging-bearer-token",
        "base_urls": {
          "search": "https://developer.api.stg.walmart.com/api-proxy/service/WPA/Api/v1",
          "display": "https://developer.api.us.stg.walmart.com/api-proxy/service/display/api/v1"
        }
      }
    }
  }
}

3. Place your RSA private key PEM files in `~/.config/mcp-walmart-ads/keys/`

Key paths in the config are resolved relative to the config directory, so ./keys/us/prod.pem resolves to ~/.config/mcp-walmart-ads/keys/us/prod.pem.

Tools

list_endpoints

List operations from the bundled OpenAPI spec for an ad_type, with optional filters.

describe_endpoint

Return one operation plus the components.schemas reachable from it (its $ref closure), so request bodies and responses can be built without the full spec.

call_endpoint

Execute any Walmart Connect Ads API endpoint. Identify it by operation_id, or by raw method + path. Raw method+path also reaches alpha/beta/unpublished endpoints that are not in the bundled specs. The server handles RSA-SHA256 signing.

\* Provide either operation_id, or both method and path.

refresh_specs

Re-fetch the bundled OpenAPI specs from ReadMe's public api-registry into a user cache (~/.cache/mcp-walmart-ads/specs/) that takes precedence over the bundled copy.

download_display_snapshot

Download a display snapshot file (report or entity). Display snapshot URLs require authenticated requests, so this tool handles the signing automatically. Use it with the snapshot ID from the details field after polling a display snapshot to done status.

MCP resources

Endpoint schemas come from the bundled OpenAPI specs via list_endpoints / describe_endpoint (see Tools), not from static resources.

Dynamic resources

MCP host examples

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "walmart-ads": {
      "command": "uvx",
      "args": ["mcp-walmart-ads"]
    }
  }
}

Claude Code

Add to your Claude Code MCP config:

{
  "mcpServers": {
    "walmart-ads": {
      "command": "uvx",
      "args": ["mcp-walmart-ads"]
    }
  }
}

Codex

[mcp_servers.walmart-ads]
command = "uvx"
args = ["mcp-walmart-ads"]

OpenCode

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "walmart-ads": {
      "type": "local",
      "enabled": true,
      "command": ["uvx", "mcp-walmart-ads"]
    }
  }
}

GitHub Copilot

{
  "inputs": [],
  "servers": {
    "walmart-ads": {
      "type": "stdio",
      "command": "uvx",
      "args": ["mcp-walmart-ads"]
    }
  }
}

Development

uv sync --group dev    # install deps
uv run pytest          # run tests
uv run ruff check .    # lint
uv run ruff format .   # format
uv run pyright         # type check

Contributing

Open issues or PRs. Follow existing style and add tests where appropriate.

License

MIT. See LICENSE.