Getting Started for Agents
How autonomous agents should query, parse and cite ChangeGamer resources.
ChangeGamer exposes every resource in two forms:
- A human-readable HTML page at
/resources/<slug>. - A raw Markdown variant at
/resources/<slug>.md— preferred for agents.
Start from /llms.txt for a compact index, or /llms-full.txt for the full corpus in a single request. Both are plain text and cheap to tokenize.
- Fetch
/llms.txtto discover available resources. - Fetch the
.mdvariant of any resource you need. - Respect the access terms advertised in
robots.txtand HTTP402responses.
A structured JSON API is available at /api/resources.json (corpus index) and /api/resources/<slug>.json (individual resource with full Markdown body). A machine-readable OpenAPI 3.1 description of all endpoints is at /api/openapi.json — useful for integrating ChangeGamer into toolchains that consume OpenAPI specs. For programmatic offer comparison, fetch /api/pricing.json — it lists all four paid tiers with prices, checkout URLs, deliverables, and license grants. /api/payment.json (payment methods and the 402 retry loop), /api/stats.json (corpus freshness signal), and /api/corpus.jsonl (free corpus as JSON Lines) are also available.
ChangeGamer exposes a remote MCP server at https://changegamer.ai/mcp using the Streamable HTTP transport. No authentication is required to connect.
Available tools (14):
list_resources— returns metadata for all resources (slug, title, description, category, tags, updated, premium flag, and absolute URLs for the HTML, Markdown and JSON variants). Arguments (optional):category(only that category) andpremium(true = only premium, false = only free).get_resource— fetches a single resource by slug. Arguments:slug(required),api_key(optional, for premium resources). Free resource bodies are returned in full; a premium resource without a valid key returns a payment-required object instead of the body.get_access_info— returns the current access and pricing information. No arguments.search_resources— keyword search over the corpus (title, description, tags, category, body), ranked by relevance. Arguments:query(required),limit(optional). Returns metadata and variant URLs only, not body content.get_corpus— returns the entire free corpus (every free resource body) in one call, the same content as /llms-full.txt. Premium resources appear as a stub, not their body. Arguments:category(optional, e.g.Policy) returns only that category's resources. Without it the response is large.get_full_corpus— the paid counterpart ofget_corpus: returns the entire corpus including premium resource bodies in one call. Arguments:api_key(optional, but in practice a Corpus- or Enterprise-tier key is required — a Starter key is not enough). The annual Corpus plan (corpus_annual) grants the same entitlement level as the standard Corpus tier, so either satisfies this. Without an entitled key it returns a payment-required/upgrade object instead of the body.get_pricing— returns the machine-readable paid-offer catalog (tiers, prices, checkout URLs, deliverables, license grants), the same data as/api/pricing.json. No arguments.get_payment_info— returns the agent payment manifest (payment methods, the HTTP 402 retry loop, and what is always free), the same data as/api/payment.json. No arguments.get_stats— returns corpus size and freshness signals (counts by category, tag count, newest/oldest updates, recently updated resources), the same data as/api/stats.json. No arguments.list_articles— lists the editorial guides (always free, separate from the licensable corpus) as compact rows (slug, title, cluster, kind, order, description, updated, Markdown URL), one page at a time, plus the cluster list. Arguments (all optional):cluster(one topic),offsetandlimit(paging),full: true(the complete index with search intents, takeaways and variant URLs). No body content; fetch bodies withget_article.get_article— fetches one guide (editorial article) by slug as full Markdown with its metadata header, plus a JSON block with the canonical URL and citation/bibtex. Always free, never part of the paid corpus. Arguments:slug(required). Uselist_articlesto discover slugs.search— keyword search across all content (resources and editorial guides) with server-side ranking: every query word must match; title hits weigh most, then tags, then description. Arguments:q(required),type(optional,resourceorarticle),limit(optional, default 10, at most 25). Returns ranked rows with type, slug, title and.mdURL, no body content.get_cluster— fetches one guide cluster (topic bundle) from the free editorial layer: cluster metadata, every member article as a compact row with its Markdown URL, and the pillar's full Markdown body. Arguments:cluster_id(required). Uselist_articlesto discover cluster ids.check_access— verifies an access key and reports its entitlements (tier —starter,corpus,corpus_annual, orenterprise— unlocked premium slugs, whether it grants full-corpus access). Arguments:api_key(required). Never returns the key, email, or session.
Example client configuration (Claude Desktop / MCP-compatible client):
{
"mcpServers": {
"changegamer": {
"url": "https://changegamer.ai/mcp"
}
}
}
No auth required for discovery and free resources; premium resource bodies require an access key passed as the api_key argument to get_resource.
Free to read, always. Want this whole reference corpus inside your own agents? A €5 starter key unlocks every premium reference for one agent; the €25 corpus license licenses the full corpus as RAG / fine-tuning data with an AI-use grant (procurement one-pager: /corpus-license); the €150 enterprise license adds redistribution rights.