Skip to main content
Glama
Datajang

mcp-narajangteo

by Datajang
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NARA_API_KEYYes공공데이터포털에서 발급받은 '조달청_나라장터 입찰공고정보서비스'의 ServiceKey (일반 인증키 Decoding).

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_bids_by_keywordA
    Search Korean government procurement notices (나라장터).
    Returns BOTH regular bid notices (입찰공고) AND preliminary specifications (사전규격)
    for service-type (용역) projects including consulting, development, and SI.

    Args:
        keyword: Search keyword for bid title (공고명).
                 Examples: '인공지능', 'AI', '플랫폼', '시스템 구축', etc.
        days: Search window in days from today (default: 7).
              Increase for older bids, e.g. 30, 60, 90.

    Returns:
        Formatted string with bid information
recommend_bids_for_deptA
    Search government procurement notices with department context for personalized recommendations.
    Returns up to 60 results (30 regular bids + 30 pre-specs) with analysis instructions.
    LLM can flexibly present Top N items or all relevant items based on user's request.
    Prioritizes items with non-zero budgets.

    Args:
        keyword: Search keyword (e.g., 'AI', 'Cloud', '플랫폼')
        department_profile: Description of your team/department.
                           Examples: 'UI/UX 디자인팀', 'Database Migration Unit',
                                    'AI/ML 개발팀', '클라우드 인프라팀'
        days: Search window in days from today (default: 7).
              Increase for older bids, e.g. 30, 60, 90.

    Returns:
        Formatted recommendations with strategic analysis
analyze_bid_detailA
    Download and extract text from bid attachment (RFP/제안요청서) for strategic analysis.
    Supports HWP, HWPX, PDF, DOCX, XLSX, and ZIP files.
    ZIP files are processed with priority: 제안요청서 > 과업지시서 > .hwp > .pdf

    Args:
        file_url: Attachment URL (ntceSpecDocUrl1 from search results)
        filename: Filename (ntceSpecFileNm1 from search results)
        department_profile: Optional - Your team description for strategic analysis.
                           If provided, response includes analysis prompts for Fit Score,
                           Core Tasks, Winning Strategy, and Risk Factors.

    Returns:
        Extracted document text with optional analysis prompts

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
nara_infoInformation about Nara procurement bid service.
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

A4.2/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap. analyze_bid_detail focuses on document extraction and analysis, get_bids_by_keyword performs general keyword searches, and recommend_bids_for_dept provides personalized recommendations based on department context. The boundaries are well-defined and unambiguous.

Naming Consistency5/5

All three tools follow a consistent verb_noun pattern with clear, descriptive names: analyze_bid_detail, get_bids_by_keyword, and recommend_bids_for_dept. The naming convention is uniform throughout the set, making it easy to understand each tool's function at a glance.

Tool Count4/5

Three tools is appropriate for this government procurement domain, covering search, analysis, and recommendation workflows. While slightly minimal, each tool serves a distinct and valuable purpose, and the count aligns well with the server's focused scope on Korean procurement notices.

Completeness4/5

The toolset covers core workflows effectively: searching bids, analyzing bid details, and providing personalized recommendations. Minor gaps exist, such as the lack of tools for bid submission or tracking, but the available tools enable agents to perform essential procurement analysis tasks without significant dead ends.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources