mcp-server-starter
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_REPO | No | GitHub repository in `owner/name` form for the GitHub adapter. | |
| MCP_ADAPTER | No | Selects the adapter to use: `memory`, `rest`, or `github`. | |
| GITHUB_TOKEN | No | GitHub token for higher rate limits or private repositories. | |
| MCP_HTTP_TOKEN | No | Bearer token used to authenticate HTTP transport requests. | |
| MCP_ALLOW_WRITES | No | Set to `true` to enable write tools such as `create_item`. The server is read-only by default. | false |
| MCP_PRODUCT_NAME | No | Product name used by the REST adapter, e.g. `Example CRM`. | |
| MCP_REST_API_KEY | No | API key used by the REST adapter. | |
| MCP_ALLOWED_HOSTS | No | Comma-separated allowed Host header values for HTTP DNS-rebinding protection, e.g. `mcp.example.com`. | |
| MCP_REST_BASE_URL | No | Base URL of the JSON REST API for the REST adapter. | |
| MCP_REST_ITEM_PATH | No | Overrides the REST adapter item path. | |
| MCP_ITEM_DESCRIPTION | No | Description of the items exposed by the REST adapter, e.g. `customer records`. | |
| MCP_REST_CREATE_PATH | No | Overrides the REST adapter create path. | |
| MCP_REST_SEARCH_PATH | No | Overrides the REST adapter search path. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Tools for searching and reading help-centre articles in Example Help Centre. Use search_items to find relevant items, then get_item to read one in full.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_itemsA | Search help-centre articles in Example Help Centre. Returns the best matches with a short snippet; call get_item for the full text. |
| get_itemA | Read one of the help-centre articles in full, by id. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| summarize_item | Summarise one of the help-centre articles for a busy reader. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| API rate limits | One of the help-centre articles |
| Exporting your data | One of the help-centre articles |
| Resetting your password | One of the help-centre articles |
| Setting up single sign-on (SSO) | One of the help-centre articles |
TDQS
Scored across 2 tools
The two tools have clearly distinct roles: search_items finds articles with snippets, while get_item retrieves one article in full by id. The descriptions explicitly guide the agent to search first and fetch full text second, leaving no meaningful overlap.
Both names use consistent snake_case verb_noun structure: search_items and get_item. The singular/plural difference is natural and predictable for retrieving one item versus searching many.
Two tools are minimal but well matched to a simple read-only help-centre server: search and retrieve. The surface is slightly thinner than the typical 3–15 range, but neither tool feels redundant or out of place.
For a read-only help-centre article domain, search plus full retrieval covers the core workflow completely. There are no obvious missing create/update/delete operations, and search can serve as the discovery path when the article id is unknown.