Skip to main content
Glama
tatumio

Tatum MCP Server

Official

get_metadata_v4

Retrieve metadata for NFTs or multitokens by specifying chain, token address, and IDs. Works across Ethereum, Base, Arbitrum, BNB Smart Chain, Polygon, Optimism, Celo, and Chiliz blockchains.

Instructions

[blockchain_data] /v4/data/metadata 10 credits per API call > 📘 Note for v3 API users: > > As part of our documentation consolidation, we removed the dedicated page for GET /v3/data/metadata. Users can refer to GET /v4/data/metadata for the latest documentation, as both endpoints function the same—simply replace v4 with v3 in the API URL if using the v3 version. Get metadata of NFTs (ERC-721 and ERC-1155) or multitokens (ERC-1155 only) by IDs for a given token address! Our API lets you search for all tokens on: Ethereum - ethereum-mainnet / ethereum-sepolia / ethereum-holesky Base - base-mainnet / base-sepolia Arbitrum - arb-one-mainnet / arb-testnet BNB (Binance) Smart Chain - bsc-mainnet / bsc-testnet Polygon - polygon-mainnet Optimism - optimism-mainnet / optimism-testnet Celo - celo-mainnet / celo-testnet Chiliz - chiliz-mainnet To get started: Provide a chain name, token address and comma-separated list of IDs. Our API will return relevant metadata about each specified token, including its name, description, image, and more. Aside from the metadata information, the response also contains token types and metadata url minted in each token.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chainYesThe blockchain to work with.
tokenAddressYesThe blockchain address of the NFT to get metadata for.
tokenIdsYesThe IDs of the tokens to get metadata for. It is possible to enter list of multiple IDs as a comma separated string.

Implementation Reference

  • Handler function that calls the Tatum API v4 endpoint /v4/data/metadata to fetch NFT/multitoken metadata.
    async getMetadata(args: any): Promise<any> {
      const url = `/v4/data/metadata`;
      const parameters = {
        chain: args.chain,
        tokenAddress: args.tokenAddress,
        tokenIds: args.tokenIds
      };
      return await this.apiClient.executeRequest('GET', url, parameters);
    }
  • Input schema for the get_metadata tool, defining parameters chain, tokenAddress, tokenIds.
    {
      name: 'get_metadata',
      description: 'Fetch metadata of NFTs or multitokens by token address and IDs.',
      inputSchema: {
        type: 'object',
        properties: {
          chain: {
            type: 'string',
            description: 'The blockchain to work with.',
            example: 'ethereum-mainnet'
          },
          tokenAddress: {
            type: 'string',
            description: 'The blockchain address of the NFT to get metadata for.',
            example: '0xba30E5F9Bb24caa003E9f2f0497Ad287FDF95623'
          },
          tokenIds: {
            type: 'string',
            description: 'The IDs of the tokens to get metadata for. It is possible to enter list of multiple IDs as a comma separated string.'
          }
        },
        required: ['chain', 'tokenAddress', 'tokenIds']
      }
    },
  • src/index.ts:115-119 (registration)
    Registration of the get_metadata tool handler in the MCP CallToolRequestSchema switch statement.
    case 'get_metadata':
      if (!args.chain || !args.tokenAddress || !args.tokenIds) {
        throw new McpError(ErrorCode.InvalidParams, 'Missing required parameters: chain, tokenAddress, tokenIds');
      }
      return await this.dataService.getMetadata(args);
  • src/index.ts:198-202 (registration)
    Registration of get_metadata in the ListToolsRequestSchema handler, exposing the tool name and schema.
    ...DATA_TOOLS.map(tool => ({
      name: tool.name,
      description: `[data] ${tool.description}`,
      inputSchema: tool.inputSchema
    }))
  • Helper function in TatumApiClient that performs the actual HTTP request to Tatum API endpoints like /v4/data/metadata.
    public async executeRequest(
      method: string,
      path: string,
      parameters: Record<string, any> = {}
    ): Promise<TatumApiResponse> {
      const validMethods = ['GET', 'POST', 'PUT', 'DELETE', 'PATCH'];
      
      if (!method || !path || !validMethods.includes(method.toUpperCase())) {
        return {
          error: 'Invalid method or path',
          status: 400,
          statusText: 'Bad Request'
        };
      }
      try {
        const config: AxiosRequestConfig = {
          method: method.toLowerCase() as any,
          url: this.buildUrl(path, parameters),
        };
    
        // Handle request body for POST/PUT requests
        if (['POST', 'PUT'].includes(method.toUpperCase())) {
          config.data = parameters;
        }
    
        const response: AxiosResponse = await this.client.request(config);
    
        return {
          data: response.data,
          status: response.status,
          statusText: response.statusText
        };
      } catch (error: any) {
        return {
          error: error.response?.data?.message ?? error.response?.statusText ?? error.message ?? 'Request failed',
          status: error.response?.status ?? 0,
          statusText: error.response?.statusText ?? 'Error'
        };
      }
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions '10 credits per API call' (cost implication) and describes what the response contains ('metadata about each specified token, including its name, description, image, and more'). However, it doesn't disclose important behavioral traits like rate limits, error conditions, pagination, or whether this is a read-only operation. The description adds some value but leaves significant gaps for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is poorly structured and contains unnecessary information. It begins with API endpoint details and a note for v3 users that doesn't help tool selection. The core purpose is buried in the middle, and the blockchain list is excessively detailed. While all information is technically relevant, the presentation lacks front-loading and contains sentences that don't earn their place for tool selection purposes.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 3 parameters, 100% schema coverage, but no annotations and no output schema, the description provides adequate but incomplete context. It covers the purpose, supported networks, and response content, but lacks information about error handling, rate limits, and detailed behavioral characteristics. The absence of an output schema means the description should ideally explain return values more thoroughly than it does.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the schema already documents all three parameters thoroughly. The description adds minimal value beyond the schema: it mentions 'comma-separated list of IDs' (already in schema) and lists supported blockchain networks (helpful context not in schema). This meets the baseline expectation when schema coverage is high, but doesn't significantly enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get metadata of NFTs (ERC-721 and ERC-1155) or multitokens (ERC-1155 only) by IDs for a given token address.' It specifies the resource (NFT/multitoken metadata), the action (get), and the key parameters (token address and IDs). However, it doesn't explicitly differentiate from sibling tools like 'get_collections_v4' or 'get_nft_balances_v4', which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides implied usage context by listing supported blockchains and stating 'To get started: Provide a chain name, token address and comma-separated list of IDs.' However, it doesn't explicitly state when to use this tool versus alternatives like 'get_owners_v4' or 'get_collections_v4', nor does it provide exclusion criteria or prerequisites beyond the required parameters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tatumio/tatum-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server