Skip to main content
Glama
Klever MCP Server
by klever-io

Klever MCP Server

A Model Context Protocol (MCP) server tailored for Klever blockchain smart contract development. This server maintains and serves contextual knowledge including code patterns, best practices, and runtime behavior for developers working with the Klever VM SDK.

Features

  • šŸš€ Triple Mode Operation: Run as HTTP API server, MCP stdio server, or public hosted MCP server

  • šŸ’¾ Flexible Storage: In-memory or Redis backend support

  • šŸ” Smart Context Retrieval: Query by type, tags, or contract type

  • šŸ“ Automatic Pattern Extraction: Parse Klever contracts to extract examples and patterns

  • šŸŽÆ Relevance Ranking: Intelligent scoring and ranking of context

  • šŸ”„ Live Updates: Add and update context in real-time

  • šŸ›”ļø Type Safety: Full TypeScript with Zod validation

  • šŸ“š Comprehensive Knowledge Base: Pre-loaded with Klever VM patterns, best practices, and examples

  • šŸ”§ Contract Validation: Automatic detection of common issues and anti-patterns

  • šŸš€ Deployment Scripts: Ready-to-use scripts for contract deployment, upgrade, and querying

Related MCP server: code-graph-rag-mcp

Quick Start

Install and run instantly via npx — no cloning required:

npx -y @klever/mcp-server

Or connect to the hosted public server:

claude mcp add -t http klever-vm https://mcp.klever.org/mcp

See MCP Client Integration for client-specific configuration.

Architecture

mcp-klever-vm/
ā”œā”€ā”€ src/
│   ā”œā”€ā”€ api/          # HTTP API routes with validation
│   ā”œā”€ā”€ context/      # Context management service layer
│   ā”œā”€ā”€ mcp/          # MCP protocol server implementation
│   ā”œā”€ā”€ parsers/      # Klever contract parser and validator
│   ā”œā”€ā”€ storage/      # Storage backends (memory/Redis)
│   │   ā”œā”€ā”€ memory.ts # In-memory storage with size limits
│   │   └── redis.ts  # Redis storage with optimized queries
│   ā”œā”€ā”€ types/        # TypeScript type definitions
│   ā”œā”€ā”€ utils/        # Utilities and ingestion tools
│   └── knowledge/    # Modular knowledge base (95+ entries)
│       ā”œā”€ā”€ core/     # Core concepts and imports
│       ā”œā”€ā”€ storage/  # Storage patterns and mappers
│       ā”œā”€ā”€ events/   # Event handling and rules
│       ā”œā”€ā”€ tokens/   # Token operations and decimals
│       ā”œā”€ā”€ modules/  # Built-in modules (admin, pause)
│       ā”œā”€ā”€ tools/    # CLI tools (koperator, ksc)
│       ā”œā”€ā”€ scripts/  # Helper scripts
│       ā”œā”€ā”€ examples/ # Complete contract examples
│       ā”œā”€ā”€ errors/   # Error patterns
│       ā”œā”€ā”€ best-practices/ # Optimization and validation
│       └── documentation/  # API reference
ā”œā”€ā”€ tests/            # Test files
└── docs/             # Documentation

Key Improvements Made

  1. Storage Layer

    • Added memory limits to prevent OOM in InMemoryStorage

    • Optimized Redis queries to avoid O(N) KEYS command

    • Added atomic transactions for Redis operations

    • Improved error handling and validation

  2. API Security

    • Added input validation for all endpoints

    • Batch operation size limits

    • Proper error responses without leaking internals

    • Environment-aware error messages

  3. Type Safety

    • Centralized schema validation

    • Proper TypeScript interfaces for options

    • Runtime validation of stored data

  4. Performance

    • Batch operations using Redis MGET

    • Index-based queries instead of full scans

    • Optimized count operations

Installation

  1. Clone the repository:

git clone https://github.com/klever-io/mcp-klever-vm.git
cd mcp-klever-vm
  1. Install dependencies:

pnpm install
  1. Copy environment configuration:

cp .env.example .env
  1. Install Klever SDK tools (required for transactions):

chmod +x scripts/install-sdk.sh && ./scripts/install-sdk.sh
  1. Build the project:

pnpm run build

Configuration

Edit .env file to configure the server:

# Server Mode (http, mcp, or public)
MODE=http

# HTTP Server Port (only for http mode)
PORT=3000

# Storage Backend (memory or redis)
STORAGE_TYPE=memory

# Maximum contexts for in-memory storage (default: 10000)
MEMORY_MAX_SIZE=10000

# Redis URL (only if STORAGE_TYPE=redis)
REDIS_URL=redis://localhost:6379

# Node environment (development or production)
NODE_ENV=development

MCP Client Integration

Claude Code

# Add via npx (recommended)
claude mcp add klever-vm -- npx -y @klever/mcp-server

# Or connect to the public hosted server
claude mcp add -t http klever-vm https://mcp.klever.org/mcp

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "klever-vm": {
      "command": "npx",
      "args": ["-y", "@klever/mcp-server"]
    }
  }
}

For detailed setup, see the Claude Desktop Installation Guide.

Cursor

Add to your Cursor MCP settings (.cursor/mcp.json):

{
  "mcpServers": {
    "klever-vm": {
      "command": "npx",
      "args": ["-y", "@klever/mcp-server"]
    }
  }
}

VS Code (GitHub Copilot)

Add to .vscode/mcp.json in your project:

{
  "servers": {
    "klever-vm": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@klever/mcp-server"]
    }
  }
}

For detailed setup, see the VS Code Installation Guide.

Public MCP Server

The Klever MCP Server can be hosted as a public shared service, allowing any developer to connect without running it locally.

Connecting to the Public Server

# Add permanently (user-level)
claude mcp add -t http klever-vm https://mcp.klever.org/mcp

# Add for current project only
claude mcp add -t http -s project klever-vm https://mcp.klever.org/mcp

Available Tools (Public Mode)

The public server exposes a read-only subset of tools for security:

Tool

Description

query_context

Search the Klever VM knowledge base

get_context

Retrieve a specific context by ID

find_similar

Find contexts similar to a given context

get_knowledge_stats

Get knowledge base statistics

enhance_with_context

Enhance queries with relevant Klever VM context

Write operations (add_context) and shell-based tools (init_klever_project, add_helper_scripts) are disabled in public mode.

Self-Hosting with Docker

# Build and run
docker build -t mcp-klever-vm .
docker run -p 3000:3000 mcp-klever-vm

# Or using docker compose
docker compose up -d

Then connect:

claude mcp add -t http klever-vm-local http://localhost:3000/mcp

Self-Hosting without Docker

pnpm install
pnpm run build
pnpm run start:public

Environment Variables (Public Mode)

Variable

Default

Description

MODE

http

Set to public for hosted mode

PORT

3000

Server port

CORS_ORIGINS

(unset)

Comma-separated allowed origins. Unset or * allows all origins

RATE_LIMIT_MCP

60

MCP endpoint requests/min per IP

RATE_LIMIT_API

30

API endpoint requests/min per IP

BODY_SIZE_LIMIT

1mb

Max request body size

Deployment Notes

For production at mcp.klever.org:

  • Deploy Docker container behind a reverse proxy (nginx/Caddy/cloud LB) for TLS termination

  • Ensure proxy passes mcp-session-id header and supports SSE (disable response buffering)

  • Single instance is sufficient as the server is read-only with an in-memory knowledge base

  • Consider Cloudflare for DDoS protection (SSE is supported)

Usage

Knowledge Base Loading

The server automatically loads the Klever knowledge base based on your storage type:

Memory Storage (Default)

  • Knowledge is automatically loaded when the server starts

  • No need to run pnpm run ingest separately

  • Data exists only while server is running

  • Best for development and testing

Redis Storage

# First, ingest the knowledge base (one time)
pnpm run ingest

# Then start the server
pnpm run dev
  • Knowledge persists in Redis database

  • Survives server restarts

  • Best for production use

This will load:

  • Smart contract templates and examples

  • Annotation rules and best practices

  • Storage mapper patterns and comparisons

  • Deployment and query scripts

  • Common errors and solutions

  • Testing patterns

  • API reference documentation

Running as HTTP Server

# Development mode
pnpm run dev

# Production mode
pnpm run build && pnpm start

The HTTP API will be available at http://localhost:3000/api

Running as MCP Server

MODE=mcp pnpm start

Use with any MCP-compatible client.

API Endpoints

POST /api/context

Ingest new context into the system.

{
  "type": "code_example",
  "content": "contract code here",
  "metadata": {
    "title": "Token Contract Example",
    "description": "ERC20-like token implementation",
    "tags": ["token", "fungible"],
    "contractType": "token"
  }
}

GET /api/context/:id

Retrieve specific context by ID.

POST /api/context/query

Query contexts with filters.

{
  "query": "transfer",
  "types": ["code_example", "best_practice"],
  "tags": ["token"],
  "contractType": "token",
  "limit": 10,
  "offset": 0
}

PUT /api/context/:id

Update existing context.

DELETE /api/context/:id

Delete context.

GET /api/context/:id/similar

Find similar contexts.

POST /api/context/batch

Batch ingest multiple contexts.

MCP Tools

When running as MCP server, the following tools are available:

  • query_context: Search for relevant Klever development context

  • add_context: Add new context to the knowledge base

  • get_context: Retrieve specific context by ID

  • find_similar: Find contexts similar to a given context

  • get_knowledge_stats: Get statistics about the knowledge base

  • init_klever_project: Initialize a new Klever smart contract project with helper scripts

  • enhance_with_context: Automatically enhance queries with relevant Klever VM context

Context Types

  • code_example: Working code snippets and examples (Rust smart contract code)

  • best_practice: Recommended patterns and practices

  • security_tip: Security considerations and warnings

  • optimization: Performance optimization techniques

  • documentation: General documentation and guides

  • error_pattern: Common errors and solutions

  • deployment_tool: Deployment scripts and utilities (bash scripts, tools)

  • runtime_behavior: Runtime behavior explanations

Pre-loaded Knowledge Base

The MCP server includes a comprehensive knowledge base with 95+ entries organized into 11 categories:

Critical Patterns

  • Payment handling and token operations

  • Decimal conversions and calculations

  • Event emission and parameter rules

  • CLI tool usage and best practices

Contract Patterns & Examples

  • Basic contract structure templates

  • Complete lottery game implementation

  • Staking contract with rewards

  • Cross-contract communication patterns

  • Remote storage access patterns

  • Token mapper helper modules

Development Tools

  • Koperator: Complete CLI reference with argument encoding

  • KSC: Build commands and project setup

  • Deployment, upgrade, and query scripts

  • Interactive contract management tools

  • Common utilities library (bech32, network management)

Storage & Optimization

  • Storage mapper selection guide with performance comparisons

  • Namespace organization patterns

  • View endpoints for efficient queries

  • Gas optimization techniques

  • OptionalValue vs Option patterns

Best Practices & Security

  • Input validation patterns

  • Error handling strategies

  • Admin and pause module usage

  • Access control patterns

  • Common mistakes and solutions

Ingesting Contracts

Use the built-in ingestion utilities to parse and import Klever contracts:

import { StorageFactory } from './storage/index.js';
import { ContextService } from './context/service.js';
import { ContractIngester } from './utils/ingest.js';

const storage = StorageFactory.create('memory');
const contextService = new ContextService(storage);
const ingester = new ContractIngester(contextService);

// Ingest a single contract
await ingester.ingestContract('./path/to/contract.rs', 'AuthorName');

// Ingest entire directory
await ingester.ingestDirectory('./contracts', 'AuthorName');

// Add common patterns
await ingester.ingestCommonPatterns();

Development

# Run tests
pnpm test

# Lint code
pnpm run lint

# Format code
pnpm run format

# Watch mode
pnpm run dev

# Ingest/update knowledge base
pnpm run ingest

Contract Validation

The server can automatically validate Klever contracts and detect issues:

import { KleverValidator } from './parsers/validators.js';

const issues = KleverValidator.validateContract(contractCode);
// Returns array of detected issues with suggestions

Validation checks include:

  • Event annotation format (double quotes, camelCase)

  • Managed type API parameters

  • Zero address validation in transfers

  • Optimal storage mapper selection

  • Module naming conventions

Example Use Cases

1. Smart Contract Development Assistant

Integrate with your IDE to provide context-aware suggestions for Klever contract development.

2. Code Review Tool

Automatically check contracts against best practices and security patterns.

3. Learning Platform

Provide examples and explanations for developers learning Klever development.

4. Documentation Generator

Extract and organize contract documentation automatically.

Project Specifications and Examples

For complete project implementation examples and specifications, see:

  • Project Specification Template - A fill-in template for specifying Klever smart contract projects. Guides AI assistants through MCP knowledge discovery, task tracking, and phased implementation. Includes a KleverDice example.

Project Initialization

The MCP server includes a powerful project initialization tool that creates a new Klever smart contract project with all necessary helper scripts.

Using the init_klever_project Tool

When connected via MCP, use the init_klever_project tool:

{
  "name": "my-token-contract",
  "template": "empty",
  "noMove": false
}

Parameters:

  • name (required): The name of your contract

  • template (optional): Template to use (default: "empty")

  • noMove (optional): If true, keeps project in subdirectory (default: false)

Generated Helper Scripts

The tool creates the following scripts in the scripts/ directory:

  • build.sh: Builds the smart contract

  • deploy.sh: Deploys to Klever testnet with auto-detection of contract artifacts

  • upgrade.sh: Upgrades existing contract (auto-detects from history.json)

  • query.sh: Query contract endpoints with proper encoding/decoding

  • test.sh: Run contract tests

  • interact.sh: Shows usage examples and available commands

Example Workflow

  1. Initialize project:

    # Via MCP tool
    init_klever_project({"name": "my-contract"})
  2. Build contract:

    ./scripts/build.sh
  3. Deploy to testnet:

    ./scripts/deploy.sh
  4. Query contract:

    ./scripts/query.sh --endpoint getSum
    ./scripts/query.sh --endpoint getValue --arg myKey
  5. Upgrade contract:

    ./scripts/upgrade.sh

All deployment history is tracked in output/history.json for easy reference.

Automatic Context Enhancement

The MCP server can automatically enhance queries with relevant Klever VM context. This ensures your MCP client always has access to the most relevant information.

Using Context Enhancement

Use the enhance_with_context tool to automatically add relevant context to any query:

{
  "tool": "enhance_with_context",
  "arguments": {
    "query": "How do I create a storage mapper?",
    "autoInclude": true
  }
}

This will:

  1. Extract relevant keywords from the query

  2. Search the knowledge base for matching contexts

  3. Return an enhanced query with context included

  4. Provide metadata about what was found

Integration Pattern

For MCP clients that want to always check Klever context first:

// Always enhance Klever-related queries
if (query.match(/klever|kvm|smart contract|endpoint/i)) {
  const enhanced = await callTool('enhance_with_context', { query });
  // Use enhanced.enhancedQuery for processing
}

The context enhancement feature automatically enriches queries with relevant Klever VM knowledge from the comprehensive knowledge base.

Integration Examples

VS Code Extension

// Query for token transfer examples
const response = await fetch('http://localhost:3000/api/context/query', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    query: 'transfer',
    types: ['code_example'],
    contractType: 'token'
  })
});

CLI Tool

# Using curl to add context
curl -X POST http://localhost:3000/api/context \
  -H "Content-Type: application/json" \
  -d '{
    "type": "security_tip",
    "content": "Always check for zero address",
    "metadata": {
      "title": "Zero Address Check",
      "tags": ["security", "validation"]
    }
  }'

Contributing

Contributions are welcome! Please:

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Add tests

  5. Submit a pull request

License

MIT License - see LICENSE file for details

Acknowledgments

Available Tools

23 tools
add_contextAInspect

Add a new knowledge entry to the Klever VM context store. Use this to save code examples, best practices, security tips, or documentation that can later be retrieved via query_context or search_documentation. Returns the generated ID of the new entry.

Inputs: type (required), content (required), metadata (required).

add_helper_scriptsA
Idempotent
Inspect

Add build, deploy, upgrade, query, test, and interact automation scripts to an existing Klever smart contract project. Creates a scripts/ directory with bash scripts and updates .gitignore. Run this from the project root directory (where Cargo.toml is located). This tool generates scaffold files — for koperator CLI syntax reference (correct flags like --args, --values for payments), use search_documentation instead.

Inputs: contractName.

analyze_contractA
Read-onlyIdempotent
Inspect

Analyze Klever smart contract Rust source code for common issues. Checks for missing imports, missing #[klever_sc::contract] macro, missing endpoint annotations, payable handlers without call_value usage, storage mappers without #[storage_mapper], and missing event definitions. Returns findings with severity (error/warning/info) and links to relevant knowledge base entries.

Inputs: sourceCode (required), contractName.

check_sdk_statusA
Read-onlyIdempotent
Inspect

Check whether the Klever SDK is installed and report the status of each component. Returns JSON with installation state and versions for: ksc (smart contract compiler), koperator (blockchain CLI), VM library (libvmexeccapi), and wallet key file. Run this before init_klever_project or install_klever_sdk to verify prerequisites.

Inputs: no named parameters.

deploy_scAInspect

Build an unsigned smart contract deployment transaction for the Klever blockchain. Provide either wasmPath (preferred — reads the file server-side) or wasmHex. Returns the unsigned transaction for client-side signing. The MCP server NEVER handles private keys.

Inputs: sender (required), wasmPath, wasmHex, initArgs, +1 more.

enhance_with_contextA
Read-onlyIdempotent
Inspect

Augment a natural-language query with relevant Klever VM knowledge base context. Extracts Klever-specific keywords, finds matching entries, and returns the original query combined with relevant code examples and documentation in markdown. Use this to enrich a user prompt before answering Klever development questions.

Inputs: query (required), autoInclude.

find_similarA
Read-onlyIdempotent
Inspect

Find knowledge base entries similar to a given entry by comparing tags and content. Returns related contexts ranked by similarity score. Useful for discovering related patterns, examples, or documentation after finding one relevant entry.

Inputs: id (required), limit.

freeze_klvAInspect

Build an unsigned Freeze KLV transaction on the Klever blockchain. Freezing KLV provides energy/bandwidth for network operations and enables staking rewards. Returns the unsigned transaction for client-side signing.

Inputs: sender (required), amount (required), network.

get_accountA
Read-onlyIdempotent
Inspect

Get full account details for a Klever blockchain address including nonce, balance, frozen balance, allowance, and permissions. Use this when you need comprehensive account state beyond just the balance.

Inputs: address (required), network.

get_asset_infoA
Read-onlyIdempotent
Inspect

Get complete properties and configuration for any asset on the Klever blockchain (KLV, KFI, KDA tokens, NFT collections). Returns supply info, permissions (CanMint, CanBurn, etc.), roles, precision, and metadata. Note: string fields like ID, Name, Ticker are base64-encoded in the raw response.

Inputs: assetId (required), network.

get_balanceA
Read-onlyIdempotent
Inspect

Get the KLV or KDA token balance for a Klever blockchain address. Returns the balance in the smallest unit (for KLV: 1 KLV = 1,000,000 units with 6 decimal places). Optionally specify an asset ID to query a specific KDA token balance instead of KLV.

Inputs: address (required), assetId, network.

get_blockA
Read-onlyIdempotent
Inspect

Get block information from the Klever blockchain by nonce (block number). If no nonce is provided, returns the latest block. Returns hash, timestamp, proposer, number of transactions, and other block metadata.

Inputs: nonce, network.

get_contextA
Read-onlyIdempotent
Inspect

Retrieve a single knowledge base entry by its unique ID. Returns the full entry including content, metadata, tags, and related context IDs. Use this after query_context or find_similar to get complete details for a specific entry.

Inputs: id (required).

get_knowledge_statsA
Read-onlyIdempotent
Inspect

Get summary statistics of the Klever VM knowledge base. Returns total entry count, counts broken down by context type (code_example, best_practice, security_tip, etc.), and a sample entry title for each type. Useful for understanding what knowledge is available before querying.

Inputs: no named parameters.

get_transactionA
Read-onlyIdempotent
Inspect

Get transaction details by hash from the Klever blockchain. Returns sender, receiver, status, block info, contracts, and receipts. Uses the API proxy for indexed data.

Inputs: hash (required), network.

init_klever_projectAInspect

Scaffold a new Klever smart contract project using the SDK. Creates the Rust project structure via ksc new and generates automation scripts (build, deploy, upgrade, query, test, interact). Requires Klever SDK installed at ~/klever-sdk/. Run check_sdk_status first to verify.

Inputs: name (required), template, noMove.

install_klever_sdkA
Idempotent
Inspect

Download and install Klever SDK tools to ~/klever-sdk/. Fetches the latest versions from the Klever CDN, installs binaries, and downloads required VM library dependencies. Supports macOS (arm64/amd64) and Linux. Run check_sdk_status first to see what is already installed.

Inputs: tool.

invoke_scAInspect

Build an unsigned smart contract invocation transaction on the Klever blockchain. Calls a state-changing endpoint on a deployed contract. Returns the unsigned transaction for client-side signing. For read-only calls, use query_sc instead.

Inputs: sender (required), scAddress (required), funcName (required), args, +2 more.

list_validatorsA
Read-onlyIdempotent
Inspect

List active validators on the Klever blockchain network. Returns validator addresses, names, commission rates, delegation info, and staking amounts.

Inputs: network.

query_contextA
Read-onlyIdempotent
Inspect

Search the Klever VM knowledge base for smart contract development context. Returns structured JSON with matching entries, scores, and pagination. Use this for precise filtering by type or tags; use search_documentation for human-readable "how do I..." answers.

Inputs: query, types, tags, contractType, +2 more.

query_scA
Read-onlyIdempotent
Inspect

Execute a read-only query against a Klever smart contract (VM view call). Returns the contract function result as base64-encoded return data. Arguments must be base64-encoded. Use this to read contract state without modifying it.

Inputs: scAddress (required), funcName (required), args, caller, +1 more.

search_documentationA
Read-onlyIdempotent
Inspect

Search Klever VM documentation and knowledge base. Returns human-readable markdown with titles, descriptions, and code snippets. Covers koperator CLI syntax (sc invoke, sc create, sc upgrade), --args type prefixes, --values payment flags, contract metadata flags, ABI decoding, and all smart contract development topics. ALWAYS use this tool first when you need to know the correct flags or argument syntax for koperator commands. Use this instead of query_context when you need formatted developer documentation.

Inputs: query (required), category.

send_transferAInspect

Build an unsigned KLV or KDA token transfer transaction on the Klever blockchain. Returns the unsigned transaction data and hash for client-side signing. The MCP server NEVER handles private keys — signing must be done externally.

Inputs: sender (required), receiver (required), amount (required), assetId, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 23 tools

    Disambiguation5/5

    Tools have clearly distinct purposes. For example, query_context and search_documentation both search the knowledge base but differ in output format (structured JSON vs human-readable markdown). All other tools target different resources or actions.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with underscores, such as add_context, get_balance, deploy_sc. No mixing of conventions.

    Tool Count4/5

    23 tools is on the higher end of the acceptable range. The server covers a broad domain including blockchain queries, smart contract lifecycle, and knowledge management, so the count is justified but some consolidation (e.g., reducing knowledge base tools) could improve coherence.

    Completeness4/5

    The tool set covers major workflows: SDK installation, project scaffolding, code analysis, deployment, invocation, queries, transfers, and knowledge base management. A minor gap is the lack of an explicit contract upgrade tool, though helper scripts include an upgrade script.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers