Skip to main content
Glama
deenesjakoruzh
jitbit

jitbit-helpdesk-mcp

Official
by jitbit
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
JavaScript
Remote

Jitbit Helpdesk MCP 서버

AI 어시스턴트가 Jitbit Helpdesk에서 지원 티켓을 검색하고 읽을 수 있도록 하는 MCP(Model Context Protocol) 서버입니다. SaaS 및 온프레미스 설치 환경 모두에서 작동합니다.

npm version

⚠️ 지원 중단 알림: Jitbit은 이제 버전 11.21 이상을 실행하는 모든 SaaS 및 온프레미스 설치 환경에서 /api/mcp에 내장된 HTTP MCP 엔드포인트를 제공합니다. 이것이 AI 어시스턴트를 Jitbit에 연결하는 권장 방식입니다. 더 많은 도구를 제공하고, Jitbit 릴리스와 자동으로 동기화되며, 로컬 설치가 필요하지 않습니다. 이 npm 패키지는 곧 지원이 중단될 예정이며, 11.21 이전 버전의 온프레미스 설치 환경에만 권장됩니다. Jitbit MCP 문서를 참조하세요.

설정

두 가지 옵션:

  1. 호스팅된 HTTP 엔드포인트 (권장) — Jitbit에 내장되어 있어 설치가 필요 없습니다. 버전 11.21 이상을 실행하는 SaaS 및 온프레미스 설치 환경에서 사용할 수 있습니다. Jitbit MCP 문서를 참조하세요.

  2. 로컬 npm 패키지 (지원 중단) — 이 저장소이며 npx를 통해 로컬에서 실행됩니다. 온프레미스 Jitbit 버전이 11.21 미만인 경우에만 사용하세요.

옵션 1: 호스팅된 HTTP 엔드포인트

Claude Code

claude mcp add --transport http jitbit-helpdesk https://yourcompany.jitbit.com/api/mcp \
  --header "Authorization: Bearer your-api-token"

Claude Desktop, Cursor, Windsurf

{
  "mcpServers": {
    "jitbit-helpdesk": {
      "type": "http",
      "url": "https://yourcompany.jitbit.com/api/mcp",
      "headers": {
        "Authorization": "Bearer your-api-token"
      }
    }
  }
}

옵션 2: 로컬 npm 패키지

Claude Code

claude mcp add jitbit-helpdesk \
  -e JITBIT_URL=https://yourcompany.jitbit.com \
  -e JITBIT_TOKEN=your-api-token \
  -- npx -y jitbit-helpdesk-mcp

Claude Desktop, Cursor, Windsurf

설정 파일에 추가하세요:

  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) 또는 %APPDATA%\Claude\claude_desktop_config.json (Windows)

  • Cursor: 설정 > MCP 서버

  • Windsurf: 설정 > MCP 서버

{
  "mcpServers": {
    "jitbit-helpdesk": {
      "command": "npx",
      "args": ["-y", "jitbit-helpdesk-mcp"],
      "env": {
        "JITBIT_URL": "https://yourcompany.jitbit.com",
        "JITBIT_TOKEN": "your-api-token"
      }
    }
  }
}

환경 변수

변수

필수

설명

JITBIT_URL

예

Jitbit 인스턴스의 기본 URL (SaaS: https://yourcompany.jitbit.com, 온프레미스: 서버 URL)

JITBIT_TOKEN

예

API 토큰 — 아래 참조

API 토큰 가져오기

  1. Jitbit Helpdesk에 로그인합니다.

  2. 사용자 프로필(우측 상단 아바타 클릭)로 이동합니다.

  3. "API Token" 버튼을 클릭합니다.

  4. 토큰을 복사하여 JITBIT_TOKEN 값으로 사용합니다.

Related MCP server: tickiti-mcp

도구

jitbit_search_tickets

키워드나 구문으로 티켓을 검색합니다.

매개변수:

  • query (문자열, 필수) — 검색 쿼리

  • limit (숫자, 기본값 25) — 최대 결과 수 (1–100)

  • offset (숫자, 기본값 0) — 페이지네이션 오프셋

jitbit_list_tickets

티켓을 나열하고 필터링합니다.

매개변수:

  • mode (문자열, 선택 사항) — "all", "unanswered" 또는 "updated"

  • status (문자열, 선택 사항) — 티켓 상태별 필터링

  • limit (숫자, 기본값 25) — 최대 결과 수 (1–100)

  • offset (숫자, 기본값 0) — 페이지네이션 오프셋

jitbit_get_ticket

전체 대화 스레드가 포함된 단일 티켓을 가져옵니다.

매개변수:

  • ticketId (숫자, 필수) — 티켓 ID

개발

npm install
npm run build

라이선스

MIT

Available Tools

3 tools
jitbit_get_ticketGet Jitbit Helpdesk TicketA
Read-onlyIdempotent

Get a single ticket with its full conversation thread from Jitbit Helpdesk.

Args:

  • ticketId (number): The ticket ID to retrieve

Returns: Full ticket details including subject, body, status, priority, category, submitter, assignee, tags, and complete comment history.

ParametersJSON Schema
NameRequiredDescriptionDefault
ticketIdYesThe ticket ID to retrieve

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already provide key behavioral hints (read-only, non-destructive, idempotent, open-world), so the bar is lower. The description adds valuable context by specifying that it retrieves 'full ticket details' and 'complete comment history,' which clarifies the scope of data returned beyond what annotations indicate. No contradictions with annotations are present.

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 front-loaded with the core purpose in the first sentence, followed by structured Args and Returns sections. Each sentence adds value without redundancy, making it efficient and easy to parse for an AI agent.

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 the tool's low complexity (1 parameter, no output schema) and rich annotations, the description is mostly complete. It covers purpose, parameters, and return details. However, it could benefit from more explicit usage guidelines compared to siblings, slightly reducing completeness for optimal agent decision-making.

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%, with the parameter 'ticketId' fully documented in the schema. The description mentions 'ticketId' in the Args section but does not add significant meaning beyond what the schema provides, such as format examples or constraints. Baseline score of 3 is appropriate as the schema handles parameter documentation adequately.

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 the specific action ('Get a single ticket') and resource ('from Jitbit Helpdesk'), including the scope ('with its full conversation thread'). It distinguishes from sibling tools like 'jitbit_list_tickets' and 'jitbit_search_tickets' by focusing on retrieving a single ticket rather than listing or searching multiple tickets.

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 implies usage context by specifying 'a single ticket,' suggesting it's for detailed retrieval rather than bulk operations. However, it does not explicitly state when to use this tool versus alternatives like 'jitbit_list_tickets' or 'jitbit_search_tickets,' nor does it mention any exclusions or prerequisites for use.

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

jitbit_list_ticketsList Jitbit Helpdesk TicketsB
Read-onlyIdempotent

List and filter tickets in Jitbit Helpdesk.

Args:

  • mode (string, optional): Filter mode — "all", "unanswered", "updated"

  • status (string, optional): Filter by ticket status, passed to the Jitbit API as-is

  • limit (number): Maximum results to return, 1-100 (default: 25)

  • offset (number): Number of results to skip for pagination (default: 0)

Returns: List of tickets with ID, subject, status, priority, category, submitter, and assignee.

ParametersJSON Schema
NameRequiredDescriptionDefault
modeNoFilter mode: "all", "unanswered", "updated"
statusNoFilter by ticket status
limitNoMaximum results to return
offsetNoNumber of results to skip for pagination

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already cover key behavioral traits (read-only, non-destructive, idempotent, open-world). The description adds minimal context beyond this, such as mentioning pagination via 'offset' and the return format, but doesn't disclose rate limits, authentication needs, or detailed behavioral constraints. No contradiction with annotations.

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

Conciseness4/5

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

The description is appropriately sized and front-loaded with the core purpose. The Args and Returns sections are structured but slightly verbose, as some details (e.g., parameter defaults) are redundant with the schema. Most sentences earn their place, though minor trimming could improve efficiency.

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 the tool's moderate complexity, rich annotations, and 100% schema coverage, the description is mostly complete. It explains the return format (list of tickets with fields), which compensates for the lack of an output schema. However, it could better address sibling tool differentiation and usage scenarios to enhance completeness.

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 input schema fully documents parameters. The description repeats parameter details (e.g., mode options, limit range) without adding significant meaning beyond the schema, such as explaining how 'status' interacts with 'mode' or providing usage examples. Baseline 3 is appropriate given high schema coverage.

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 as 'List and filter tickets in Jitbit Helpdesk,' which specifies the verb (list/filter) and resource (tickets). However, it doesn't explicitly differentiate from sibling tools like 'jitbit_search_tickets,' which likely has overlapping 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 its siblings (jitbit_get_ticket, jitbit_search_tickets). It lacks explicit context, exclusions, or alternatives, leaving the agent to infer usage based on tool names alone.

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

jitbit_search_ticketsSearch Jitbit Helpdesk TicketsB
Read-onlyIdempotent

Search for tickets in Jitbit Helpdesk by keyword or phrase.

Args:

  • query (string): Search query to match against ticket subjects and bodies

  • limit (number): Maximum results to return, 1-100 (default: 25)

  • offset (number): Number of results to skip for pagination (default: 0)

Returns: List of matching tickets with ID, subject, status, priority, category, submitter, and assignee.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query to match against ticket subjects and bodies
limitNoMaximum results to return
offsetNoNumber of results to skip for pagination

TDQS

B3.2/5.0
Behavior3/5

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

Annotations cover key behavioral traits (read-only, non-destructive, idempotent, open-world), so the description's burden is lower. It adds value by specifying that the search matches against ticket subjects and bodies, which isn't in the annotations. However, it doesn't disclose other behaviors like rate limits, authentication needs, or error handling, keeping the score at a baseline level.

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

Conciseness4/5

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

The description is well-structured and appropriately sized, with a clear purpose statement followed by parameter and return details. It avoids unnecessary fluff, though the parameter section slightly repeats schema information, which is minor but keeps it from a perfect score.

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 the tool's moderate complexity, rich annotations, and high schema coverage, the description is reasonably complete. It explains the search scope and return format, though without an output schema, it could benefit from more detail on the ticket structure. However, it covers the essentials for a search operation.

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%, meaning the input schema already documents all parameters thoroughly. The description repeats some parameter details (e.g., query matches subjects and bodies) but doesn't add significant new meaning beyond the schema. This meets the baseline score when schema coverage is high.

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 searches for tickets in Jitbit Helpdesk by keyword or phrase, providing a specific verb ('search') and resource ('tickets'). However, it doesn't explicitly differentiate from sibling tools like jitbit_list_tickets, which might also retrieve tickets but potentially without search 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 jitbit_get_ticket or jitbit_list_tickets. It mentions searching by keyword or phrase but doesn't specify scenarios where this is preferred over other methods, leaving the agent to infer usage from context alone.

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 updatesv1.0.1
    • First observedjitbit_get_ticket
    • First observedjitbit_list_tickets
    • First observedjitbit_search_tickets
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

A3.5/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: get_ticket retrieves a single ticket with full details, list_tickets provides filtered listings with pagination, and search_tickets performs keyword-based searches. There is no overlap in functionality—an agent can easily choose the right tool based on whether they need a specific ticket, a filtered list, or a search.

Naming Consistency5/5

All tools follow a consistent jitbit_verb_noun pattern (jitbit_get_ticket, jitbit_list_tickets, jitbit_search_tickets). The naming is uniform, using snake_case throughout with clear verbs (get, list, search) that accurately describe each action.

Tool Count3/5

With only 3 tools, the server feels thin for a helpdesk domain that typically involves ticket management workflows. While the tools cover basic retrieval and listing, the count is borderline low for operations like creating, updating, or closing tickets, which are common in such systems.

Completeness2/5

The tool set is severely incomplete for a helpdesk server. It only provides read-only operations (get, list, search), with no ability to create, update, assign, or close tickets. This leaves significant gaps that will cause agent failures when trying to perform common helpdesk tasks beyond querying existing data.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Server for Intercom

    raoulbia-ai
    A
    license
    A
    quality
    C
    maintenance
    An MCP-compliant server that enables AI assistants like Claude Desktop to access and analyze Intercom support tickets with full conversation history.
    4
    8
    Apache 2.0
  • tickiti-mcp by tickiti

    tickiti-mcpofficial

    tickiti
    A
    license
    B
    quality
    B
    maintenance
    An MCP server that exposes the Tickiti helpdesk API to AI assistants, enabling ticket management and helpdesk operations via natural language.
    11
    MIT

  • FS_MCP_thin

    cbreland-DLR
    F
    license
    B
    quality
    D
    maintenance
    A read-only MCP server that connects AI assistants to Freshservice Service Desk for ticket triage, asset analysis, and support history summarization.
    23
    -

  • freshservice-mcp

    mchluba
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that enables AI assistants to interact with Freshservice service desk, supporting ticket search, retrieval, and creation via a configurable, Docker-first deployment.
    MIT