Intuition MCP Server - Grant Application

3. Ecosystem Development Grant Applications
1

Project Name: Intuition MCP Server

Team / Individual Name(s): Ludarep & Nald (Full-Stack Blockchain Developers)

Links:

Summary:

Intuition MCP Server is open-source infrastructure that connects AI agents to onchain trust data through the Model Context Protocol. We have built a functional MVP featuring trust scoring, ENS resolution, and an interactive dashboard. This grant funds our contribution to the official Intuition MCP repository: implementing sybil-resistant scoring algorithms (EigenTrust, AgentRank), building comprehensive developer tools and SDKs, creating cross-chain reputation aggregation, and establishing thorough documentation. All code remains open-source and self-hostable, enabling any developer to query trust scores, verify credentials, and discover experts through AI agents.

Project Category:

  • AI Context / MCP (Primary)

  • Developer Tooling

  • Identity / DID / Reputation

Elevator Pitch:

We are building the canonical MCP server that makes Intuition’s trust data accessible to AI agents through open-source infrastructure, not a SaaS product.

Origin Story:

I recognized that AI agents (Claude Desktop, ChatGPT, autonomous systems) had zero native access to onchain trust data. Developers were manually querying attestations and calculating scores, creating fragmented implementations.

Nald and I built a complete MCP server in two weeks. After launching our MVP, we discovered the official Intuition team had a repository in progress. We immediately reached out to collaborate and merge our work into the official ecosystem as long-term core contributors.

Notable Traction:

  • Built functional MVP through two weeks of intensive development

  • Deployed production application at intuitionmcp.xyz using mainnet data

  • Received recognition from Intuition founder regarding our technical approach

  • Active collaboration with core developers including Zet and Saulo

  • Positive engagement from community developers in Intuition Discord

  • Dashboard serves as testing playground for early adopters

Current Users:

Early testing phase with developers in the Intuition Discord community, demonstrating trust score queries, attestation lookups, credential verification using mainnet data. Growing interest from AI agent developers seeking trust infrastructure.

2. What We Are Building

Problem Statement:

AI agents are becoming primary interfaces for information and coordination but lack native access to verifiable trust data, creating critical gaps:

  1. No Trust Context: AI agents cannot assess reputation, verify credentials, or evaluate expertise onchain, limiting their effectiveness in trust-critical scenarios

  2. Developer Friction: Building trust-aware applications requires manual GraphQL queries, custom scoring algorithms, and complex attestation analysis

  3. Sybil Vulnerability: Current trust scoring approaches using basic counting or keyword matching are easily manipulated through coordinated fake attestations

  4. Fragmented Tools: No standardized protocol exists for AI agents to access onchain trust data programmatically

Our Solution:

We are building the canonical open-source MCP server for Intuition that provides AI agents with native trust intelligence. All development contributions go directly to the official Intuition repository at GitHub - 0xIntuition/intuition-mcp-server.

Repository Integration:

All work will be contributed to and maintained within the official Intuition MCP repository. We are building official protocol infrastructure, not a separate competing product. Our goal is to become top contributors to Intuition ecosystem, maintaining and evolving this infrastructure long-term.

Development Phases

Phase 1: Trust Scoring Infrastructure (Weeks 1-4)

Core Deliverables:

  • EigenTrust algorithm implementation with sybil-resistance

  • AgentRank (PageRank-style algorithm for attestation graphs)

  • Transitive trust computation using EAS SDK (3-hop traversal)

  • Custom graph indexer for deep relationship queries

  • Network-effect trust calculation engine

  • Comprehensive algorithm documentation and technical specification

  • Performance benchmarks and optimization reports

  • 95% test coverage on scoring engine

Technical Implementation:

  • Integration with EAS transitive-trust-SDK for proven algorithms

  • Graph database optimization for network traversal

  • Caching strategies for frequently queried trust scores

  • Attack simulation testing for sybil-resistance validation

Success Criteria:

  • Trust scores demonstrably resistant to coordinated attack simulations

  • Transitive trust queries complete in under 2 seconds for 3-hop relationships

  • Algorithm documentation published with full mathematical specifications

  • Successfully merged into official Intuition MCP repository

  • Peer review completed by Intuition technical team

Phase 2: Developer Experience & Tooling (Weeks 5-8)

Core Deliverables:

  • Interactive documentation site with live code examples and API playground

  • TypeScript/JavaScript SDK with comprehensive type definitions (npm package)

  • Python client library with async support and error handling (PyPI package)

  • 5+ integration guides covering Claude Desktop, ChatGPT, LangChain, and autonomous agents

  • 4+ production-ready example applications that developers can fork and deploy

  • Professional educational content including 6-8 video tutorials and 5-6 technical blog posts

  • API reference documentation with interactive testing interface

  • Troubleshooting guides and common integration patterns

Example Applications:

  • Trust-gated content access system

  • Hiring tool with credential verification

  • Reputation dashboard with analytics

  • Expert discovery interface

Success Criteria:

  • Documentation site operational with 30+ interactive code examples

  • SDKs published to npm and PyPI with comprehensive test suites

  • Time-to-first-query reduced to under 5 minutes for new developers

  • Positive feedback from 15+ developers during testing phase

  • Integration templates demonstrably reduce development time by 60% or more

Phase 3: Cross-Chain Reputation System (Weeks 9-12)

Core Deliverables:

  • Multi-chain identity aggregation supporting Ethereum, Base, Arbitrum, and Optimism

  • ENS domain resolution integrated with trust data

  • Farcaster social proof integration and verification

  • Lens Protocol profile aggregation

  • Unified reputation scoring algorithm across multiple data sources

  • Exportable reputation passports in JSON format with shareable links

  • RESTful API endpoints for third-party integrations

  • MCP tool for automated reputation passport generation

Technical Implementation:

  • Cross-chain RPC integration for data fetching

  • Identity resolution across multiple networks

  • Social graph analysis from Farcaster and Lens

  • Reputation score normalization across chains

Success Criteria:

  • Successfully aggregates identity data from 4+ blockchain networks

  • Reputation passports generated with 85%+ data accuracy

  • API handles 300+ passport generation requests per hour

  • Integration operational with 2+ social proof platforms

  • Positive user testing feedback from 10+ community members

Future Enhancements (Post-Grant):

The following features may be proposed and developed after successful completion of core infrastructure, subject to community feedback and ecosystem needs:

  • .trust domain resolution (pending protocol readiness)

  • Additional blockchain network integrations

  • Advanced analytics and visualization tools

  • Real-time attestation monitoring systems

  • Custom trust metric creation API

  • Enhanced caching and performance optimization

  • Additional social proof platform integrations

These enhancements would maintain the open-source, self-hostable nature of the core infrastructure.

Stage of Development:

MVP Live on Mainnet → Active Collaboration with Official Team → Building Core Infrastructure

Technical Architecture:

image
image1436×1128 64.2 KB

Core Integrations:

  • MCP Protocol: Native integration for AI agent communication

  • EAS Transitive Trust SDK: Proven sybil-resistant scoring algorithms

  • Intuition GraphQL API: Mainnet attestation data queries

  • Custom Graph Indexer: Deep relationship queries and network traversal

  • Web3 Libraries: ethers.js for blockchain interactions

  • ENS: Domain name resolution for .eth addresses

  • Farcaster: Social proof and identity verification

  • Lens Protocol: Decentralized social graph data

  • Cross-chain RPC: Multi-chain identity aggregation

Security Considerations:

  • All code is open source and publicly auditable

  • Read-only operations for core functionality with no private key management

  • Comprehensive input validation and sanitization

  • Rate limiting on API endpoints to prevent abuse

  • Sybil-resistant algorithms protect against score manipulation

  • Secure credential verification without exposing private information

  • Following MCP security best practices for agent interactions

3. Team & Execution Ability

Team Backgrounds:

Ludarep (Lead Developer):

  • Full-stack blockchain developer specializing in DeFi protocols, zero-knowledge applications, and AI integrations

  • Built ShadowRep, an FHE-based confidential reputation system successfully deployed to Sepolia testnet with React frontend

  • Created Aztec Dark Market, a privacy-preserving trading platform using Aztec zero-knowledge technology, overcoming significant CPU compatibility challenges to deploy contracts to devnet

  • Developed PolyBot, extensive Polymarket trading infrastructure including automated bots, web dashboards, and analytics platforms

  • Extensive experience with Next.js, TypeScript, Solidity, GraphQL, and blockchain infrastructure

  • Active contributor to web3 ecosystem with GitHub username “rudazy”

  • Strong focus on developer experience and comprehensive documentation

Nald (Co-Developer & Technical Architect):

  • Blockchain developer with deep expertise in smart contract development and system architecture

  • Close collaborator on all major projects with proven track record

  • Specializes in performance optimization and scalability solutions

  • Experience with complex data indexing and backend infrastructure development

Team Track Record:

  • Built functional Intuition MCP MVP through two weeks of intensive development

  • Deployed multiple production-ready applications across various blockchain ecosystems

  • Strong commitment to documentation and developer experience

  • Active community engagement and technical support

  • Experience shipping complex features including cross-chain integrations and zero-knowledge implementations

Execution Proof:

1. Intuition MCP Server -
https://www.intuitionmcp.xyz | https://github.com/rudazy/Intuition-
Live production with trust scoring, ENS resolution, mainnet integration.

image
image1362×613 92.5 KB

2. ShadowRep -
https://shadowrep.vercel.app/ | https://github.com/rudazy/shadowrep
FHE reputation on Sepolia testnet.

image
image1366×605 89.1 KB

3. Aztec Dark Market -
https://github.com/rudazy/Aztec- | https://github.com/rudazy/aztec-dark-market-app
ZK trading platform on Aztec devnet.

image
image1280×550 76 KB

4. PolyBot -
https://www.polybot.finance/ | https://github.com/rudazy/polybot
Polymarket trading infrastructure with 24/7 automation.

image
image1366×594 79.9 KB

Commitment Level:

Full-time commitment for the 12-week grant duration. Post-grant, we commit to long-term part-time maintenance and feature development as core contributors to the official Intuition ecosystem, with monthly feature releases and continuous community support. Our intention is to become top contributors to Intuition infrastructure over the coming years.

Team Structure:

  • Ludarep: Trust algorithms, documentation, smart contract integration, community engagement, developer relations

  • Nald: Infrastructure development, custom indexer, API optimization, performance tuning, backend architecture

Technical Advisors:

  • Intuition core development team providing technical guidance on protocol integration and best practices

  • Zet and Saulo offering developer feedback on trust scoring approaches and ecosystem alignment

  • Community developers providing testing feedback and real-world use case insights

Prior Blockchain & AI Experience:

  • Web3 Development: 3+ years building DeFi protocols, zero-knowledge applications, prediction market infrastructure, and blockchain indexers

  • AI Integration: Built AI-powered systems, Claude Desktop integrations, and autonomous agent frameworks

  • Developer Tools: Created comprehensive dashboards, RESTful APIs, and SDK libraries for blockchain protocols

  • Community Building: Active participation in hackathons, Discord communities, and open-source contributions

  • Cross-chain Development: Worked extensively with Ethereum, Base, Arbitrum, Optimism, and custom Layer 2 solutions

4. Grant Request & Milestones

Amount Requested: 24,000 USD

(Or equivalent value in TRUST tokens)

Budget Allocation:

  • Phase 1: 10,000 USD (Trust Scoring Infrastructure - Weeks 1-4)

  • Phase 2: 8,000 USD (Developer Experience & Tooling - Weeks 5-8)

  • Phase 3: 6,000 USD (Cross-Chain Reputation System - Weeks 9-12)

Total: 24,000 USD over 12 weeks

Detailed Budget Breakdown

Phase 1: Trust Scoring Infrastructure - 10,000 USD (Weeks 1-4)

Budget Allocation:

  • Algorithm development and implementation: 5,000 USD

  • Custom indexer development: 2,500 USD

  • Testing, benchmarking, and optimization: 1,500 USD

  • Documentation and technical specifications: 1,000 USD

Deliverables:

  • EigenTrust algorithm implementation with comprehensive test coverage

  • AgentRank (PageRank for attestations) with convergence optimization

  • Transitive trust computation supporting 3-hop relationship traversal

  • Custom graph indexer optimized for deep relationship queries

  • Network-effect trust calculation engine

  • Mathematical model documentation and algorithm whitepaper

  • Performance benchmarks demonstrating query efficiency

  • Attack simulation results validating sybil-resistance

Success Criteria:

  • Trust scores demonstrably resistant to coordinated attack simulations with documented test results

  • Transitive trust queries return results in under 2 seconds for 3-hop relationships

  • Algorithm documentation published with complete mathematical specifications

  • 95% or higher test coverage on scoring engine

  • Code successfully merged into official Intuition MCP repository

  • Peer review completed and approved by Intuition technical team

Phase 2: Developer Experience & Tooling - 8,000 USD (Weeks 5-8)

Budget Allocation:

  • SDK development (TypeScript & Python): 3,000 USD

  • Documentation site and interactive examples: 2,000 USD

  • Educational content (videos, blogs, tutorials): 2,000 USD

  • Example applications and templates: 1,000 USD

Deliverables:

  • Interactive documentation site with live code examples and API testing playground

  • TypeScript/JavaScript SDK with comprehensive type definitions published to npm

  • Python client library with async support and error handling published to PyPI

  • 5+ detailed integration guides covering major AI platforms

  • 4+ production-ready example applications with deployment instructions

  • 6-8 professional video tutorials covering all integration scenarios

  • 5-6 technical blog posts explaining architecture and best practices

  • API reference documentation with interactive testing capabilities

  • Troubleshooting guides and common integration pattern documentation

Success Criteria:

  • Documentation site operational with minimum 30 interactive code examples

  • SDKs published to npm and PyPI with comprehensive test suites and CI/CD

  • New developers achieve first successful query in under 5 minutes

  • Positive feedback collected from 15+ developers during testing phase

  • Integration templates demonstrably reduce development time by 60% or more compared to building from scratch

  • Video tutorials achieve clarity scores above 4.5/5 from community feedback

Phase 3: Cross-Chain Reputation System - 6,000 USD (Weeks 9-12)

Budget Allocation:

  • Multi-chain integration development: 2,500 USD

  • Social proof platform integrations: 1,500 USD

  • Reputation passport system: 1,500 USD

  • Testing and optimization: 500 USD

Deliverables:

  • Multi-chain identity aggregation supporting Ethereum, Base, Arbitrum, and Optimism

  • ENS domain resolution integrated with trust score data

  • Farcaster social proof integration and verification system

  • Lens Protocol profile aggregation and analysis

  • Unified reputation scoring algorithm normalizing data across sources

  • Exportable reputation passports in JSON format with shareable public links

  • RESTful API endpoints enabling third-party integrations

  • MCP tool for automated reputation passport generation

  • Cross-chain identity resolution system

Success Criteria:

  • System successfully aggregates identity data from 4+ blockchain networks

  • Reputation passports generated with 85% or higher data accuracy

  • API reliably handles 300+ passport generation requests per hour

  • Integration operational with minimum 2 social proof platforms (Farcaster, Lens)

  • Positive user testing feedback from 10+ community members

  • Cross-chain resolution correctly identifies same entity across networks

Total Development Timeline: 12 weeks (4 weeks per phase)

Each phase delivers production-ready code, comprehensive documentation, and measurable success criteria. Development is structured to build upon previous phases while delivering standalone value at each milestone. All code is contributed to the official Intuition MCP repository throughout development.

Key Dependencies:

  • Intuition mainnet GraphQL API stability and continued uptime

  • EAS transitive-trust-SDK compatibility and maintenance

  • MCP protocol specification compliance and stability

  • Community feedback during testing phases

  • Third-party API availability (ENS, Farcaster, Lens)

Risk Assessment & Mitigation:

Risk Likelihood Impact Mitigation Strategy
GraphQL API changes Medium High Version pinning, fallback strategies, regular compatibility testing
Algorithm implementation complexity Medium Medium Phased implementation, expert consultation, iterative testing
Slower than expected adoption Low Medium Strong documentation, comprehensive examples, active community support
Security vulnerabilities discovered Low High Regular security audits, community bug bounty program, open source review
Third-party API downtime Low Low Intelligent caching strategies, graceful degradation, multiple data providers
Performance issues at scale Medium Medium Load testing, continuous optimization, horizontal scaling architecture

5. Intuition Ecosystem Alignment

Why Intuition:

Intuition is the only protocol providing composable onchain attestations combined with economic signals through staking, making it the ideal foundation for AI-accessible trust infrastructure. The protocol architecture of atoms, triples, and vaults is specifically designed for programmatic trust queries.

How We Leverage Intuition Primitives:

Atoms (Identity & Concepts):

  • Query atoms to resolve addresses to verified identities

  • Traverse atom relationships to understand trust networks

  • Utilize atom metadata for domain resolution and profile information

  • Create new atoms for AI agent identities and custom trust concepts

Triples (Attestations):

  • Core foundation of trust scoring through subject-predicate-object relationship analysis

  • Weight triples based on predicate types (verified credentials, expertise markers, trust relationships)

  • Aggregate triples to calculate comprehensive reputation scores

  • Filter triples by timestamp, stake amount, and creator reputation for nuanced analysis

  • Track attestation patterns over time for trend detection and anomaly identification

Signal (Economic Weight):

  • Utilize vault stakes as primary trust signals where higher stake indicates higher confidence

  • Implement minimum stake thresholds to filter low-quality attestations

  • Calculate position-weighted scores where total user position matters

  • Monitor signal changes over time for reputation trend analysis

  • Enable economic games around attestation accuracy

Knowledge Graph:

  • Traverse graph for transitive trust computation enabling reputation propagation through networks

  • Discover expert clusters through graph analysis algorithms

  • Identify trust communities and reputation networks

  • Map influence patterns across the ecosystem

  • Calculate network-effect scores based on graph position using AgentRank

MCP Integration:

  • Native MCP server makes Intuition data universally accessible to all AI agents

  • Standardized tool interface (getTrustScore, verifyCredential, findExperts, generatePassport)

  • Real-time queries without requiring custom API integration for each agent platform

  • Positions Intuition as the default trust layer for AI agent infrastructure

Why It Must Be Built on Intuition:

  1. Composable Attestations: No other protocol offers standardized trust primitives AI can query with this flexibility

  2. Economic Signals: Staking provides crucial sybil-resistance essential for reliable trust scoring

  3. Network Effects: Intuition growing knowledge graph creates compounding value where more attestations enable better trust calculations in a virtuous cycle

  4. Protocol Primitives: Atoms, triples, and vaults are architected specifically for programmatic trust queries, unlike general-purpose attestation systems

  5. Decentralized and Verifiable: AI agents require provable trust data that cannot be manipulated by centralized authorities

No other protocol combines composable attestations, economic signals, native identity primitives, and a growing knowledge graph in a manner that makes comprehensive, programmatic trust computation viable at scale.

Which Intuition Primitives We Use:

  • Atoms: Identity resolution, concept mapping, profile data, agent registration

  • Triples: Core attestation data for all trust calculations and verification

  • Signal/Vaults: Economic weight for scoring confidence and sybil-resistance

  • Knowledge Graph: Transitive trust and relationship mapping

  • DID/Agent Registry: Identity verification for AI agents and users

  • MCP: Native protocol integration for AI accessibility

We leverage Intuition complete primitive stack to build comprehensive trust infrastructure, not merely querying surface-level data.

Data Structures & Schemas:

New Schemas We Will Introduce:

1. AgentRank Score Schema:

Subject: [Agent DID/Address]
Predicate: "has_agentrank_score"
Object: {
  rank: number,
  pagerank_score: number,
  network_position: number,
  inbound_trust_count: number,
  outbound_trust_count: number,
  damping_factor: number,
  calculated_at: timestamp,
  convergence_iterations: number
}

AgentRank Explanation:

AgentRank implements a PageRank-style algorithm for AI agents based on Intuition attestation graph. Agents with more inbound trust from high-ranked agents receive higher scores, providing sybil-resistant reputation that accounts for network effects. This approach goes beyond simple attestation counting to capture an agent’s position and influence within the trust network.

2. Trust Score Schema:

Subject: [Address/DID]
Predicate: "has_trust_score"
Object: {
  overall_score: number,
  credibility: number,
  expertise: number,
  reliability: number,
  calculated_at: timestamp,
  algorithm_version: string,
  confidence_interval: number
}

3. Reputation Passport Schema:

Subject: [Address/DID]
Predicate: "reputation_passport"
Object: {
  chains: array,
  social_proof: object,
  trust_score: number,
  attestation_summary: object,
  generated_at: timestamp
}

4. AI Agent Identity Schema:

Subject: [Agent DID]
Predicate: "ai_agent_identity"
Object: {
  agent_type: string,
  capabilities: array,
  trust_threshold: number,
  registered_at: timestamp
}

Triple Patterns (Natural Language Format):

Our system creates and queries attestations using intuitive natural language predicates that remain human-readable while maintaining machine-processability:

Credential Verification:

  • “vitalik.eth” → “is verified as” → “Ethereum Core Developer”

  • “0x123…” → “holds credential” → “Solidity Expert Certificate”

Expert Discovery:

  • “alice.eth” → “has expertise in” → “DeFi Protocol Design”

  • “bob.eth” → “is recognized for” → “Smart Contract Security Auditing”

Trust Relationships:

  • “agent_claude” → “trusts” → “0xabc… for governance advice”

  • “trading_bot” → “delegates to” → “security_expert.eth”

Transparency & Provenance:

  • “trust_score_v2” → “calculated from” → “[list of attestation IDs]”

  • “reputation_metric” → “based on” → “AgentRank algorithm v1.2”

Identity Aggregation:

  • “user_passport_123” → “aggregates identity from” → “[Ethereum, Base, Farcaster]”

  • “0x456…” → “has unified reputation across” → “4 blockchain networks”

Network Activity Impact:

Every feature we build directly increases Intuition ecosystem activity:

  • Trust Score Queries: Thousands of GraphQL requests daily, increasing node utilization and demonstrating data utility

  • Developer Adoption: More applications built on the infrastructure means exponentially more users creating attestations

  • Cross-Chain Passports: Reputation aggregation drives attestation creation across multiple networks

  • Open-Source Contributions: Community improvements and extensions create sustained development activity

  • AI Agent Integration: New use cases for attestations drive organic protocol growth

Expected Network Growth (Conservative Projections):

  • Month 1: 1,000-2,000 trust score queries establishing baseline usage

  • Month 3: 10,000+ queries, 20+ active developers, initial production integrations

  • Month 6: 50,000+ queries, 50+ developers, 5+ production applications generating attestations

  • Month 12: Self-sustaining growth through community contributions and ecosystem expansion

Each metric compounds: more queries drive more development, which attracts more users, who create more attestations, improving data quality and attracting additional applications in a virtuous cycle.

Long-Term Ecosystem Contribution (12-24 Months):

Post-Grant Commitment:

We are committed to becoming top contributors to Intuition’s infrastructure over the long term. Our post-grant contributions include:

Ongoing Maintenance:

  • Monthly feature releases and improvements

  • Regular security audits and vulnerability assessments

  • Performance optimization and scaling enhancements

  • Bug fixes and issue resolution

  • Dependency updates and compatibility maintenance

Community Support:

  • Active developer relations and technical support

  • Community workshops and educational sessions

  • Integration assistance for projects building on the infrastructure

  • Documentation updates reflecting ecosystem evolution

Research & Development:

  • Research publications on trust algorithms and network effects

  • Open-source standards development for AI-trust infrastructure interoperability

  • Collaboration with academic institutions on reputation systems

  • Continuous algorithm improvements based on real-world data

Ecosystem Growth:

  • Partnership development with AI platforms and protocols

  • Technical blog posts and integration case studies

  • Conference presentations and hackathon participation

  • Mentoring new developers joining the Intuition ecosystem

Our goal is not merely to deliver a grant, but to become essential infrastructure contributors who help shape the future of onchain trust for years to come.

6. Open Source Commitment

License: Apache 2.0 or MIT (matching Intuition licensing choice)

What Remains Open Source:

  • All trust scoring algorithms (EigenTrust, AgentRank, transitive trust)

  • Complete MCP server implementation

  • All SDKs (TypeScript, Python)

  • Comprehensive documentation and examples

  • Graph indexer implementation

  • Integration templates and example applications

  • Testing frameworks and benchmarking tools

Self-Hostable Architecture:

Any developer or organization can run their own instance of the MCP server without permission or fees. The architecture is designed for easy deployment and maintenance.

Community-Maintained:

We welcome contributions from day one. Development follows open-source best practices: contribution guidelines, code review, public issue tracking, transparent roadmap, and regular updates.

No Vendor Lock-In:

The infrastructure contains no proprietary features or vendor-specific dependencies. All components use standard, well-documented protocols and interfaces.

Sustainability Model:

The core MCP server, algorithms, and SDKs remain free and self-hostable indefinitely. Any future commercial activities (consulting, hosted instances, premium support) will be clearly separated from core infrastructure and entirely optional.

7. Additional Materials

Live Demo: https://www.intuitionmcp.xyz

Source Code: https://github.com/rudazy/Intuition-

Contact Email: Ludaluda134@gmail.com

8. Applicant Attestation

I confirm that all information submitted in this application is accurate and complete. I commit to delivering these milestones as open-source contributions to the official Intuition MCP repository and becoming a long-term top contributor to Intuition protocol infrastructure.

Applicant Name: Ludarep (in collaboration with Nald)

Wallet Address: 0x0E61743E1A36f5e74B58989028ECc5B73fc7379b

Date: December 4, 2024

In Summary:

This grant funds 12 weeks of focused infrastructure development: trust scoring algorithms (EigenTrust, AgentRank), comprehensive developer tools and SDKs, and cross-chain reputation aggregation. All work is contributed to the official Intuition MCP repository as open-source, self-hostable infrastructure that positions Intuition as the definitive trust layer for AI agents.

We are committed to delivering high-quality infrastructure and becoming top long-term contributors to the Intuition ecosystem.

Grant Amount: 24,000 USD