Skip to main content
Glama
enesjakozh
ucalyptus

Prem MCP Server

by ucalyptus
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Prem MCP 서버

대장간 배지

Prem AI를 위한 모델 컨텍스트 프로토콜(MCP) 서버 구현으로, Claude 및 기타 MCP 호환 클라이언트와의 원활한 통합을 지원합니다. 이 서버는 MCP 인터페이스를 통해 Prem AI의 강력한 기능에 대한 액세스를 제공합니다.

특징

  • 🤖 채팅 완성 : Prem AI의 언어 모델과 상호 작용하세요

  • 📚 RAG 지원 : 문서 저장소 통합을 통한 검색 증강 생성

  • 📝 문서 관리 : 저장소에 문서 업로드 및 관리

  • 🎭 템플릿 시스템 : 특수 출력을 위해 미리 정의된 프롬프트 템플릿을 사용합니다.

  • ⚡ 스트리밍 응답 : 모델 출력의 실시간 스트리밍

  • 🛡️ 오류 처리 : 강력한 오류 처리 및 로깅

Related MCP server: MCP Server Sample

필수 조건

  • Node.js(v16 이상)

  • API 키가 있는 Prem AI 계정

  • Prem 프로젝트 ID

설치

Smithery를 통해 설치

Smithery를 통해 Claude Desktop용 prem-mcp-server를 자동으로 설치하려면:

지엑스피1

수동 설치

# Using npm
npm install prem-mcp-server

# Using yarn
yarn add prem-mcp-server

# Using pnpm
pnpm add prem-mcp-server

구성

1. 환경 변수

프로젝트 루트에 .env 파일을 만듭니다.

PREM_API_KEY=your_api_key_here
PREM_PROJECT_ID=your_project_id_here

2. 커서 구성

Cursor와 함께 Prem MCP 서버를 사용하려면 ~/.cursor/mcp.json 에 다음을 추가하세요.

{
  "mcpServers": {
    "PremAI": {
      "command": "node",
      "args": ["/path/to/your/prem-mcp/build/index.js", "--stdio"],
      "env": {
        "PREM_API_KEY": "your_api_key_here",
        "PREM_PROJECT_ID": "your_project_id_here"
      }
    }
  }
}

/path/to/your/prem-mcp 프로젝트 디렉토리의 실제 경로로 바꾸세요.

3. Claude 데스크톱 구성

Claude Desktop 사용자의 경우 claude_desktop_config.json 에 다음을 추가하세요.

{
  "mcpServers": {
    "PremAI": {
      "command": "npx",
      "args": ["prem-mcp-server", "--stdio"],
      "env": {
        "PREM_API_KEY": "your_api_key_here",
        "PREM_PROJECT_ID": "your_project_id_here"
      }
    }
  }
}

용법

서버 시작

npx prem-mcp-server

예시 프롬프트

  1. 기본 채팅

Let's have a conversation about artificial intelligence.

  1. 문서가 포함된 RAG

Based on the documents in repository XYZ, what are the key points about [topic]?

  1. 템플릿 사용

Use template ABC to generate [specific type of content].

문서 업로드

이 서버는 RAG 작업을 위해 Prem AI 저장소에 문서를 업로드하는 기능을 지원합니다. 지원되는 형식은 다음과 같습니다.

  • .txt

  • .pdf

  • .docx

API 참조

채팅 완료 매개변수

  • query : 입력 텍스트

  • system_prompt : 사용자 정의 시스템 프롬프트

  • model : 모델 식별자

  • temperature : 반응 무작위성(0-1)

  • max_tokens : 최대 응답 길이

  • repository_ids : RAG의 저장소 ID 배열

  • similarity_threshold : 문서 유사도에 대한 임계값

  • limit : 문서 청크의 최대 수

템플릿 매개변수

  • template_id : 프롬프트 템플릿의 ID

  • params : 템플릿별 매개변수

  • temperature : 반응 무작위성(0-1)

  • max_tokens : 최대 응답 길이

개발

# Clone the repository
git clone https://github.com/yourusername/prem-mcp-server.git

# Install dependencies
npm install

# Build the project
npm run build

# Run tests
npm test

문제 해결

일반적인 문제

  1. 서버를 찾을 수 없습니다

    • claude_desktop_config.json 에서 서버 경로를 확인하세요.

    • 서버가 실행 중인지 확인하세요

  2. API 키가 유효하지 않습니다

    • Prem AI API 키가 유효한지 확인하세요.

    • API 키에 필요한 권한이 있는지 확인하세요

  3. 문서 업로드 실패

    • 파일 형식이 지원되는지 확인하세요

    • 파일 권한 확인

    • 저장소 ID가 올바른지 확인하세요

기여하다

기여를 환영합니다! 풀 리퀘스트를 제출해 주세요.

특허

MIT 라이센스 - 자세한 내용은 LICENSE 파일을 참조하세요.

감사의 말

지원하다

이슈 및 기능 요청은 GitHub 이슈 페이지를 이용해 주세요.

Available Tools

3 tools
chatC

Chat with Prem AI - supports chat completions with optional RAG capabilities.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesThe chat message to send
system_promptNoOptional system prompt to guide the model's behavior
modelNoOptional model to use for completion
temperatureNoOptional temperature for response generation
max_tokensNoOptional maximum tokens to generate
repository_idsNoOptional array of repository IDs for RAG
similarity_thresholdNoOptional similarity threshold for RAG
limitNoOptional limit of context chunks for RAG

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'chat completions with optional RAG capabilities' but doesn't describe key behavioral traits like whether this is a read-only or mutating operation, authentication requirements, rate limits, response format, or error handling. For a chat tool with 8 parameters and no annotations, this leaves significant gaps in understanding how the tool behaves.

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 extremely concise and front-loaded: a single sentence that captures the core functionality. Every word earns its place with no redundancy or unnecessary elaboration. The structure efficiently communicates the tool's purpose without wasting space.

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

Completeness2/5

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

Given the tool's complexity (8 parameters, no output schema, no annotations), the description is incomplete. It doesn't address behavioral aspects, usage context, or output expectations. While the schema covers parameters well, the description fails to provide the additional context needed for an agent to understand when and how to use this tool effectively, especially compared to siblings.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all 8 parameters thoroughly. The description adds minimal value beyond the schema by mentioning 'optional RAG capabilities', which loosely relates to parameters like repository_ids, similarity_threshold, and limit. However, it doesn't provide additional semantic context or usage examples beyond what's in the parameter descriptions.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Chat with Prem AI - supports chat completions with optional RAG capabilities.' It specifies the verb ('Chat with'), resource ('Prem AI'), and key capabilities (chat completions with optional RAG). However, it doesn't explicitly differentiate from sibling tools like 'prem_chat_with_template' beyond mentioning RAG capabilities.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'prem_chat_with_template' or 'prem_upload_document'. It mentions optional RAG capabilities but doesn't specify scenarios where RAG is beneficial or when to choose this tool over siblings. No explicit when/when-not statements or alternative recommendations are included.

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

prem_chat_with_templateC

Chat using a predefined Prem AI prompt template

ParametersJSON Schema
NameRequiredDescriptionDefault
template_idYesID of the prompt template to use
paramsYesParameters to fill in the template
modelNoOptional model to use
temperatureNoOptional temperature parameter
max_tokensNoOptional maximum tokens to generate

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Chat') but lacks details on permissions, rate limits, response format, or potential side effects. For a tool with multiple parameters and no annotation coverage, this is a significant gap in transparency.

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, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and appropriately sized, making it easy for an agent to parse quickly.

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

Completeness2/5

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

Given the tool's complexity (5 parameters, nested objects, no output schema) and lack of annotations, the description is incomplete. It doesn't explain return values, error conditions, or behavioral nuances, leaving the agent with insufficient context for effective use.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema fully documents all parameters. The description adds no additional meaning beyond implying template-based chat, which is already covered by the schema's parameter descriptions. This meets the baseline for high schema coverage without extra value.

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

Purpose4/5

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

The description clearly states the verb ('Chat') and resource ('using a predefined Prem AI prompt template'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'chat' or 'prem_upload_document', which would require more specific language about template-based versus direct chat functionality.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'chat' or 'prem_upload_document', nor does it specify prerequisites such as needing a pre-existing template or appropriate parameters. This leaves the agent without clear usage context.

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

prem_upload_documentC

Upload a document to a Prem AI repository

ParametersJSON Schema
NameRequiredDescriptionDefault
repository_idYesID of the repository to upload to
file_pathYesPath to the file to upload

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden. It mentions 'Upload' which implies a write operation, but doesn't disclose behavioral traits like authentication requirements, file size limits, supported formats, error handling, or what happens on success. This leaves significant gaps for an upload tool.

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, clear sentence with zero waste—it directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded for an upload operation.

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

Completeness2/5

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

Given no annotations, no output schema, and a mutation tool (upload), the description is incomplete. It lacks details on permissions, return values, error cases, or operational limits, which are critical for safe and effective use.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents both parameters (repository_id, file_path). The description doesn't add any meaning beyond what the schema provides, such as examples or constraints. Baseline 3 is appropriate when the schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the action ('Upload') and target resource ('document to a Prem AI repository'), making the purpose immediately understandable. It doesn't differentiate from sibling tools (chat, prem_chat_with_template), which are unrelated communication tools, so it doesn't need explicit sibling differentiation.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or exclusions. It simply states what the tool does without context about appropriate scenarios or constraints.

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. 3 tool updates
    • First observedchat
    • First observedprem_chat_with_template
    • First observedprem_upload_document
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

C2.8/5.0

Scored across 3 tools

Disambiguation3/5

The tools have some overlap but are distinguishable by their specific functions. 'chat' and 'prem_chat_with_template' both handle chat completions, which could cause confusion, but 'prem_chat_with_template' specifies template usage, and 'prem_upload_document' is clearly distinct for document uploads. The descriptions help differentiate them, but the chat-focused tools have ambiguous boundaries.

Naming Consistency2/5

The naming is inconsistent with mixed conventions. 'chat' uses a simple verb, 'prem_chat_with_template' uses a verbose prefix and underscores, and 'prem_upload_document' follows a similar pattern but differs in structure. There is no uniform verb_noun pattern, and the prefix 'prem_' is applied inconsistently, leading to a chaotic naming style.

Tool Count3/5

With 3 tools, the count is borderline for a server's scope. It feels thin, potentially lacking operations like document retrieval or template management, but it covers basic chat and document upload functionalities. For a Prem AI server, more tools might be expected to handle a complete workflow, making this slightly under-scoped.

Completeness2/5

There are significant gaps in the tool surface for a Prem AI domain. The tools cover chat completions and document upload but lack operations for retrieving documents, managing templates, or performing other AI tasks like embeddings or fine-tuning. This incomplete coverage will likely cause agent failures when trying to execute common workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches