NEO Model Context Protocol Server (MCP)
Introduction
GemTM is an AI studio specializing in Model Context Servers that connect AI applications with external systems. Our team has successfully delivered grant-funded projects for industry leaders like Coinbase and Tezos. We are requesting funding to develop a Model Context Protocol (MCP) server that enables AI applications to query NEO data using natural language.
Project Overview
The Model Context Protocol (MCP) allows AI applications, particularly large language models (LLMs), to interact with blockchain networks by translating natural language queries into structured blockchain requests, simplifying complex data into a format that LLMs can process and making it accessible without requiring technical expertise.
Currently, accessing blockchain data demands specialized skills, limiting its reach, as tools like block explorers are designed primarily for developers rather than non-technical users. The MCP server addresses this challenge by enabling natural language queries for blockchain data through integration with an LLM, offering a standardized and reusable framework for developers to integrate blockchain data with AI applications, and broadening accessibility by facilitating AI-driven data access for a wider audience.
Benefits to the NEO Ecosystem
- Non-technical users can leverage AI applications to query data using natural language.
- A flexible framework speeds up the development of AI-driven tools and applications.
- Attracts new users and developers by enabling AI-driven features for blockchain data access.
- Lays the groundwork for advanced AI-blockchain integrations.
Project Deliverables
1. MCP Server for NEO
- Connects to NEO's data.
- Includes tools for basic queries (e.g., balances, transactions, token transfers).
- Supports querying at a specific block height for historical data analysis.
- Enables sending transactions to contracts.
- Provides transaction analysis by transaction hash.
- Supports contract deployment on the blockchain.
- Allows execution of scripts to automate blockchain tasks.
- Supports running local forked instances for testing and debugging.
2. Documentation and Examples
- Technical documentation for the MCP server.
- Sample queries and use cases for developers.
- Developer tutorial for integrating the MCP server with AI applications.
Implementation Plan
- Research and Design — Study NEO's data and design the MCP server.
- Development — Build the MCP server and integrate it with an LLM for query processing.
- Testing — Ensure functionality and accuracy of the server’s features.
- Documentation — Produce guides and examples for developers.
Timeline
- Week 1: Research and Design
- Week 2: Development and Testing
- Week 3: Development and Testing
- Week 4: Documentation and MCP Server Delivery
This one-month schedule delivers a working MCP server as a proof-of-concept.
Budget
We request 4000 NEO for this one-month project, covering team compensation, development resources, and infrastructure costs.
Unique Value Proposition
- Enables intuitive access for AI applications to process blockchain data.
- Reusable and extensible for developers across blockchains.
- Optimized for NEO's architecture.
- Combines AI with blockchain data access in a developer-friendly way.
Community and Open Source
We will open-source the MCP server, inviting the NEO community to contribute and adapt it. Community input will guide future improvements, ensuring the server meets the ecosystem’s needs.
Conclusion
This project will enhance NEO's ecosystem by enabling AI applications to access its data seamlessly, benefiting users and developers alike. We are committed to delivering a high-quality, open-source MCP server and collaborating with the community.
Thank you,
💎™️
https://www.gemtm.xyz/
Proposal Info :clipboard:
-
Proposal Type:
request-for-funding -
Amount Requested:
3500 -
Token:
0xef4073a0f2b305a38ec4050e4d3d28bc40ea63f5(NEO) -
Receiver Address:
NLnfdJ5mHHiXF397nHQ3zYMt9wc6fK2GbB(0x6de8aa39192e281dffff684eefd41bbc548e9609) -
Created by: @MatthysenZ :rocket:
-
Proposal :
https://grantshares.io/app/details/1e23b7f868278f1ac252f8f752ec59bc -
Raw Intents: :eyes:
[ {
"target_contract" : "0x6276c1e3a68280bc6c9c00df755fb691be1162ef",
"method" : "releaseTokens",
"params" : [ {
"type" : "Hash160",
"value" : "ef4073a0f2b305a38ec4050e4d3d28bc40ea63f5"
}, {
"type" : "Hash160",
"value" : "6de8aa39192e281dffff684eefd41bbc548e9609"
}, {
"type" : "Integer",
"value" : "3500"
} ],
"call_flags" : 15
} ]
👇 React with 👍 if you liked it, or 👎 if you think this proposal can be enhanced!
In terms of timing, this proposal appears to align with similar ongoing initiatives within the NEO ecosystem most notably, SpoonOS, which also aims to simplify developer and AI interactions with blockchain data. It would be helpful to understand how this project differentiates itself in scope and approach, or whether there is potential overlap.
Additionally, it’s difficult to assess the team’s previous experience or technical capabilities, as the proposal doesn’t provide links to prior open-source contributions, past project examples or working demos.
Regarding the deliverables, the proposal outlines the creation of a “proof of concept” MCP server, but the usability expectations for that proof of concept remain unclear to me. What is the absolute minimum viable product that will be delivered?
Finally, if the proof of concept proves successful, what are the next steps? Is there a roadmap for expanding functionality, supporting other chains, or building a user-facing interface? Understanding the long-term vision would help gauge how this initiative might evolve into a core piece of infrastructure for the NEO ecosystem.
The website is a bit... light and a Github link could be nice to see if you have one :)
Thank you @snakeyrob and @NeoDashboard for your feedback! We'd like to address your questions:
Team Experience & Credentials
GemTM has successfully delivered several projects with various Chains and has received grants from Coinbase, Tezos and other chains for building developer tooling.
Differentiation from SpoonOS
Our approach differs from SpoonOS in key ways: • Standardized protocol layer optimized for NEO's architecture and data models • Interoperability with multiple LLM providers • Specialized tooling for blockchain-specific datasets • Built with cross-chain extensibility
Minimum Viable Product
Our proof-of-concept will deliver: • Functioning MCP server with NEO RPC compatibility • Demo integration with a Claude, VSCode/Cline • Complete documentation and developer guides
Future Roadmap
If successful, we plan to: 1. Expand query capabilities to all NEO operations 2. Create a user-friendly deployment strategies 3. Add support for advanced NEO contract interactions 4. Develop more sophisticated query optimization
We are available for a detailed discussion of our technical background and relevant experience over a Zoom call at your convenience.
Thank you for your consideration! 💎™️
Differentiation from SpoonOS
Our approach differs from SpoonOS in key ways: • Standardized protocol layer optimized for NEO's architecture and data models • Interoperability with multiple LLM providers • Specialized tooling for blockchain-specific datasets • Built with cross-chain extensibility
This sounds wrong to me but will let others give their opinion :)
I think NEO doesn't need a MCP for itself for now. Our focus is expanding to other useful areas.
@Jim8y: I don't remember if it was you or not... BUT, did you play a bit with MCP servers and made a PoC for Neo data? Or was someone else? If yes, what do you think about this proposal?
@Jim8y: I don't remember if it was you or not... BUT, did you play a bit with MCP servers and made a PoC for Neo data? Or was someone else? If yes, what do you think about this proposal?
its here
https://github.com/r3e-network/neo-n3-mcp
{ "mcpServers": { "neo-n3": { "command": "npx", "args": [ "-y", "@r3e/neo-n3-mcp" ] } } }