Skip to main content
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.

Connect Portal MCP

  • MCP endpoint: https://portal.sqd.dev/mcp
  • Authentication: Free, no API keys required
claude mcp add --transport http sqd-portal https://portal.sqd.dev/mcp
Test the connection:
claude mcp list
See the Claude Code documentation for more details.

Available tools

29 tools across EVM, Solana, Bitcoin, and Hyperliquid — all queryable in natural language.

Dataset Discovery

ToolDescription
portal_list_datasetsSearch and filter available datasets
portal_get_dataset_infoGet dataset metadata, tables, and latest block

EVM Tools

ToolDescription
portal_get_block_numberGet latest or finalized block number
portal_block_at_timestampConvert Unix timestamp to block number
portal_query_blocksQuery block data with field presets
portal_query_logsQuery event logs with address/topic filters
portal_query_transactionsQuery transactions (includes traces and state diffs via flags)
portal_get_erc20_transfersGet ERC20 token transfers (auto-filters Transfer events)
portal_decode_logsDecode event logs (Transfer, Swap, etc.)
portal_get_recent_transactionsGet recent transactions without manual block math
portal_get_wallet_summaryWallet activity: transactions, tokens, NFTs
portal_get_contract_activityContract interaction count, callers, events
portal_get_top_contractsMost active contracts by transaction count
portal_get_transaction_densityTransaction count per block
portal_get_time_seriesAggregate metrics over time intervals

Solana Tools

ToolDescription
portal_query_solana_transactionsQuery transactions (includes balances, token balances, logs, rewards via flags)
portal_query_solana_instructionsQuery program instructions with account filters
portal_solana_analyticsTransaction stats, program rankings, fee analysis
portal_solana_time_seriesTPS, fee, and wallet trends over time

Bitcoin Tools

ToolDescription
portal_query_bitcoin_transactionsQuery Bitcoin transactions
portal_query_bitcoin_inputsQuery transaction inputs (UTXO spending)
portal_query_bitcoin_outputsQuery transaction outputs (UTXO creation)
portal_bitcoin_analyticsTransaction stats, fee analysis, size distribution
portal_bitcoin_time_seriesBlock size, fees, and transaction trends over time

Hyperliquid Tools

ToolDescription
portal_query_hyperliquid_fillsQuery trade fills with PnL, fees, routing
portal_query_hyperliquid_replica_cmdsQuery orders, cancels, transfers, leverage updates
portal_aggregate_hyperliquid_fillsVolume, PnL, and trader stats by coin
portal_hyperliquid_time_seriesVolume, trades, and unique traders over time
portal_hyperliquid_analyticsTrading volume, top coins, trader rankings

Known limitations

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.

Best practices

  1. Use timeframes for any query — All query tools support the timeframe parameter (e.g., "24h", "7d") — no need to calculate block ranges manually
  2. Try specialized tools first — Use high-level tools like portal_get_wallet_summary or portal_get_recent_transactions before lower-level query tools
  3. Always filter queries — Use addresses, topics, or other filters to keep responses under the 50KB cap
  4. Leverage analytics tools — Use per-chain analytics and time series tools to get summaries without fetching raw data
  5. 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