About ootlebook-explorer
ootlebook-explorer is a read-only MCP server for AI agents that need to inspect the Tari base layer on mainnet or Esmeralda. It reads public explorer data without keys or dependencies beyond Node 20+.
Key features
- 01Read latest block and mempool stats
- 02Inspect block metadata and transaction counts
- 03Page through block outputs
- 04Retrieve miner coinbase extra data
Use cases
- 01Check the latest Tari chain tip
- 02Inspect block contents and proof-of-work details
- 03Review outputs and miner coinbase data
MCP support
Exposes read-only tools for querying Tari chain tips, blocks, and block outputs from the public text explorer. Each tool accepts mainnet or esmeralda as the network.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
3Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| network | enum | No | mainnet, or the esmeralda testnetmainnet | esmeralda |
Details
From the project READMEootlebook-explorer-mcp
An MCP server that lets an AI agent read the Tari base layer (Minotari, mainnet or the Esmeralda testnet) from Tari's public text explorer. Read-only, no keys, no dependencies beyond Node 20+. Inspired by kstrycharz/tariblocktools.
| Tool | What it answers |
|---|---|
tari_tip | the latest block's height, hash and time, and the mempool size |
tari_block | one block: hashes, time, proof-of-work algorithm, coinbase total, counts of outputs, inputs and kernels |
tari_block_outputs | a block's outputs, every page of them; coinbases include the miner's coinbase extra data as text (coinbase_only for just those) |
Every tool takes network: mainnet (default) or esmeralda.
Use it
claude mcp add ootlebook-explorer -- npx -y ootlebook-explorer-mcp # Claude Code
Other MCP clients: run npx -y ootlebook-explorer-mcp as a stdio server. From a checkout: node explorer-mcp/server.mjs.
Test
npm test # offline, against a fake explorer
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.