Skip to main content The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench Explore Tool Discovery
Live 39 Actions

Alchemy MCP Server
for AI Agents

Connect your AI agent to StackOne's Alchemy MCP server and give it 39 MCP tools out of the box. Auth, tool execution, and security all managed.

Alchemy logo
Alchemy MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

39 Agent Actions

Create, read, update, and delete across Alchemy — and extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Alchemy MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Alchemy tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Alchemy call.

Tools Discovery →

What is the Alchemy MCP Server?

A Alchemy MCP server lets AI agents read and write Alchemy data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Alchemy MCP server ships with 39 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Alchemy MCP Tools

Every action from Alchemy's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Contract Metadatas

  • Get Contract Metadata

    Retrieve collection-level metadata (name, symbol, total supply, OpenSea data) for a single NFT contract.

  • Search Contract Metadata

    Search for NFT contracts by keyword across all ERC-721 and ERC-1155 contract metadata (name, symbol, description).

Transaction Receipts

  • Get Transaction Receipt

    Get the transaction receipt (status, gas used, logs, block hash) for a single transaction hash.

  • Get Transaction Receipts

    Batch-fetch all transaction receipts for an entire block in a single call, identified by block number or block hash.

Other (35)

  • Get NFTs For Owner

    Retrieve all NFTs currently owned by a specified wallet address on the selected EVM network, with optional metadata and spam/airdrop filtering.

  • Get NFTs For Contract

    Retrieve all NFTs associated with a specific NFT contract on the selected EVM network, with optional metadata and pagination.

  • Get Owners For NFT

    Retrieve the current owner(s) of a specific NFT token identified by contract address and token ID.

  • Get Owners For Contract

    Retrieve all wallet addresses that own at least one token from an NFT contract, with optional per-token balances and pagination.

  • Get Contracts For Owner

    Retrieve all NFT contracts (collections) from which a wallet address holds at least one token, with optional metadata and filtering.

  • Get NFT Metadata

    Retrieve full metadata (name, image, attributes, token URI) for a single NFT identified by contract address and token ID.

  • Get NFT Metadata Batch

    Retrieve metadata for up to 100 NFTs across multiple contracts in a single batched request.

  • Get Contract Metadata Batch

    Retrieve collection-level metadata for multiple NFT contracts in a single batched request.

  • Get Floor Price

    Retrieve the current floor prices for an NFT collection across supported marketplaces (OpenSea, LooksRare). Provide EITHER contractAddress OR collectionSlug — never both, never neither.

  • Get Spam Contracts

    Retrieve the complete list of NFT contracts that Alchemy has classified as spam. Requires the Growth tier or higher — free/starter accounts receive HTTP 403.

  • Get NFT Sales

    Retrieve historical NFT sales data across supported on-chain marketplaces, filterable by block range, marketplace, contract, token, buyer/seller, and taker.

  • Get Tokens By Address

    Get tokens (fungible + native) held by one or more wallet addresses across specified EVM networks in a single chain-agnostic call.

  • Get Token Balances By Address

    Get token balances (native + ERC-20) held by one or more wallet addresses across specified EVM networks in a single chain-agnostic call.

  • Get NFTs By Address

    Get NFTs held by one or more wallet addresses across specified EVM networks, with optional spam/airdrop filters, in a single chain-agnostic call.

  • Get NFT Contracts By Address

    Get NFT contracts (collections) that one or more wallet addresses hold at least one token from, across specified EVM networks in a single chain-agnostic call.

  • Get Token Prices By Symbol

    Fetch current market prices for up to 25 tokens identified by their ticker symbols (e.g. ETH, BTC, USDC).

  • Get Token Prices By Address

    Fetch current DEX-sourced prices for up to 25 tokens identified by network and contract address pairs.

  • Get Historical Token Prices

    Fetch time-series price history for a single token over a caller-specified time window at 5-minute, hourly, or daily granularity.

  • Get Native Balance

    Get the native token balance (ETH / MATIC / BNB / etc.) for an address on the selected EVM network.

  • Get Block By Number

    Get block information (timestamp, hash, transactions, gas usage) for a specific block number on the selected EVM network.

  • Get Transaction By Hash

    Get transaction details (from, to, value, input data, gas, block) for a specific transaction hash.

  • Get Event Logs

    Get contract event logs matching filter criteria (block range, address, topics) — the core method for indexing token transfers and contract events.

  • Get Gas Price

    Get the current gas price (in wei, hex-encoded) on the selected EVM network.

  • Get Token Allowance

    Returns the ERC-20 token allowance granted by an owner to a spender for a given contract.

  • Get Token Balances

    Returns ERC-20 token balances for a given wallet address, optionally filtered to specific contracts or token type.

  • Get Token Metadata

    Returns metadata (name, symbol, decimals, logo) for a given ERC-20 token contract.

  • Get Asset Transfers

    Fetch historical asset transfer events (external, internal, ERC-20, ERC-721, ERC-1155, special NFT) for any address on the selected EVM network via Alchemy's Transfers API.

  • Compute Rarity

    Compute the rarity score of each attribute for a specific NFT token within an NFT contract.

  • Summarize NFT Attributes

    Generate a summary of how frequently each attribute value appears across all NFTs in a collection.

  • Invalidate Contract

    Mark all cached tokens for the specified NFT contract as stale so the next read fetches fresh on-chain data.

  • Is Spam Contract

    Check whether a specific NFT contract is classified as spam by Alchemy.

  • Report Spam

    Report an NFT contract address to Alchemy as suspected spam. Requires the Enterprise tier or higher — lower tiers receive HTTP 403.

  • Is Airdrop NFT

    Check whether a specific NFT token was airdropped (minted to the owner via a transaction sent by a different address).

  • Read Contract State (eth_call)

    Execute a read-only contract call (view/pure function) against the current chain state, returning the raw ABI-encoded result.

  • Estimate Gas

    Estimate the gas required to execute a transaction, without submitting it to the network.

Set Up Your Alchemy MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Alchemy in under 10 lines of code.

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Alchemy MCP Server FAQ

Does StackOne have a Alchemy MCP server?
Yes. StackOne offers a hosted Alchemy MCP server with 39 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Alchemy MCP server vs direct API integration — what's the difference?
A Alchemy MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Alchemy. A Alchemy MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Alchemy at runtime. StackOne provides both.
How does Alchemy authentication work for AI agents?
Alchemy authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Alchemy account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Alchemy MCP tools vulnerable to prompt injection?
Yes — Alchemy MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Alchemy agent and how do I avoid it?
Context bloat happens when Alchemy tool schemas and API responses eat your Alchemy agent's memory, preventing it from reasoning effectively. A single Alchemy query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Alchemy agent can access?
Yes — you can limit which actions your Alchemy agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Alchemy MCP server?
Yes — you can create custom agent actions for your Alchemy MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Alchemy's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Alchemy MCP server?
Skip a Alchemy MCP server if your integration is purely software-to-software — direct Alchemy API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Alchemy actions at runtime.
What AI frameworks and AI clients does the StackOne Alchemy MCP server support?
The StackOne Alchemy MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.