Query blockchain data through Portal API using Model Context Protocol
The Portal MCP server is experimental. Available tools and behavior may change.
Connect the Portal MCP server to your favorite AI coding clients.MCP (Model Context Protocol) is an open-source standard for connecting AI applications to external systems. The Portal MCP server gives your agent direct, structured access to blockchain data: discover datasets, query transactions and logs, analyze wallets, and compare chains — all from the same conversation.This is the fastest way to move from prompt to reliable onchain analysis across 225+ datasets.
Custom connectors are available on all Claude plans. Free users are limited to one custom connector. For Team and Enterprise plans, only Owners can add connectors.
1
Add the Portal MCP server to Claude
Navigate to the Connectors page in Claude settings.
Select Add custom connector.
Add the Portal MCP server:
Name: Portal
URL: https://portal.sqd.dev/mcp
Select Add.
2
Access the MCP server in your chat
When using Claude, select the attachments button (the plus icon).
Select the Portal MCP server.
Ask Claude questions about blockchain data from Portal API.
The MCP server may struggle with memory issues when handling large volumes of data, especially on high-TPS chains like Solana and Hyperliquid. v0.7.5 introduced chunked fetching and lower default limits to mitigate this, but large unfiltered queries can still cause timeouts or incomplete results. Always use filters and keep block ranges tight on dense chains.
Use timeframes for any query — All query tools support the timeframe parameter (e.g., "24h", "7d") — no need to calculate block ranges manually
Try specialized tools first — Use high-level tools like portal_get_wallet_summary or portal_get_recent_transactions before lower-level query tools
Always filter queries — Use addresses, topics, or other filters to keep responses under the 50KB cap
Leverage analytics tools — Use per-chain analytics and time series tools to get summaries without fetching raw data
Mind block ranges — Keep queries under 10K blocks for logs, 5K for transactions, and 1K for traces for best performance. On high-TPS chains, use even smaller ranges