changegamer

Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
64%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,550token 数(工具定义)
~512 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 1.21%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "changegamer": {
      "url": "https://changegamer.ai/mcp"
    }
  }
}

远程端点

https://changegamer.ai/mcpstreamable-http

它能做什么

工具清单

工具(14)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢list_resources

List all ChangeGamer resources with metadata and absolute URLs. Returns slug, title, description, category, tags, updated date, premium flag, and HTML/Markdown/JSON variant URLs. No body content.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_resource(slug, api_key)

Fetch a ChangeGamer resource by slug. Free resources return full metadata and Markdown body. Premium resources require a valid api_key; without one a payment-required object is returned.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Resource slug (e.g. \"getting-started\")"
    },
    "api_key": {
      "type": "string",
      "description": "Access key for premium resources"
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_access_info

Return current access and pricing information for ChangeGamer resources.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢search_resources(query, limit)

Search the ChangeGamer corpus by keyword. Ranks resources by relevance across title, description, tags, category, and body, and returns metadata plus HTML/Markdown/JSON URLs (no body content). Use this to find resources before fetching them with get_resource.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search keywords, e.g. \"retrieval augmented generation\" or \"mcp auth\""
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "description": "Maximum number of results (default 10)."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_corpus

Return the entire free corpus as one document (every free resource title, description, canonical URL, and full Markdown body) — the same content as /llms-full.txt. Premium resources appear as a stub with a purchase link, not their body. Use this to ingest everything in a single call; the response is large.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_full_corpus(api_key)

Return the ENTIRE corpus including premium resource bodies in one document — the keyed deliverable of the Corpus/Enterprise license. Requires a Corpus- or Enterprise-tier api_key (a Starter key unlocks premium resources but NOT the corpus file); without an entitled key a payment-required/upgrade object is returned. The free, premium-stubbed version is get_corpus.

输入模式

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "description": "Corpus/Enterprise license key (cg_...)"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_pricing

Return the full paid-offer catalog: every tier with price, currency, interval, checkout URL, what it unlocks, deliverables, and license grant — plus the free layer and premium slug list. Same data as /api/pricing.json.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_payment_info

Return the agent payment manifest: every way to pay (HTTP 402 + Bearer key, MCP, Stripe checkout, x402, RSL per-crawl), the exact 402 retry loop, what is always free, and the recommended path per use case. Same data as /api/payment.json.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡get_stats

Return corpus stats: total/free/premium counts, per-category counts, tag count, newest/oldest update dates, the 10 most recently updated resources, feed URLs — plus an editorial block (guide count, words, newest publish) merged at runtime from the static articles index. A small freshness/size signal to poll before deciding whether to re-ingest.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_articles

List all ChangeGamer editorial guides (always free, separate from the licensable corpus): cluster-first hub/spoke graph with every article's title, search intent, word count, takeaways count and variant URLs. No body content — fetch bodies with get_article.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_article(slug)

Fetch one ChangeGamer guide (editorial article) by slug as full Markdown with its metadata header. Always free — never part of the paid corpus. Use list_articles to discover slugs.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Article slug (e.g. \"rag-in-production\")"
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢search(q, limit)

Keyword search across ALL ChangeGamer content (resources and editorial guides) with server-side ranking: term hits in title weigh most, then tags, then description. Returns ranked rows with type, slug, title and .md URL (no body content). Use get_resource/get_article to fetch winners.

输入模式

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Search query — one or more keywords"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "description": "Max results (default 10)"
    }
  },
  "required": [
    "q"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_cluster(cluster_id)

Fetch one ChangeGamer guide cluster (topic bundle) from the free editorial layer: pillar metadata, every sub-article with variant URLs, and the pillar’s full Markdown body. Use list_articles to discover cluster ids.

输入模式

{
  "type": "object",
  "properties": {
    "cluster_id": {
      "type": "string",
      "description": "Cluster id, e.g. \"rag-in-production\""
    }
  },
  "required": [
    "cluster_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢check_access(api_key)

Verify an access key and report what it unlocks. Returns valid:true/false; when valid, the tier, when it was created, the premium slugs it unlocks, and that it grants the gated /api/corpus.full.jsonl + get_full_corpus deliverable. Never returns the key, email, or Stripe session. Use this to confirm a freshly-purchased key works before relying on it.

输入模式

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "description": "Access key to verify (cg_...)"
    }
  },
  "required": [
    "api_key"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本14 个工具
已验证未记录版本14 个工具
已验证未记录版本14 个工具