TAU Assistant Cline

This guide walks you through the integration of Fabric Model Context Protocol⁠ (MCP) to access Fabric data through natural language conversations with Cline.

Prerequisites

• Cline⁠ installed (latest version)
• A Gateway API key from TAU Studio
• npx⁠ or bunx⁠ installed and available in your path

Configuration Steps

1. Open Configuration File

Create or edit your cline_mcp_settings.json file.

2. Add Configuration

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 API Key

Replace GATEWAY_API_KEY with your API key from TAU Studio.

Using The Fabric Resource in Cline

After configuring Cline:

1. Restart Cline
2. Start a new conversation
3. Enable the TAU MCP from the context menu
4. Add “TAU Server Instructions” as a resource to your chat context

Available Tools and Usage

The TAU MCP provides several tools for interacting with Fabric datasets:

Schema Retrieval Tools

• Get TAU schema by deployment ID: Access the GraphQL schema using a deployment ID (0x…)
• Get TAU schema by TAU ID: Access the schema for the current deployment of a TAU dataset (5zvR82…)
• Get TAU schema by IPFS hash: Access the schema using a TAU dataset’s IPFS manifest hash (Qm…)

Query Execution Tools

• Execute query by deployment ID: 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

• Get top TAU deployments: Find the top 3 TAU deployments indexing a specific contract on a particular chain

Natural Language Queries

One of the most powerful features of the TAU MCP integration is the ability to ask questions in natural language. Cline 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
4. Convert your question into an appropriate GraphQL query
5. Execute the query and present the results in a readable format

Example Natural Language Queries

1What are the anchors with the highest trust scores on deployment 0xde0a7b5368f846f7d863d9f64949b688ad9818243151d488b4c6b206145b9ea3?

1Which campaigns have the most rewards distributed in this TAU dataset?

1Show me the most recent 5 proofs submitted for the RewardDistributor contract

Key Identifier Types

When working with Fabric datasets, you’ll encounter different types of identifiers:

• TAU ID (e.g., 5zvR82...): Logical identifier for a TAU dataset
• Deployment ID (e.g., 0x4d7c...): Identifier for a specific, immutable deployment
• IPFS Hash (e.g., QmTZ8e...): Identifier for the manifest of a specific deployment