Skip to main content
Glama
apexapi

apexapi-mcp

Official
by apexapi
README.md
# apexapi-mcp

MCP server for [ApexApi](https://apexapi.dev) — call 120+ AI models (OpenAI, Anthropic, Google, DeepSeek, Qwen…) and read the live web (scrape / crawl / structured extract) from any MCP client, with one `ak-` API key and one prepaid balance.

## Tools

`chat`, `list_models`, `get_balance`, `scrape_page`, `crawl_site`, `extract_structured`, `check_job`, `generate_image`, `generate_speech`

## Local (stdio)

Get a key at https://apexapi.dev/keys, then add to your MCP client config:

```json
{
  "mcpServers": {
    "apexapi": {
      "command": "npx",
      "args": ["-y", "apexapi-mcp"],
      "env": { "APEXAPI_API_KEY": "ak-..." }
    }
  }
}
```

Claude Code: `claude mcp add apexapi -e APEXAPI_API_KEY=ak-... -- npx -y apexapi-mcp`

## Remote (Streamable HTTP)

Endpoint: `https://api.apexapi.dev/mcp` with header `Authorization: Bearer ak-...`

Responses use MCP Streamable HTTP framing (SSE) — clients like Claude Code handle this natively; it is not a plain-JSON REST endpoint.

Claude Code: `claude mcp add --transport http apexapi https://api.apexapi.dev/mcp --header "Authorization: Bearer ak-..."`

## Docs

https://apexapi.dev/docs/mcp

TDQS

A4/5.0

Scored across 9 tools

Disambiguation5/5

Each tool targets a distinct operation: balance, chat, model catalog, single-page scraping, site crawling, structured extraction, job polling, image generation, and speech generation. Even the web-scraping trio (scrape_page, crawl_site, extract_structured) is clearly differentiated by scope and output format.

Naming Consistency4/5

Most tools follow a clear verb_noun snake_case pattern (list_models, scrape_page, generate_image, etc.). The exception is 'chat,' which is just a verb and breaks the pattern slightly, though it is still readable.

Tool Count5/5

With 9 tools, the server covers a broad but well-defined API surface. Each tool serves a distinct function without redundancy, and the count is appropriate for an API aggregator.

Completeness4/5

The core workflows are covered: balance checking, model discovery, chat, web scraping (single and multi-page), structured data extraction, job polling, image and speech generation. Missing are minor conveniences like canceling or listing jobs, but agents can work around these.

Maintenance

ActivityInactive
ResponsivenessNo issues