Sapiom MCP Server

Một khóa API cho phép các tác nhân truy cập vào hơn 80 công cụ: tìm kiếm web, tìm kiếm sâu, tự động hóa trình duyệt, chụp ảnh màn hình, hơn 400 mô hình LLM, tạo hình ảnh, chuyển văn bản thành giọng nói, hiệu ứng âm thanh và xác minh điện thoại. Thanh toán theo mức sử dụng với cơ chế quản lý chi tiêu tích hợp sẵn.

Tài liệu

Sapiom

All You Need

MCP ServerSkill

$claude mcp add sapiom -- npx -y @sapiom/mcp

sapiom-prompt

Scan every AI paper published this week, build a knowledge graph of how they connect, and deploy a searchable interface my team can explore visually.

Instant access to 20+ paid services with pay-per-use pricing. No vendor account setup required.

Two ways in

Sapiom ships two MCP servers, for two jobs — plus a plain SDK:

  • Authoring MCP (@sapiom/mcp, local via npx) — build, test & deploy workflows. Inside a step, capabilities are called via the typed ctx.sapiom.* client.
  • Remote MCP (https://api.sapiom.ai/v1/mcp) — call any capability directly as an sapiom_* tool, no workflow needed.
  • SDK (@sapiom/axios / @sapiom/fetch) — wrap your HTTP client and hit the gateways from code.

Rule of thumb: authoring MCP for anything multi-step, scheduled, or deployable; remote MCP (or the SDK) for a one-off call.

Authoring MCP — build workflows

Connect your AI coding agent to the Sapiom authoring MCP (@sapiom/mcp):

Claude Code:


claude mcp add sapiom -- npx -y @sapiom/mcp


Other clients (Cursor, Windsurf, etc.):


{

  "mcpServers": {

    "sapiom": {

      "command": "npx",

      "args": ["-y", "@sapiom/mcp"]

    }

  }

}


Sign in once with the sapiom_authenticate tool — it opens a browser to approve access, then caches your key in ~/.sapiom/credentials.json for every subsequent call. No API key to paste.

Remote MCP — call capabilities directly

Connect to the hosted remote MCP to call any capability as a direct sapiom_* tool:

Claude Code:


claude mcp add sapiom --transport http https://api.sapiom.ai/v1/mcp



{

    "sapiom": {

      "transport": "http",

      "url": "https://api.sapiom.ai/v1/mcp"

    }

  }

}


If your platform requires explicit auth, add --header "x-api-key: YOUR_API_KEY" (CLI) or a "headers": { "x-api-key": "YOUR_API_KEY" } block (JSON). Get a key at app.sapiom.ai/settings.

What You Can Do — direct tool calls (remote MCP)

These sapiom_* tools are exposed by the remote MCP for one-off, direct calls. Inside a workflow, call the same capabilities via ctx.sapiom.* — see Workflows.

CategoryExamples
SearchWeb search with AI answers (Linkup), web + news results (You.com)
BrowserFetch page content as markdown, capture screenshots
AudioText-to-speech, sound effects, voice listing
AI ModelsChat with LLMs (GPT-4o, Claude, etc.), list models and pricing
ImageGenerate images from text (FLUX Schnell/Dev/Pro)
VerifySMS verification (send + check codes)
GovernanceAgent registration, spending rules, scoped API keys

Use tool_discover (remote MCP) to find the right tools for your task — describe a goal and get ranked recommendations with examples.

Recipes

Chain remote-MCP tools for common one-off tasks:

Research Report

sapiom_searchsapiom_deep_searchsapiom_chat

Search both Linkup and You.com for broad source coverage, then synthesize findings into a structured report using an LLM. Use depth: "deep" on sapiom_search for thorough coverage of complex topics.

Visual Website Audit

sapiom_screenshotsapiom_chatsapiom_generate_image

Capture a screenshot of a live website, analyze the design and UX with an LLM, then generate a mockup image of proposed improvements.

Podcast Episode

sapiom_searchsapiom_chatsapiom_text_to_speech

Research a topic with web search, write a podcast script with an LLM, then convert to audio. Use sapiom_list_voices to pick a voice. Split scripts over ~400 words into chunks.

Governed Agent Workflow

sapiom_create_agentsapiom_create_spending_rulesapiom_create_transaction_api_key

Register a named agent, set spending limits (e.g., $100/day rolling cap), and create a scoped API key for autonomous operation. Use agentName on subsequent tool calls for spend tracking.

Competitor Intelligence

sapiom_fetchsapiom_deep_searchsapiom_chatsapiom_generate_image

Extract content from a competitor’s website, search for recent news and coverage, synthesize an analysis with an LLM, and generate a comparison infographic.

Tips

  • Start with tool_discover — it recommends tools based on your objective and returns usage examples
  • Use agentName on tool calls to track spend per agent and enforce spending rules
  • Free endpointssapiom_status, sapiom_list_voices, and sapiom_list_models cost nothing
  • Combine search providerssapiom_search (Linkup) and sapiom_deep_search (You.com) use different indexes for broader coverage
  • Spending rules — use sapiom_create_spending_rule to cap costs by amount, count, or time window

SDK Access (Direct HTTP)

For programmatic access without MCP, use the Node.js SDK:


import { withSapiom } from "@sapiom/axios";

import axios from "axios";


const client = withSapiom(axios.create(), {

  apiKey: process.env.SAPIOM_API_KEY,

});


const { data } = await client.post(

  "https://linkup.services.sapiom.ai/v1/search",

  { query: "quantum computing", depth: "standard", outputType: "sourcedAnswer" }

);



npm install @sapiom/axios axios


Python and other languages: use any HTTP client with Authorization: Bearer sk_... header against gateway URLs.

Documentation

Fetch any doc as markdown by adding .md to the URL.

TopicURL
Searchhttps://docs.sapiom.ai/capabilities/search.md
AI Modelshttps://docs.sapiom.ai/capabilities/ai-models.md
Browserhttps://docs.sapiom.ai/capabilities/browser.md
Audiohttps://docs.sapiom.ai/capabilities/audio.md
Imageshttps://docs.sapiom.ai/capabilities/images.md
Verifyhttps://docs.sapiom.ai/capabilities/verify.md
Authoring MCPhttps://docs.sapiom.ai/integration/mcp-servers/setup.md
Remote MCPhttps://docs.sapiom.ai/integration/mcp-servers/remote.md
Workflows Quickstarthttps://docs.sapiom.ai/workflows/quick-start.md
Pricinghttps://docs.sapiom.ai/pricing.md