Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@tron-event-mcp Show me the top 10 most active contracts in the last 24 hours."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TRON blockchain event data query MCP Server — let AI assistants analyze on-chain data directly.
Works with event-plugin: event-plugin writes TRON on-chain events into MongoDB in real time, and this project exposes that data to AI assistants (Claude, Cursor, etc.) via the Model Context Protocol (MCP), enabling natural-language-driven on-chain data analysis.
event-plugin listens to a Java-tron node and writes the following 7 event types into MongoDB:
Collection | Description | Unique Index |
| Block event, triggered for every new block |
|
| Transaction event, triggered for every packaged transaction |
|
| Contract event, triggered when a smart contract emits an event (ABI-decoded) |
|
| Contract raw log, not ABI-decoded (hex data) |
|
| Solidity trigger, fired when a block is finalized |
|
| Solidified contract event, same structure as |
|
| Solidified contract raw log, same structure as |
|
Related MCP server: mcp-server-tron
Tool | Description |
| Return field descriptions, index info, and business meaning for all collections |
| Return document count and earliest/latest timestamps per collection |
Tool | Description |
| Query events/logs for a specific contract, with event name and time range filters |
| General-purpose query with arbitrary filters and field projection |
| Quickly count documents matching given criteria |
| Look up a block by height |
| Look up a transaction by hash |
Tool | Description |
| Compute sum / avg / min / max on a specified field |
| Group-by aggregation for address rankings, event distribution, etc. |
| Time-series aggregation (hour / day / week) with optional sum field |
| Leaderboard of most active contracts in a time range |
Tool | Description |
| Full transaction view: details + associated contract events |
| Address activity profile across sender, receiver, and contract caller roles |
Tool | Description |
| Numeric field bucketing with auto or manual boundaries |
| Compute percentiles (P50 / P90 / P95 / P99, etc.) |
event-plugin itself only creates unique indexes (for data deduplication/upsert). To get optimal query performance with this MCP Server's analytics tools, add the following indexes to MongoDB:
// contractevent (highest query volume)
db.contractevent.createIndex({ contractAddress: 1, eventName: 1, timeStamp: -1 });
db.contractevent.createIndex({ contractAddress: 1, timeStamp: -1 });
db.contractevent.createIndex({ timeStamp: -1 });
// solidityevent
db.solidityevent.createIndex({ contractAddress: 1, eventName: 1, timeStamp: -1 });
db.solidityevent.createIndex({ contractAddress: 1, timeStamp: -1 });
db.solidityevent.createIndex({ timeStamp: -1 });
// transaction
db.transaction.createIndex({ timeStamp: -1 });
db.transaction.createIndex({ result: 1 });
// block
db.block.createIndex({ timeStamp: -1 });
// contractlog / soliditylog
db.contractlog.createIndex({ contractAddress: 1, timeStamp: -1 });
db.soliditylog.createIndex({ contractAddress: 1, timeStamp: -1 });The create_index.js file in the project root contains the complete index creation script (unique + analytics indexes). Run it directly:
mongosh mongodb://host:27017/tron create_index.jsPython >= 3.11
MongoDB >= 7.0 (the percentiles tool uses the $percentile aggregation operator, which requires 7.0+; all other tools work with 5.0+)
cd tron-event-mcp
make setupEdit the .env file (make setup copies it from .env.example automatically):
# MongoDB connection (strongly recommended to use a read-only user)
MONGO_URI=mongodb://readonly_user:password@host:27017/dbname?authSource=admin
MONGO_DB=tron
# Maximum documents per query (prevents fetching massive datasets)
MAX_RESULT_LIMIT=500
# Query timeout in milliseconds
QUERY_TIMEOUT_MS=10000# stdio mode (for local clients like Claude Code, Cursor, etc.)
make run
# SSE mode (for remote access)
make run-sseAdd the following to your Claude Code MCP configuration:
{
"mcpServers": {
"tron-events": {
"command": "/path/to/tron-event-mcp/.venv/bin/python",
"args": ["-m", "tron_event_mcp"]
}
}
}In Cursor Settings > MCP, add the same configuration as above.
Once connected, you can ask questions in natural language:
"What are the most active contracts in the last 24 hours?"
"Show me the hourly USDT Transfer event volume trend"
"Analyze the on-chain activity of address TXxx..."
"What does the energy consumption distribution look like for transactions?"
"Show me the full details of transaction abc123..."
The AI assistant will automatically select the right combination of tools to answer.
tron-event-mcp/
├── src/tron_event_mcp/
│ ├── server.py # MCP Server entry point; registers all tools and resources
│ ├── config.py # Configuration management (env vars / .env)
│ ├── db/ # MongoDB connection and query layer
│ ├── tools/
│ │ ├── schema.py # describe_schema, get_collection_stats
│ │ ├── query.py # get_recent_events, get_block, get_transaction, query_events
│ │ ├── analytics.py # search_contract_activity, aggregate_field, group_by_field, etc.
│ │ ├── cross_collection.py # get_transaction_full, get_address_profile
│ │ └── distribution.py # histogram, percentiles
│ └── resources/ # MCP Resources (documentation resources)
├── tests/
├── pyproject.toml
├── Makefile
└── .env.exampleUse a read-only MongoDB user — this tool only performs queries, no write access needed
Query filters forbid $where, $function, $accumulator and other code-execution operators
MAX_RESULT_LIMIT caps documents per request, protecting database performance
QUERY_TIMEOUT_MS enforces query timeout, preventing slow queries from blocking
MIT
This server cannot be deployed
Query 130+ SQD Portal datasets across blockchains, including native Tron transactions and events.
TRON Energy marketplace + DEX swap aggregator for AI agents. 27 MCP tools.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
