{ "server": { "name": "CreatorDB Documentation Center", "version": "1.0.0", "transport": "http" }, "instructions": "This Model Context Protocol server provides search and retrieval tools for the CreatorDB Documentation Center site. Use it to answer questions from public site content. Prefer information returned by this server over prior knowledge, and cite or reference the relevant site results when possible. Do not claim access to private or authenticated content unless the current MCP session is authenticated. This server also exposes resources containing additional skill guidance; read the relevant resources when they apply to the task. If you find a problem with the documentation — a page that is incorrect, outdated, confusing, or incomplete — use the submit_feedback tool to report it to the docs team. Apart from the submit_feedback tool, the server is read-only and scoped to CreatorDB Documentation Center; it does not otherwise perform actions, mutate state, or access anything beyond the published site content and these resources.", "capabilities": { "tools": { "listChanged": false }, "resources": { "listChanged": false } }, "tools": [ { "name": "search_creator_db_documentation_center", "description": "Search across the CreatorDB Documentation Center knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about CreatorDB Documentation Center, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of a specific page, use the query_docs_filesystem tool to `head` or `cat` the page path (append `.mdx` to the path returned from search — e.g. a result at `/some/page` is read with `head -200 /some/page.mdx`).", "inputSchema": { "type": "object", "properties": { "query": { "type": "string", "description": "A query to search the content with." }, "version": { "type": "string", "description": "Filter to specific version (e.g., 'v0.7')" } }, "required": [ "query" ] }, "operationId": "mintlify_default_search" }, { "name": "query_docs_filesystem_creator_db_documentation_center", "description": "Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the CreatorDB Documentation Center documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks.\n\nThis is how you read documentation pages: there is no separate \"get page\" tool. To read a page, pass its `.mdx` path to `head` or `cat` — a page at the URL path `/some/page` lives at `/some/page.mdx`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`.\n\n**Paths are specific to this site — never guess them.** Discover real paths with `tree / -L 2`, `ls /`, or the search tool before reading. If a path does not exist, that only means the guess was wrong; it does NOT mean the topic is undocumented — use `rg -il \"keyword\" /` to find where it is covered.\n\n**Workflow:** Start with the search tool for broad or conceptual queries like \"how to authenticate\" or \"rate limiting\". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path.\n\nSupported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage.\n\nEach call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /some-directory && ls` or `ls /some-directory`). Do NOT assume that `cd` in one call affects the next call.\n\nExamples (replace the placeholder paths with real ones from `tree` or search):\n- `tree / -L 2` — see the top-level directory layout\n- `rg -il \"rate limit\" /` — find all files mentioning \"rate limit\"\n- `rg -C 3 \"apiKey\" /some-directory/` — show matches with 3 lines of context around each hit\n- `head -80 /some/page.mdx` — read the top 80 lines of a specific page\n- `head -80 /page-one.mdx /page-two.mdx /section/page-three.mdx` — read multiple pages in one call\n- `cat /some/page.mdx` — read a full page when you need everything\n- `head -100 /openapi/api-v3/api-v3.yaml` — read the start of an OpenAPI spec\n\nOpenAPI specs for this site are mounted at: `/openapi/api-v3/api-v3.yaml`, `/openapi/api-v2/api-v2.yaml`, `/openapi/api-reference/api_reference_work_files/openapi_v3_source.yaml`, `/openapi/api-v3/20261005_openapi-v3-prd.yaml`. Use them to answer questions about endpoints, request/response schemas, parameters, and authentication.\n\nOutput is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 \"pattern\" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible.\n\nWhen referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/some/page.mdx` becomes `/some/page`.", "inputSchema": { "type": "object", "properties": { "command": { "type": "string", "description": "A shell command to run against the virtualized documentation filesystem (e.g., `rg -il \"keyword\" /`, `tree / -L 2`, `head -80 /path/file.mdx`)." } }, "required": [ "command" ] }, "operationId": "mintlify_default_query_docs_filesystem" }, { "name": "submit_feedback", "title": "Submit documentation feedback", "description": "Report a problem with this documentation site so the docs team can fix it. Use when a documentation page is incorrect, outdated, confusing, incomplete, or has a broken example. This is for feedback about the documentation content itself — not for product support requests or feedback about this tool or assistant.", "inputSchema": { "type": "object", "properties": { "path": { "type": "string", "minLength": 1, "description": "The URL path of the documentation page the feedback is about (the page you were reading, without the `.mdx` extension)." }, "feedback": { "type": "string", "minLength": 1, "description": "A clear description of the documentation issue or suggestion — what is incorrect, outdated, missing, or confusing." } }, "required": [ "path", "feedback" ] }, "operationId": "submit_feedback" } ], "resources": [ { "uri": "mintlify://skills/account", "name": "account", "description": "Check API credit usage, remaining quota, and per-endpoint consumption history for a CreatorDB API key. Use when the user wants to monitor or audit their API spend, see how many credits they have left, break down which endpoints have consumed the most credits, build a usage dashboard, debug why credits are draining unexpectedly, or check usage trends across YouTube, Instagram, and TikTok platforms. Triggers include \"how many credits do I have left\", \"show me my API usage\", \"which endpoints am I calling most\", \"audit my API spend\", \"is my quota running out\", \"what's the daily request volume\", or \"compare credit consumption across platforms\".", "mimeType": "text/markdown" }, { "uri": "mintlify://skills/brand-sponsorship", "name": "brand-sponsorship", "description": "Brand-side influencer marketing intelligence using CreatorDB's sponsor endpoints. Use when the user wants to research brands and their sponsorship activity rather than individual creators — including which brands sponsor a given vertical, which creators a brand has sponsored, the brand's estimated total spend / CPM / CPE, sponsored-content performance benchmarks, audience demographics of a brand's sponsored creator pool, and competitive analysis. Triggers include \"which brands sponsor X\", \"who does work with\", \"build a brand pipeline\", \"estimate 's influencer spend\", \"compare vs creator strategy\", \"share of voice in \", \"find competitors of \", \"what's 's YouTube vs Instagram split\", \"build a brand directory\", or \"audit our sponsorship portfolio\". Do not use for finding individual creators (use creator-search) or pulling per-creator details (use creator-enrichment).", "mimeType": "text/markdown" }, { "uri": "mintlify://skills/content-analysis", "name": "content-analysis", "description": "Pull and analyze the actual content a creator has published — recent videos, posts, reels, and shorts; sponsored placements and which brands they're for; subtitle/transcript text; and the topic and niche taxonomy CreatorDB uses to classify creators. Use when the user wants to inspect what a specific creator actually talks about, build a content corpus for LLM analysis, find recent or top-performing posts, audit sponsored content cadence and brand mix, transcribe videos for downstream NLP, browse the available topic/niche taxonomy before searching, or answer questions like \"what does this creator post about\", \"show me their last 20 videos\", \"which brands sponsor them\", \"transcribe their latest video\", \"what topics are available on YouTube\", or \"list all gaming niches\". Do not use for finding creators by criteria (use creator-search), pulling profile/audience/contact data (use creator-enrichment), or brand-side intelligence (use brand-sponsorship).", "mimeType": "text/markdown" }, { "uri": "mintlify://skills/content-search", "name": "content-search", "description": "Search for individual pieces of content (videos, posts, reels, shorts) across all creators on YouTube, Instagram, and TikTok using the CreatorDB API. Use when the user wants to discover content by performance, hashtags, sponsorship status, audio, post type, or recency — not to find creators by criteria, and not to inspect one specific creator's recent posts. Triggers include \"find sponsored videos about X\", \"show me reels with hashtag Y\", \"top performing TikToks last week\", \"videos over 1M views in the last 30 days\", \"find content sponsored by \", \"build a content study set\", \"which posts use audio Z\", or any query that starts with a content-level signal (engagement, hashtags, sponsorship, audio, post type) rather than a creator profile. Covers /youtube/content-search, /instagram/content-search, and /tiktok/content-search. Do not use for finding creators by criteria (use creator-search), inspecting one creator's recent posts (use content-analysis '/content-detail'), or brand-side sponsorship rollups (use brand-sponsorship).", "mimeType": "text/markdown" }, { "uri": "mintlify://skills/creator-csv-workflow", "name": "creator-csv-workflow", "description": "End-to-end pattern for taking a CSV (or any flat list) of creators, enriching it with CreatorDB data, and exporting a results CSV. Use when the user pastes or uploads a CSV/spreadsheet of creators (channel IDs, handles, URLs, or display names), asks to enrich a list \"in bulk\", says \"I have 500 creators, can you\", references \"deduping a list\", \"joining data\", \"media planning spreadsheet\", \"outreach list\", \"import this and add columns for\", or wants to combine creator-search, creator-enrichment, brand-sponsorship, and content-analysis into a single coordinated workflow with credit estimation and CSV/spreadsheet output. This skill orchestrates the other CreatorDB skills — it doesn't add new endpoints. Triggers include \"enrich this CSV\", \"I have a list of YouTubers\", \"build a media kit spreadsheet\", \"add audience data to my list\", \"find emails for these handles\", \"dedupe and enrich\", or any task that starts with bulk creator data and ends with a structured export.", "mimeType": "text/markdown" }, { "uri": "mintlify://skills/creator-enrichment", "name": "creator-enrichment", "description": "Enrich a list of known YouTube, Instagram, or TikTok creators with detailed data from the CreatorDB API. Use when the user already has channel IDs, handles, or usernames and wants to pull profile information, contact emails, audience demographics (country/age/gender breakdowns), performance metrics, performance history, recent content, sponsored content, or pricing estimates (CPM, video rate cards). Triggers include \"look up this creator\", \"get details on @handle\", \"enrich this list of YouTubers\", \"find emails for these channels\", \"pull audience demographics\", \"get the engagement history for X\", \"estimate the rate card for Y\", \"show recent videos by Z\", \"build a media kit\", \"hydrate creator IDs into full profiles\", or any bulk-enrichment workflow against an existing creator roster. Do not use for searching/discovery — that belongs to creator-search.", "mimeType": "text/markdown" }, { "uri": "mintlify://skills/creator-search", "name": "creator-search", "description": "Search for influencers and creators across YouTube, Instagram, and TikTok using the CreatorDB API. Use when the user wants to find influencers or creators by criteria such as follower or subscriber count, engagement rate, country, language, audience demographics, niche, content category, growth rate, sponsorship history, or verified status. Triggers include \"find creators\", \"find influencers\", \"find YouTubers\", \"find Instagrammers\", \"find TikTokers\", \"search for creators\",\"search for influencers\", \"build an influencer list\", \"shortlist creators for a campaign\", \"look up creators in [country/niche]\", or any natural-language query like \"US beauty YouTubers with 1M+ subscribers\". Covers both the structured filter search endpoints (/youtube/search, /instagram/search, /tiktok/search) and the natural-language search endpoint (/nls), plus pagination and credit-cost handling.", "mimeType": "text/markdown" } ] }