Provides tools for searching and retrieving articles from a Zendesk Help Center, including article search with pagination and locale support, and fetching article details by ID.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Zendesk Help Center MCP Server search for articles about password reset"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that interfaces with the Zendesk Help Center API, allowing integration with Claude Desktop and other MCP-compatible clients.
Article Search: Search for articles in your Zendesk Help Center
Article Details: Retrieve detailed information about specific articles by ID
Related MCP server: Zendesk MCP Server
Node.js (v18 or higher)
A Zendesk account with API access
Zendesk API token
Clone this repository:
git clone https://github.com/yourusername/zendesk-help-center-mcp-server.git
cd zendesk-help-center-mcp-serverInstall dependencies:
npm installCreate a .env file in the root directory with your Zendesk credentials:
ZENDESK_SUBDOMAIN=your-subdomain
ZENDESK_EMAIL=your-email@example.com
ZENDESK_API_TOKEN=your-api-tokenYou can copy the .env.example file and fill in your details:
cp .env.example .envBuild the project:
npm run buildStart the server:
npm startThe server will run on standard input/output, making it compatible with Claude Desktop and other MCP clients.
The server provides the following tools:
Search for articles in your Zendesk Help Center.
Parameters:
query (string, required): Search keyword
locale (string, optional): Locale code (e.g., 'en', 'ja', 'en-us')
page (number, optional): Page number
per_page (number, optional): Number of results per page (max 100)
Get details of a specific Zendesk Help Center article by ID.
Parameters:
id (number, required): Article ID
locale (string, optional): Locale code (e.g., 'en', 'ja', 'en-us')
mcpServers ConfigurationAdd the following configuration to the mcpServers section in Claude's settings file:
{
"mcpServers": {
"zendeskHelpCenter": {
"command": "npx",
"args": ["-y", "github:hidechae/zendesk-help-center-mcp-server"],
"env": {
"ZENDESK_SUBDOMAIN": "your-subdomain",
"ZENDESK_EMAIL": "your-email@example.com",
"ZENDESK_API_TOKEN": "your-api-token"
}
}
}
}After adding this configuration, you can use the Zendesk Help Center tools within Claude.
This project uses TypeScript and follows the Model Context Protocol specification.
To run in development mode with auto-reloading:
npm run devMIT
Contributions are welcome! Please feel free to submit a Pull Request.
Get details of a specific Zendesk Help Center article by ID
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Article ID | |
| locale | No | Locale code (e.g., 'ja', 'en-us') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the burden of behavioral disclosure. 'Get details' implies a read-only operation, but it does not mention potential locale behavior, error cases, or return specifics. It conveys the core behavior but lacks deeper context, which is acceptable for a simple getter but not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that conveys the essential information without any filler. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get-by-id tool with full schema documentation, the description is sufficiently complete. It states what the tool does, and the schema covers parameters. The lack of an output schema is not a gap because the description says it returns 'details' and the tool is trivial in scope. It could mention locale behavior, but that is not necessary for basic usability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already describes both 'id' and 'locale'. The description adds minimal semantic value beyond repeating 'by ID', which reinforces the 'id' parameter but does not elaborate on 'locale' or provide additional meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Get' and clearly identifies the resource as 'a specific Zendesk Help Center article by ID'. This clearly distinguishes it from the sibling tool 'searchArticles', which is for searching rather than retrieving by ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'by ID' clearly indicates this tool is for retrieving a known article, which implies when to use it. However, it does not explicitly mention when not to use it or name the alternative 'searchArticles'. Thus it provides clear context but lacks explicit exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for articles in Zendesk Help Center
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number | |
| query | Yes | Search keyword | |
| locale | No | Locale code (e.g., 'ja', 'en-us') | |
| per_page | No | Number of results per page (max 100) |
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 only states the action without revealing read-only nature, pagination behavior, return format, or other important traits. Minimal insight beyond the basic purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that directly states the tool's purpose. It is front-loaded and contains no filler or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is too minimal for the tool's context. There is no output schema, so the return value is not explained. Behavioral traits (e.g., read-only, pagination) are absent, and there is no guidance on how this relates to 'getArticle.' More context is needed for reliable agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides descriptions for all four parameters (query, locale, page, per_page), so a baseline of 3 applies. The description adds no additional parameter semantics beyond what the schema already covers.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Search for articles in Zendesk Help Center.' It uses a specific verb ('Search') and resource ('articles'), and the sibling tool 'getArticle' suggests a distinct operation (fetching a single article), providing implicit differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when searching for articles, but it does not provide explicit guidance on when to use this tool versus alternatives like 'getArticle.' No exclusions or conditional contexts are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
searchArticles and getArticle have clearly distinct purposes: one searches across articles, the other retrieves a single article by ID. There is no overlap or ambiguity between the two operations.
Both tool names follow the verb_noun pattern in camelCase: searchArticles and getArticle. This is consistent and predictable.
With only 2 tools, the server feels minimal and borderline thin. It covers basic read operations but omits many common Help Center actions, making the scope seem constrained.
The server only provides search and get-by-ID, lacking list, create, update, or delete operations for articles. This is a significant gap for a Help Center server, as browsing categories or sections without search is impossible.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search and query nTop's knowledge base and engineering guides from AI applications.
Search your knowledge bases from any AI assistant using hybrid RAG.
Search the Cerebrium docs: deployment, cerebrium.toml, hardware, endpoints. Also sends feedback.
Read and write knowledge-base articles, categories, snippets, glossary, readers, and search data.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hidechae/zendesk-help-center-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
