Docs
Search⌘ K
  • Home
  • About TAU
  • Supported Networks
  • Protocol Contracts
  • Fabric
    • Anchors
      • TAU Token
        • AI Suite
          • Indexing
            • Resources
              AI Suite > Subgraph MCP

              4 minutes

              TAU Assistant Claude Desktop

              This guide walks you through the integration of TAU Assistant via the Model Context Protocol⁠ (MCP) to access TAU Anchors, Proofs, RewardDistributor, and context data through natural language conversations with Claude.

              Prerequisites

              • Node.js⁠ installed and available in your path
              • Claude Desktop⁠ installed (latest version)
              • A Gateway API key from TAU Studio⁠

              Installation Options

              Option 1: Using npx (Recommended)

              Configuration Steps using npx

              1. Open Configuration File

              Navigate to your claude_desktop_config.json file:

              Settings > Developer > Edit Config

              • OSX: ~/Library/Application Support/Claude/claude_desktop_config.json
              • Windows: %APPDATA%\Claude\claude_desktop_config.json
              • Linux: .config/Claude/claude_desktop_config.json

              2. Add Configuration

              Paste the following settings into your config file:

              1{2  "mcpServers": {3    "tau": {4      "command": "npx",5      "args": ["mcp-remote", "--header", "Authorization:${AUTH_HEADER}", "https://mcp.tau.org/sse"],6      "env": {7        "AUTH_HEADER": "Bearer GATEWAY_API_KEY"8      }9    }10  }11}

              3. Add Your Gateway API Key

              Replace GATEWAY_API_KEY with your API key from TAU Studio⁠.

              4. Save and Restart

              Once you’ve entered your Gateway API key into your settings, save the file and restart Claude Desktop.

              Option 2: Building from Source

              Requirements

              • Rust (latest stable version recommended: 1.75+)
                1curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
                Follow the on-screen instructions. For other platforms, see the official Rust installation guide⁠.

              Installation Steps

              1. Clone and Build the Repository

                1git clone git@github.com:tauproject/tau-mcp.git2cd tau-mcp3cargo build --release
              2. Find the Command Path

                After building, the executable will be located at target/release/tau-mcp inside your project directory.

                • Navigate to your tau-mcp directory in terminal
                • Run pwd to get the full path
                • Combine the output with /target/release/tau-mcp
              3. Configure Claude Desktop

                Open your claude_desktop_config.json file as described above and add:

                1{2  "mcpServers": {3    "tau": {4      "command": "/path/to/your/tau-mcp/target/release/tau-mcp",5      "env": {6        "GATEWAY_API_KEY": "your-api-key-here"7      }8    }9  }10}

                Replace /path/to/your/tau-mcp/target/release/tau-mcp with the actual path to the compiled binary.

              Using The TAU Resource in Claude

              After configuring Claude Desktop:

              1. Restart Claude Desktop
              2. Start a new conversation
              3. Click on the context menu (top right)
              4. Add “TAU Server Instructions” as a resource by adding graphql://tau to your chat context

              Important: Claude Desktop may not automatically utilize the TAU MCP. You must manually add “TAU Server Instructions” resource to your chat context for each conversation where you want to use it.

              Troubleshooting

              To enable logs for the MCP when using the npx option, add the --verbose true option to your args array.

              Available TAU Tools and Usage

              The TAU MCP provides several tools for interacting with TAU Anchors, Proof Anchors, RewardDistributor, and datasets:

              Schema Retrieval Tools

              • Get schema by deployment ID: Access the GraphQL schema using a deployment ID (0x…)
              • Get schema by TAU ID: Access the schema for the current deployment of a TAU dataset (e.g., TAU123…)
              • Get schema by IPFS hash: Access the schema using a TAU dataset’s IPFS manifest hash (Qm…)

              Query Execution Tools

              • Execute query by deployment ID/IPFS hash: Run GraphQL queries against specific, immutable deployments
              • Execute query by TAU ID: Run GraphQL queries against the latest version of a TAU dataset

              Discovery Tools

              • Search datasets by keyword: Find TAU datasets by keyword in their display names, ordered by signal
              • Get deployment 30-day query counts: Get aggregate query count over the last 30 days for multiple TAU dataset deployments
              • Get top TAU deployments for a wallet or contract: Find the top 3 TAU deployments indexing a specific wallet or contract on a particular chain, ordered by query fees

              Key Identifier Types

              • TAU ID (e.g., TAU123...): Logical identifier for a TAU dataset. Use execute_query_by_tau_id or get_schema_by_tau_id.
              • Deployment ID (e.g., 0x4d7c...): Identifier for a specific, immutable deployment. Use execute_query_by_deployment_id or get_schema_by_deployment_id.
              • IPFS Hash (e.g., QmTZ8e...): Identifier for the manifest of a specific, immutable deployment. Use execute_query_by_deployment_id (the gateway treats it like a deployment ID for querying) or get_schema_by_ipfs_hash.

              Benefits of Natural Language Queries

              One of the most powerful features of the TAU MCP integration is the ability to ask questions in natural language. Claude will:

              1. Understand your goal (lookup, find TAU datasets, query, get schema)
              2. Find relevant deployments if needed
              3. Fetch and interpret the TAU schema including Anchors and Proofs
              4. Convert your question into an appropriate GraphQL query
              5. Execute the query and present the results in a readable format

              This enables seamless exploration of wallet trust scores, proof validations, reward distributions, and other context data across multiple TAU datasets.

              Example Natural Language Queries

              1What is the trust score of wallet 0xabc123 on the latest TAU deployment?
              1Show me all Anchors related to wallet 0xdef456 in the last 7 days
              1List the most recent 5 proofs submitted for TAU dataset TAU789
              1Find the top reward campaigns for wallet 0x123abc on the Ethereum mainnet
              5September 5, 2025
              ⁠Edit on GitHub⁠

              IntroductionTAU Assistant Cline
              On this page
              • Prerequisites
              • Installation Options
              • Option 1: Using npx (Recommended)
              • Option 2: Building from Source
              • Using The TAU Resource in Claude
              • Troubleshooting
              • Available TAU Tools and Usage
              • Schema Retrieval Tools
              • Query Execution Tools
              • Discovery Tools
              • Key Identifier Types
              • Benefits of Natural Language Queries
              • Example Natural Language Queries
              The GraphStatusTestnetBrand AssetsForumSecurityPrivacy PolicyTerms of Service