Last updated 6 months ago
Cardano lacks a unified MCP server for LLM-powered development, governance insights, and smart contract tools, slowing innovation and limiting access for developers and voters.
Build a Cardano MCP Server for AI-assisted contract coding, Plutus doc search, and Catalyst governance insights, accessible in MCP hosts like Claude, VS Code, and other IDEs
This is the total amount allocated to Wolfram Cardano MCP Server: Smart Contracts & Catalyst.
Please provide your proposal title
Wolfram Cardano MCP Server: Smart Contracts & Catalyst
Enter the amount of funding you are requesting in ADA
75000
Please specify how many months you expect your project to last
5
Please indicate if your proposal has been auto-translated
No
Original Language
en
What is the problem you want to solve?
Cardano lacks a unified MCP server for LLM-powered development, governance insights, and smart contract tools, slowing innovation and limiting access for developers and voters.
Supporting links
Does your project have any dependencies on other organizations, technical or otherwise?
No
Describe any dependencies or write 'No dependencies'
No dependencies
Will your project's outputs be fully open source?
Yes
License and Additional Information
The project will be open-sourced under the Apache 2.0 license for maximum permissiveness and enterprise adoption. All source code will be published on GitHub from project start. Documentation, API references, and example use cases will be included. Community contributions will be encouraged through public issues and PRs.
Please choose the most relevant theme and tag related to the outcomes of your proposal
AI
Mention your open source license and describe your open source license rationale.
Apache 2.0 License for broad commercial and community use. Code will be on public GitHub from project start, with initial commits covering project details and documentation. We will post weekly updates in GitHub Discussions, Discord, and the Catalyst forum.
How do you make sure your source code is accessible to the public from project start, and people are informed?
Code will be on public GitHub from project start, with initial commits covering project details and documentation. We will post weekly updates in GitHub Discussions, Cardano Discord, and the Catalyst forum.
How will you provide high quality documentation?
Project will include clear README, Developer setup guides with screenshots & code snippets, MCP integration examples and video walkthroughs. We follow industry standard documentation practices as a long-time scientific software organization.
Please describe your proposed solution and how it addresses the problem
Cardano developers and Project Catalyst participants face steep learning curves when building smart contract or exploring Catalyst governance data. Existing tools often operate in silos, and require manual integration, making it difficult to combine blockchain functionality with AI-assisted development environment. This limits accessibility, slows innovation, and discourages new builders from engaging with the ecosystem.
The Model Context Protocol (MCP) is an open standard (based on JSON-RPC 2.0) that allows AI-powered applications and development tools to connect to external services in a modular, standardized way. By building a Cardano MCP Server, we make blockchain and governance capabilities instantly available in popular MCP-enabled hosts such as Claude, VS Code, and other AI-driven IDEs, without complex setup or custom APIs.
For developers, this means writing, testing, and deploying smart contract directly from their existing AI-assisted environments. For Catalyst participants, it means instantly searching proposals, analyzing voting trends, and getting governance insights in plain language. MCP acts as the adapter that connects Cardano to the rapidly growing ecosystem of AI tools.
We propose building the Cardano Model Context Protocol (MCP) Server, a standardized server that bridges AI-powered development environments with the Cardano blockchain. The MCP Server will:
MCP Server Diagram: https://amoeba.wolfram.com/index.php/s/wF8fqKFF5CjqiyT
The Cardano MCP server will be built as a modular, open-source implementation. Its architecture will consist of a core MCP server, a smart contract assistance module with a Retrieval Augmented Generation (RAG) pipeline for Plutus documentation and templates, and a Catalyst governance analytics module that queries and summarizes Catalyst data.
The system will be packaged for deployment via Docker, MCP Desktop Extension(DXT).
The architecture is designed for future expansion, supporting additional Cardano capabilities such as token metadata lookups, historical chain queries, contract activity summaries and wallet integration.
Please define the positive impact your project will have on the wider Cardano community
This Project will:
Integrating Cardano into the Model Context Protocol ecosystem places it at the cutting edge of AI-assisted blockchain development, attracting developers from both the AI and Web3 communities.
What is your capability to deliver your project with high levels of trust and accountability? How do you intend to validate if your approach is feasible?
Wolfram brings its proven expertise with AI, blockchain and data driven applications, ensuring the successful delivery of the Cardano MCP Server project.
Technical Capabilities
Organizational Strengths
Our team has over three decades of leadership in computational science, data science, and AI. We're used to supporting innovative systems around the world. We have multidisciplinary team specializing in AI, blockchain development, web development, data science, and community engagement. Our company has always prided ourselves on the global talent and knowledge we have. Along with our innovative tech stack, we have an in-house consulting team who has helped organizations with the most difficult problems for decades.
Milestone Title
MCP Server Architecture, GitHub launch
Milestone Outputs
Core MCP Server architecture (based on JSON-RPC 2.0) defined and documented. GitHub repository initialized with base code structure, and license (Apache 2.0). Basic MCP connection prototype functional.
Acceptance Criteria
The MCP Server must successfully compile and run locally, establishing connections to test endpoints without errors. The README file must include detailed architecture diagrams, setup instructions, and configuration examples, ensuring that developers can easily replicate the setup and extend the architecture for future use cases.
Evidence of Completion
A publicly accessible GitHub repository containing the initial commit with base code structure, Apache 2.0 license, and README documentation. The repository must include architecture diagrams and setup instructions, along with verification that the server runs locally and connects to test endpoints, demonstrated through logs or recorded walkthroughs.
Delivery Month
1
Cost
15000
Progress
20 %
Milestone Title
AI-Assisted Smart Contract Development Tool
Milestone Outputs
Plutus documentation is fully integrated into a Retrieval-Augmented Generation (RAG) pipeline, enabling precise AI guidance for smart contract development. An LLM-assisted module is implemented that allows developers to generate, validate, and refine Plutus smart contracts through natural-language prompts. All code and configuration files are version-controlled in a public GitHub repository for community use.
Acceptance Criteria
The MCP Server must enable AI tools connected through the protocol to generate syntactically valid Plutus smart contracts and validate them against predefined rules using only natural-language input. The pipeline must demonstrate accurate retrieval of relevant Plutus documentation during the contract generation process, ensuring that results are functional, explainable, and reproducible across different MCP-enabled environments such as Claude and VS Code.
Evidence of Completion
Screenshot/Video of the contract creation in MCP-enabled environments (e.g. Claude, VS Code) Code and configuration file published to GitHub
Delivery Month
2
Cost
15000
Progress
40 %
Milestone Title
Catalyst Governance Data & Analytics Tool
Milestone Outputs
The MCP Server is integrated with Cardano Catalyst APIs to retrieve governance-related data, including proposals, comments, and voting metadata. New MCP tools are developed to analyze proposal trends, funding allocations, and voting patterns, making complex governance information accessible through natural-language interaction. All source code, configuration files, and supporting documentation are maintained in a public GitHub repository.
Acceptance Criteria
Users must be able to query Catalyst governance data through natural-language input in an MCP-enabled environment. The system should return accurate and summarized analyses, including proposal insights, voting behavior, and funding trends. Queries must execute reliably, with responses validated against the raw Catalyst API data to ensure correctness, relevance, and clarity for governance participants.
Evidence of Completion
Screenshot/Video of the Cardano Catalyst governance data analysis in MCP-enabled environments. Code and configuration file published to GitHub.
Delivery Month
3
Cost
15000
Progress
60 %
Milestone Title
MCP Server Configuration, Desktop Extension (DXT) Build
Milestone Outputs
The MCP Server is packaged with configuration support for multiple setup methods, including Docker containers and Desktop Extensions (DXT). A Desktop Extension build is prepared and documented, allowing for simple installation and operation within MCP-enabled environments. The outputs include code, configuration scripts, and setup instructions published in the public GitHub repository to ensure reproducibility and ease of adoption.
Acceptance Criteria
Users must be able to install and configure the MCP Server seamlessly through either Docker or the Desktop Extension (DXT). The setup process should be simple, requiring minimal manual configuration, and must result in a fully operational MCP Server with verified connectivity to endpoints. The documentation must provide step-by-step instructions and troubleshooting guidance, ensuring accessibility for both technical and non-technical users.
Evidence of Completion
A demo video or recorded walkthrough showing the MCP Server successfully installed via Docker and marketplace, confirming that both methods produce a working server. The demonstration should highlight ease of setup and operational status of the server after installation. All configuration files, Docker scripts, and DXT build packages must be committed to the project’s public GitHub repository with version history.
Delivery Month
4
Cost
15000
Progress
80 %
Milestone Title
Documentation, Community Testing, Final Release & Publishing to MCP
Milestone Outputs
Comprehensive developer and user documentation is produced, including setup guides, API references, and detailed usage examples. Video tutorials and walkthroughs are created to demonstrate MCP server functionality across multiple environments. Community testing is conducted, and feedback is incorporated into the final release. The MCP Server is formally published to the MCP marketplace for distribution, with all code, configuration files, and documentation available in the public GitHub repository under Apache 2.0.
Acceptance Criteria
The final MCP Server release must be fully documented and published, including technical documentation, installation guides, and user tutorials. Community testers should be able to follow instructions to set up and use the MCP Server successfully. Feedback from testing must be addressed in the release, ensuring improved usability and stability. The server must be available for download and installation through the MCP marketplace, and the GitHub repository must include the complete and final project artifacts.
Evidence of Completion
Public final MCP release on GitHub. MCP published in marketplaces with published documentation available.
Delivery Month
5
Cost
15000
Progress
100 %
Please provide a cost breakdown of the proposed work and resources
The total project budget is 75,000 ADA, allocated to ensure each development stage is fully resourced and tied to measurable outputs.
MCP Server Architecture & GitHub Launch – 15,000 ADA covers initial architecture design, environment setup, and open-source repository configuration to enable transparent, collaborative development.
AI-Assisted Smart Contract Development Tool – 15,000 ADA funds the creation of AI-guided Plutus contract templates, integrated documentation, and onboarding features to lower developer entry barriers.
Catalyst Governance Data & Analytics Tool – 15,000 ADA delivers plain-language insights, proposal search, and analytics dashboards, enabling better decision-making across the Cardano ecosystem.
MCP Server Configuration & Desktop Extension (DXT) Build – 15,000 ADA supports packaging the MCP server as docker container and a one-click Desktop Extension for seamless installation from the MCP marketplace, dramatically reducing setup time.
Documentation, Community Testing & Final Release – 15,000 ADA provides user manuals, API references, and funds robust testing and fixes.
How does the cost of the project represent value for the Cardano ecosystem?
The requested budget for Cardano Model Context Protocol (MCP) Server delivers both immediate and lasting value to the Cardano ecosystem:
The potential of this project to attract a broader user base and developers to Cardano ecosystem outweigh the initial investment, ensuring the project stands as a cost-effective, high-value proposition in the rapidly evolving AI-blockchain landscape.
Terms and Conditions:
Yes
Jon Woodard, CEO
Jon Woodard is the CEO at Wolfram Blockchain Labs, where Jon coordinates the decentralized projects that connect the Wolfram Technology ecosystem to different DLT ecosystems. Previously at Wolfram Research Jon worked on projects at the direction of Wolfram Research CEO Stephen Wolfram and prior to that was a member of the team who worked on the monetization strategies and execution for Wolfram|Alpha. Jon has a background in economics and computational neuroscience. He enjoys cycling in his spare time.
Steph Macurdy, Head of Research and Education
Steph Macurdy has a background in economics, with a focus on complex systems. He attended the Real World Risk Institute in 2019, lead by Nassim Taleb, and has been investing in the crypto asset space since 2015. He previously worked for Tesla as an energy advisor and Cambridge Associates as an investment analyst. Steph is a youth soccer coach in the Philadelphia area and is interested in permaculture.
Gaurav Vishal, Manager
Gaurav Vishal is a Manager in Wolfram Research’s Technical Consulting team with over 6 years of experience in designing and delivering computational applications and enterprise AI solutions. He specializes in full-stack development, data analysis, machine learning, with expertise in microservices architecture and distributed data systems. Since joining Wolfram in 2019, he has led projects ranging from AI-powered tutoring platforms and large-scale data integration pipelines to secure on-premise analytics systems for enterprise and government clients.
Gaurav holds a B.Tech degree from IIT Bhubaneswar, where he earned the Institute’s Silver Medal for academic excellence. He also received the TSIL Research Partner Award for his research on heat transfer in coal-fired Sponge Iron Rotary Kilns. Known for his focus on computational efficiency, system reliability, and client satisfaction, Gaurav has contributed to high-impact technical solutions for Fortune 500 companies, academic institutions, and public sector organizations.
Prateek Soni, Application Developer:
Prateek Soni is an Application Developer at Wolfram, where he developed the Wolfram MCP Server to connect Wolfram technologies with Model Context Protocol clients. A certified AI Practitioner, he has experience in large language model fine-tuning, Retrieval-Augmented Generation, CAG integrations, and automation pipelines. Prateek has a background in computer applications and has worked on AI-powered solutions across healthcare, finance, and education. He enjoys traveling and exploring new places.
Vikram Kumar, Application Developer
Vikram is an Application Developer at Wolfram Research with a background in applying artificial intelligence to healthcare solutions. He holds a B.Tech in Biomedical Engineering from NIT Rourkela and is part of Wolfram’s MCP project, integrating Wolfram tools with applications such as Claude and Cursor. His work also includes implementing blockchain technologies like Zero-Knowledge Proofs (zk-SNARKs). He also has experience as a QA engineer for automated backend testing.
Rahul Kar, Quality Assurance:
Rahul Kar works as a QA Engineer at Wolfram Technology and enjoys ‘breaking’ software so it won’t break for end users. He automates repetitive regression testing with Playwright, TestNG, and Java, while adding a manual touch through exploratory testing to uncover hidden bugs. Previously, as a QA Executive at Vodafone, he worked with Selenium-based automation in telecom domain to ensure product quality. Outside of work, he enjoys reading comics.
Gabriela Guerra Galan, Project Manager
Gabriela Guerra Galan: Gabriela has 15+ years of experience leading projects. She is a certified PMP and Product Owner with bachelor's degree in Mechatronical Engineering, complemented by a master's degree in Automotive Engineering. As the co-founder of Bloinx, a startup that secured funding from the UNICEF Innovation Fund, she has demonstrated a passion for driving innovation and social impact.