About MCPChain
MCPChain brings MCP into Web3 by anchoring agent tools, trust registries, and attestable executions on-chain. Its README provides steps to build and start the chain.
Key features
- 01Anchors agent tools on-chain
- 02On-chain trust registries
- 03Attestable execution records
- 04Chain build and startup instructions
Use cases
- 01Register agent tools on-chain
- 02Maintain an on-chain trust registry
- 03Record attestable agent executions
MCP support
The project brings MCP into Web3 and anchors agent tools, trust registries, and attestable executions on-chain. The README does not describe tools exposed to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCPChain
MCPChain brings the Model Context Protocol to Web3 by anchoring agent tools, trust registries, and attestable executions on-chain.
Start the chain
cd mcpchain
ignite chain build
[Optional] Delete Previous Chain State (Safe Dev Reset)
rm -rf ~/.mcpchain
Init Chain
mcpchaind init validator --chain-id mcpchain
Create Key
mcpchaind keys add validator
Replace "stake" with "umcp" in genesis.json
sed -i '' 's/"stake"/"umcp"/g' ~/.mcpchain/config/genesis.json
Add Funds
mcpchaind genesis add-genesis-account $(mcpchaind keys show validator -a) 1000000000umcp
Generate gentx using updated denom
mcpchaind genesis gentx validator 500000000umcp --chain-id mcpchain
Collect and validate
mcpchaind genesis collect-gentxs
mcpchaind genesis validate
Start the chain with a minimum gas price
mcpchaind start --minimum-gas-prices=0.001umcp
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.