Skip to main content
Glama
Sign In
apexapi-mcp

apexapi-mcp

Official
by apexapi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

apexapi-mcp

MCP server for ApexApi — 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

Related MCP server: Korpi API MCP server

Local (stdio)

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

{
  "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

Available Tools

9 tools
chatAsk an AI modelA

Send a prompt to any of the 120+ models on ApexApi (OpenAI, Anthropic, Google, DeepSeek, Qwen, Mistral…). Use list_models to discover model slugs. Billed per token from the credit balance.

Inputs: model (required), prompt (required), system, max_tokens, +1 more.

check_jobCheck an async jobB

Poll a crawl_site or extract_structured job by id.

Inputs: id (required), kind (required).

crawl_siteRead a whole siteA

Crawl same-domain pages from a seed URL into markdown. Waits up to 60s; if still running, returns a job id for check_job. Billed $0.005 per page, capped by limit. Full page set is at result_url.

Inputs: url (required), limit.

extract_structuredExtract structured dataA

Ready-made structured JSON from Amazon, Walmart, Crunchbase, G2, Google Maps, or Zillow product/company/listing URLs. Billed $0.01 per record; failures free. Scrapers: amazon-product, walmart-product, crunchbase-company, g2-product, google-maps-business, zillow-property.

Inputs: url (required), scraper (required), limit.

generate_imageGenerate an imageA

Generate an image from a text prompt. Returns a URL. Use list_models with type=image for available models and prices.

Inputs: model (required), prompt (required), size.

generate_speechGenerate speech (TTS)A

Text-to-speech via ElevenLabs. Returns an MP3 URL. Billed per 1,000 characters.

Inputs: input (required), model, voice.

get_balanceGet credit balanceA

Current prepaid credit balance in USD. Balance is the only usage limit on ApexApi.

Inputs: no named parameters.

list_modelsList available modelsA

Live catalog of all ApexApi models with type, context window, and USD pricing (per 1M tokens for chat). Filter by type to keep the list short.

Inputs: type.

scrape_pageRead a web pageA

Fetch any URL as clean, LLM-ready markdown (or html/text). Anti-bot handling is automatic. Billed per successful page ($0.002 standard, $0.008 stealth); failures are free.

Inputs: url (required), format.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    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 recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers