de en es ja ko ru zh

Arkiv MCP Server

Name: Arkiv MCP Server
Author: arrivets

by arrivets

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

Arkiv MCP 서버

AI 에이전트와 애플리케이션에 Arkiv 데이터베이스 체인 쿼리 기능을 제공하는 Model Context Protocol (MCP) 서버입니다.

빠른 시작

1. 빌드

cd arkiv-mcp
npm install
npm run build

2. Claude Code에 추가

arkiv-mcp 디렉토리에서 다음을 실행하세요:

claude mcp add arkiv -- node $(pwd)/dist/index.js

또는 ~/.claude/settings.json에 수동으로 추가하세요:

{
  "mcpServers": {
    "arkiv": {
      "command": "node",
      "args": ["/absolute/path/to/arkiv-mcp/dist/index.js"]
    }
  }
}

Claude Desktop의 경우, 동일한 블록을 ~/Library/Application Support/Claude/claude_desktop_config.json(macOS) 또는 %APPDATA%\Claude\claude_desktop_config.json(Windows)에 추가하세요.

3. Kaolin 테스트넷 쿼리

연결되면 query_entities 도구를 사용할 수 있습니다. 예시 프롬프트:

"Arkiv의 모든 엔티티 쿼리"
"type = "post"이고 score > 10인 모든 Arkiv 엔티티 찾기"
"Arkiv 테스트넷에서 0x1234...가 소유한 엔티티 보여줘"
"status = "active"와 일치하는 첫 5개 엔티티를 가져온 후 페이지네이션"

Related MCP server: TextQL MCP Server

기능

SQL과 유사한 필터 표현식을 사용하여 Arkiv 데이터베이스 체인에서 엔티티 쿼리
전체 arkiv_query 구문 지원: 비교, 논리 연산자, 글로브(glob) 매칭, 합성 속성
커서를 사용한 페이지네이션 지원
구성 가능한 반환 필드 (속성, 메타데이터, 페이로드)
기본값으로 Kaolin 테스트넷 사용

설치

cd arkiv-mcp
npm install
npm run build

# Or use tsx for development
npm run dev

사용법

서버 시작

# Using default Kaolin testnet
npm start

# With custom node URL
npm start -- --node-url https://your-arkiv-node.rpc

# Or with tsx for development
npm run dev -- --node-url https://your-arkiv-node.rpc

환경 변수

변수	설명	필수 여부
`ARKIV_NODE_URL`	Arkiv 노드 RPC URL	아니요 (기본값: Kaolin 테스트넷)

명령줄 옵션

옵션	설명	기본값
`--node-url <url>`	Arkiv 노드 RPC URL	Kaolin 테스트넷
`--help`, `-h`	도움말 표시	-

MCP 도구

`query_entities`

Arkiv 데이터베이스 체인에서 엔티티를 쿼리합니다.

매개변수

매개변수	타입	설명	기본값
`filter`	string	필터 표현식 (아래 구문 참조)	`$all`
`limit`	number	반환할 최대 엔티티 수 (최대 200)	-
`cursor`	string	이전 응답에서 받은 페이지네이션 커서	-
`withAttributes`	boolean	결과에 속성 포함 여부	true
`withMetadata`	boolean	결과에 메타데이터(소유자, 생성자, 만료) 포함 여부	true
`withPayload`	boolean	결과에 페이로드(base64 인코딩) 포함 여부	true
`validAtBlock`	number	특정 블록 번호에서의 상태 쿼리	-

필터 구문

filter 매개변수는 arkiv_query 표현식 언어를 사용합니다:

연산자	설명	예시
`=`	같음	`status = "active"`
`!=`	같지 않음	`status != "deleted"`
`>`, `>=`, `<`, `<=`	숫자 범위	`score > 100`
`&&`	논리 AND	`type = "post" && score > 50`
`\|\|`	논리 OR	`status = "active" \|\| status = "pending"`
`!`	부정	`!(status = "deleted")`
`~`	글로브 매칭	`name ~ "test*"`
`!~`	부정 글로브 매칭	`name !~ "draft*"`

합성 속성 ($ 접두사 사용):

속성	설명
`$all`	모든 엔티티 매칭
`$owner`	현재 소유자 주소
`$creator`	원본 생성자 주소 (변경 불가)
`$key`	엔티티 키

필터 예시

# All entities
$all

# By entity key
$key = "0xabc123..."

# By owner or creator
$owner = "0x1234567890abcdef..."
$creator = "0x1234567890abcdef..."

# Attribute equality
status = "active"
type = "post"

# Numeric range
score > 100
price >= 50 && price <= 200

# Compound
project = "myapp" && type = "post" && score > 10

# Glob matching
name ~ "draft*"
!(status = "deleted")

응답 형식

{
  "entities": [
    {
      "key": "0x...",
      "owner": "0x...",
      "creator": "0x...",
      "createdAtBlock": "12345",
      "lastModifiedAtBlock": "12350",
      "expiresAtBlock": "99999",
      "contentType": "application/json",
      "payload": "<base64-encoded bytes>",
      "attributes": [
        { "key": "type", "value": "post" },
        { "key": "score", "value": 42 }
      ]
    }
  ],
  "cursor": "0x2a",
  "blockNumber": "12350",
  "count": 1
}

다음 호출 시 반환된 cursor를 cursor 매개변수로 전달하여 페이지네이션을 수행합니다. cursor가 없으면 더 이상 결과가 없는 것입니다.

개발

이 서버는 다음을 사용합니다:

@arkiv-network/sdk — Arkiv TypeScript SDK
@modelcontextprotocol/sdk — MCP 서버 SDK

프로젝트 구조

arkiv-mcp/
├── src/
│   └── index.ts          # Main server implementation
├── package.json
├── tsconfig.json
└── README.md

라이선스

MIT

Available Tools

1 tool

query_entitiesA

Query entities from an Arkiv database chain using a filter expression. The filter uses a SQL-like syntax: comparisons (=, !=, <, >, <=, >=), logical operators (&& and ||), negation (!), and glob matching (~). Special attributes: $all (match everything), $owner (current owner address), $creator (original creator address, immutable), $key (entity key). Examples: '$all', 'status = "active"', 'score > 100', 'project = "myapp" && status = "active"', '$owner = "0x1234..."', 'name ~ "test*"'

ParametersJSON Schema

Name	Required	Description
`filter`	No	Filter expression. Defaults to "$all" if omitted. Examples: 'status = "active"', 'score > 100 && type = "post"', '$owner = "0xAbc..."', '$creator = "0xDef..."', 'name ~ "prefix*"'
`limit`	No	Maximum number of entities to return (max 200)
`cursor`	No	Pagination cursor returned by a previous query
`withAttributes`	No	Include attributes in results (default: true)
`withMetadata`	No	Include metadata (owner, creator, expiry) in results (default: true)
`withPayload`	No	Include payload in results as base64 (default: true)
`validAtBlock`	No	Query state at a specific block number

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It explains the filter syntax and special attributes but does not disclose performance implications, rate limits, or confirm that it is read-only. Schema covers some aspects (e.g., limit), but behavioral context is lacking.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured paragraph that front-loads the core purpose, then details the filter syntax, special attributes, and examples. Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description does not explain return values explicitly, but the tool name and parameters imply entities with requested fields. Pagination cursor is mentioned in schema but not explained in description. Overall, it is fairly complete for a query tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds meaningful context for the 'filter' parameter by detailing the syntax and special attributes ($all, $owner, etc.), which goes beyond the schema. Other parameters are not enhanced, but the main parameter benefits significantly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool queries entities from an Arkiv database chain using a filter expression, with specific SQL-like syntax and special attributes. It is a specific verb-resource pair, and there are no sibling tools to distinguish against.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides examples and syntax details that imply when to use the tool, but does not explicitly state when not to use or mention alternatives. Since there are no sibling tools, the lack of exclusion is less critical.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

1 tool updatev1.0.0Apr 24, 2026
- First observedquery_entities

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored 2026-04-24 14:10 across 1 tool

Disambiguation5/5

Only one tool exists, so there is no risk of confusion between tools. Perfect disambiguation.

Naming Consistency5/5

With a single tool, there are no naming inconsistencies. The name 'query_entities' follows a clear verb_noun pattern.

Tool Count1/5

A single tool is insufficient for a database server; even if it's query-only, missing CRUD operations severely limits functionality. Extreme mismatch.

Completeness2/5

The server only offers query functionality, omitting essential operations like create, update, or delete. Significant gaps for typical database interaction.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

HutchDBOAuth
com.hutchdb
Store, query, and update structured data from any AI agent
Databases Knowledge & Memory
115
KlaaroOAuth
ai.klaaro
Query Klaaro datasets, documents, and extracted records from any agent.
Search Databases RAG Systems
1
busabase C
com.busabase
Database for your AI agent. Turn its output into data, docs, skills, and apps you can actually use.
Databases Data Platforms Knowledge & Memory
10921
AgentUI AppsOAuth
ai.agentui
Create AgentUI data apps: define tables, read and write records, and run programs on your data.
1

Related MCP Servers

Supabase MCP Server
Databases Developer Tools Autonomous Agents
CloudMediaServices
A
license
Not graded
quality
D
maintenance
Enables AI assistants to perform CRUD operations on Supabase databases through natural language. Supports advanced filtering, pagination, and safety checks for seamless database interaction.
Updated a year ago (2025-08-10 00:38 UTC)
MIT
TextQL MCP Server
Search Databases
alexandme
A
license
Not graded
quality
D
maintenance
Translates natural language to SQL/GraphQL queries and executes them, enabling AI agents to interact with databases through the Model Context Protocol.
Updated a year ago (2025-07-24 22:16 UTC)
1
Apache 2.0
Enterprise Knowledge Mesh
Search Knowledge & Memory Documentation Access
ashishsantikari
F
license
A
quality
D
maintenance
Enables AI agents to query structured knowledge across enterprise domains (legal, HR, compliance) with metadata-driven filtering and TF-IDF ranking.
Updated 4 months ago (2026-06-17 10:31 UTC)
4
-
Caseware Procurement Document
RAG Systems Search Databases
luiscanaveral
F
license
Not graded
quality
D
maintenance
Enables AI agents to search, retrieve, and answer grounded questions over procurement documents (invoices, purchase orders, contracts, etc.) using hybrid SQL and vector retrieval.
Updated 3 months ago (2026-06-27 20:41 UTC)
-

Arkiv MCP 서버

빠른 시작

기능

설치

사용법

서버 시작

환경 변수

명령줄 옵션

MCP 도구

query_entities

매개변수

필터 구문

필터 예시

응답 형식

개발

프로젝트 구조

라이선스

Available Tools

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Supabase MCP Server

TextQL MCP Server

Enterprise Knowledge Mesh

Caseware Procurement Document

`query_entities`