Help us improve
Share bugs, ideas, or general feedback.
Scaffolds MCP resource definitions with URI templates and registration. Use when adding a resource, exposing data via URI, or creating a readable endpoint.
npx claudepluginhub cyanheads/cyanheads --plugin fcc-broadband-mcp-serverHow this skill is triggered — by the user, by Claude, or both
Slash command
/fcc-broadband-mcp-server:add-resourceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Resources use the `resource()` builder from `@cyanheads/mcp-ts-core`. Each resource lives in `src/mcp-server/resources/definitions/` with a `.resource.ts` suffix. The standard registration pattern uses a `definitions/index.ts` barrel that collects all resources into an `allResourceDefinitions` array for `createApp()`. Fresh scaffolds start with direct imports in `src/index.ts` — the barrel is i...
Scaffolds MCP resource definitions with URI templates and registration. Use when adding a resource, exposing data via URI, or creating a readable endpoint.
Scaffolds MCP resource definitions with URI templates, params, and pagination. Helps expose data via URI for Model Context Protocol servers.
Scaffolds new MCP resource definitions with URI templates, parameter schemas, and pagination support. Register resources and smoke-test via stdio/HTTP.
Share bugs, ideas, or general feedback.
Resources use the resource() builder from @cyanheads/mcp-ts-core. Each resource lives in src/mcp-server/resources/definitions/ with a .resource.ts suffix. The standard registration pattern uses a definitions/index.ts barrel that collects all resources into an allResourceDefinitions array for createApp(). Fresh scaffolds start with direct imports in src/index.ts — the barrel is introduced as definitions grow. Match the pattern already used by the project you're editing.
Tool coverage. Not all MCP clients expose resources — many are tool-only (Claude Code, Cursor, most chat UIs). Before adding a resource, verify the same data is reachable via the tool surface — either through a dedicated tool, included in another tool's output, or bundled into a broader tool. A resource whose data has no tool path is invisible to a large share of agents.
{paramName} for path parameters (e.g., myscheme://{itemId}/data)src/mcp-server/resources/definitions/{{resource-name}}.resource.tscreateApp() resource list (directly in src/index.ts for fresh scaffolds, or via a barrel if the repo already has one)bun run devcheck to verifybun run rebuild && bun run start:stdio (or start:http)/**
* @fileoverview {{RESOURCE_DESCRIPTION}}
* @module mcp-server/resources/definitions/{{RESOURCE_NAME}}
*/
import { resource, z } from '@cyanheads/mcp-ts-core';
export const {{RESOURCE_EXPORT}} = resource('{{scheme}}://{{{paramName}}}/data', {
description: '{{RESOURCE_DESCRIPTION}}',
mimeType: 'application/json',
// size: 1024, // optional: content size in bytes, if known
params: z.object({
{{paramName}}: z.string().describe('{{PARAM_DESCRIPTION}}'),
}),
// auth: ['resource:{{resource_name}}:read'],
async handler(params, ctx) {
ctx.log.debug('Fetching resource', { {{paramName}}: params.{{paramName}} });
// Pure logic — throw on failure, no try/catch
return { /* resource data */ };
},
list: async (extra) => ({
resources: [
{
uri: '{{scheme}}://all',
name: '{{RESOURCE_LIST_NAME}}',
mimeType: 'application/json',
},
],
}),
});
For resources that return large result sets, include cursor in the URI template params and use opaque cursor pagination in the handler. The cursor arrives as a validated URI param. paginateArray requires a RequestContext for logging — create one from requestContextService:
import { extractCursor, paginateArray, requestContextService } from '@cyanheads/mcp-ts-core/utils';
// URI template: '{{scheme}}://{{{paramName}}}/items'
params: z.object({
{{paramName}}: z.string().describe('{{PARAM_DESCRIPTION}}'),
cursor: z.string().optional().describe('Opaque pagination cursor'),
}),
async handler(params, ctx) {
const allItems = await fetchAllItems(params.{{paramName}});
const cursor = extractCursor({ cursor: params.cursor });
const reqCtx = requestContextService.createRequestContext({
operation: 'list-{{paramName}}',
parentContext: { requestId: ctx.requestId, traceId: ctx.traceId },
});
const page = paginateArray(allItems, cursor, 20, 100, reqCtx);
return {
items: page.items,
nextCursor: page.nextCursor,
};
},
// src/index.ts (fresh scaffold default)
import { createApp } from '@cyanheads/mcp-ts-core';
import { {{RESOURCE_EXPORT}} } from './mcp-server/resources/definitions/{{resource-name}}.resource.js';
await createApp({
tools: [/* existing tools */],
resources: [{{RESOURCE_EXPORT}}],
prompts: [/* existing prompts */],
});
If the repo already uses src/mcp-server/resources/definitions/index.ts, add the export to that barrel instead:
export { {{RESOURCE_EXPORT}} } from './{{resource-name}}.resource.js';
errors[] contractResources can opt into the same typed error contract as tools — bound to a typed ctx.fail(reason, …) keyed by the declared reason union:
import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
export const articleResource = resource('article://{pmid}', {
description: 'Read an article by PMID.',
errors: [
{ reason: 'no_pmid_match', code: JsonRpcErrorCode.NotFound,
when: 'PMID not found in the index.',
recovery: 'Use pubmed_search_articles to discover valid PMIDs first.' },
{ reason: 'withdrawn', code: JsonRpcErrorCode.NotFound,
when: 'Article was withdrawn upstream.',
recovery: 'Check PubMed directly for retraction or withdrawal notices.' },
{ reason: 'upstream_throttled', code: JsonRpcErrorCode.RateLimited,
when: 'Upstream PubMed quota hit.', retryable: true,
recovery: 'Wait a few seconds and retry the request.' },
],
params: z.object({ pmid: z.string().describe('PubMed ID') }),
async handler(params, ctx) {
const article = await fetchOne(params.pmid);
if (!article) throw ctx.fail('no_pmid_match', `PMID ${params.pmid} not indexed`);
if (article.withdrawn) throw ctx.fail('withdrawn');
return article;
},
});
Without errors[], the handler receives plain Context (no fail method) and throws via error factories (notFound, serviceUnavailable, …) directly. The contract is opt-in. See skills/api-errors/SKILL.md for the full pattern, baseline codes, and conformance rules.
resource() optionsBeyond description, params, handler, and list, the builder also supports:
| Field | Purpose |
|---|---|
name | Short human-readable name for resources/list. Defaults to a slug derived from the URI template if omitted. |
output | Optional Zod schema for runtime validation of the handler return value (parity with tool()'s output). |
format | Optional formatter mapping the handler's return to the ReadResourceResult.contents[] shape. Default: string passthrough; objects serialized to JSON. Override when you need to attach permissions, custom encodings, or split into multiple content items. |
annotations | Resource annotations (e.g., audience, priority) — see ResourceAnnotations. |
title | Human-readable display title (defaults to name). |
examples | Array of { name, uri } example entries surfaced in resources/list for discoverability. |
src/mcp-server/resources/definitions/{{resource-name}}.resource.tsresource() uses a valid URI template with {paramName} syntaxparams fields have .describe() annotationsoutput schema added if the handler returns structured data that benefits from runtime validation@fileoverview and @module header presenthandler(params, ctx) is pure — throws on failure, no try/catcherrors[] contract declared: every entry has a recovery field (≥5 words, lint-enforced)src/mcp-server/tools/definitions/ for a tool that exposes this data, or document why this resource is resources-onlylist() function provided if the resource is discoverableextractCursor/paginateArray) — applies to both handler data and list() catalogs with many entriescreateApp() resource list (directly or via barrel)bun run devcheck passesbun run rebuild && bun run start:stdio (or start:http)