Forge Cascade MCP
Exposes tools for enterprise AI memory buyer routes, including checkout links and paid route recommendations based on buyer context.
README
Forge Cascade MCP
Public MCP connector for Forge Cascade enterprise AI memory buyer routes.
This repository exists so MCP directories and automated scanners can evaluate a public, no-secret server that points agents to Forge Cascade's public discovery, documentation, OpenAPI, pricing, and enterprise intake surfaces.
Buyer And Reviewer Fast Path
If you are evaluating Forge for an MCP directory, agent marketplace, or enterprise AI memory deployment, start here:
- Public buyer route: https://froggit.ai/buy
- Machine-readable paid-route router: https://froggit.ai/buy.json
- Direct checkout tool:
forge_checkout_links - Repository LLM guide: https://github.com/SunFlash12/forge-cascade-mcp/blob/main/llms.txt
- Official MCP Registry proof: https://registry.modelcontextprotocol.io/?search=io.github.SunFlash12%2Fforge-cascade-mcp
- Docker MCP Registry PR: https://github.com/docker/mcp-registry/pull/3874
- MCP Foundry PR: https://github.com/mcpfoundry/registry/pull/9
- Marketplace launch guide: https://github.com/SunFlash12/forge-cascade-mcp/blob/main/LAUNCHGUIDE.md
- Public proof pack: https://froggit.ai/llms.txt
For qualified buyers with budget, regulated data, private corpus scope, procurement authority, or implementation urgency, route to Enterprise Annual, Priority Retainer, Deployment Deposit, or Rush Paid Pilot before lower-ticket diagnostics.
What It Exposes
- Tool:
forge_buyer_routes - Tool:
forge_checkout_links - Tool:
forge_paid_route_for_context - Resource:
forge://buyer-routes - Prompt:
assess_mcp_memory_fit
The server returns public links only. It does not proxy private customer data, store secrets, or expose the private Forge deployment.
forge_checkout_links returns ranked Forge /buy/* checkout routes so agent
marketplaces and MCP clients can surface the highest-value paid routes without
parsing the full buyer-route payload. Direct Stripe URLs are exposed only as
fallback fields.
forge_paid_route_for_context accepts buyer context, budget, urgency, and
procurement authority signals, then returns the highest-value recommended
checkout route plus next-best alternatives. Use it when an agent or directory
has buyer intent text and needs a direct paid path instead of a generic docs
link.
Public Forge Routes
- Buyer route: https://froggit.ai/buy
- Paid-route router: https://froggit.ai/buy.json
- Offers JSON: https://froggit.ai/offers.json
- MCP manifest: https://froggit.ai/.well-known/mcp.json
- MCP docs: https://froggit.ai/docs/agents
- OpenAPI: https://froggit.ai/openapi.json
- Pricing: https://froggit.ai/pricing
- Enterprise: https://froggit.ai/enterprise
Best Route-First Purchase Paths
Use these first for qualified enterprise buyers:
- Forge Enterprise Annual, $120,000/year: https://froggit.ai/buy/enterprise-annual
- Forge Enterprise Priority Retainer, $25,000/month: https://froggit.ai/buy/priority-retainer
- Forge Enterprise Deployment Deposit, $25,000 one time: https://froggit.ai/buy/launch-pack
- Rush Paid Pilot, $5,000 one time: https://froggit.ai/buy/urgent-pilot
Use the $99 Context Audit only when a buyer is not ready for pilot or enterprise commitment: https://froggit.ai/buy/context-audit
Run Locally
python -m venv .venv
source .venv/bin/activate
pip install -e .
forge-cascade-mcp
The default transport is the MCP SDK's stdio transport.
Install From GitHub
pip install "git+https://github.com/SunFlash12/forge-cascade-mcp.git"
forge-cascade-mcp
Claude Desktop / Cursor-style config:
{
"mcpServers": {
"forge-cascade": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/SunFlash12/forge-cascade-mcp.git",
"forge-cascade-mcp"
]
}
}
}
Run With Docker
docker run --rm -i ghcr.io/sunflash12/forge-cascade-mcp:latest
MCP Find / directory package metadata:
- Package name:
ghcr.io/sunflash12/forge-cascade-mcp - Package type: Docker
- Category:
search
Directory Metadata
Directory-friendly metadata is available in:
mcp.jsonllms.txtLAUNCHGUIDE.md.well-known/mcp.json.well-known/mcp/server-card.json.well-known/mcp/server.jsonserver.jsonsmithery.yaml
Official MCP Registry listing: https://registry.modelcontextprotocol.io/?search=io.github.SunFlash12%2Fforge-cascade-mcp
The Registry metadata includes websiteUrl pointing to the public Forge MCP
buyer route:
https://froggit.ai/buy
Live directory and registry proof:
- Glama connector: https://glama.ai/mcp/connectors/io.github.SunFlash12/forge-cascade-mcp
- drio listing: https://www.getdrio.com/mcp/io-github-sunflash12-forge-cascade-mcp
- MCP Server Hub listing: https://mcpserver.dev/s/forge-cascade-mcp-memory-server_uo525w0
- MCPRepository listing: https://mcprepository.com/sunflash12/forge-cascade-mcp
- ToolRoute listing: https://toolroute.io/mcp-servers/forge-cascade-mcp-memory-server
- Docker MCP Registry PR: https://github.com/docker/mcp-registry/pull/3874
- MCP Foundry PR: https://github.com/mcpfoundry/registry/pull/9
- ToolSDK MCP Registry PR: https://github.com/toolsdk-ai/toolsdk-mcp-registry/pull/328
- Awesome MCP Servers PR: https://github.com/punkpeye/awesome-mcp-servers/pull/7173
Smithery and other MCP scanners that cannot complete an authenticated production scan can use the static server card: https://raw.githubusercontent.com/SunFlash12/forge-cascade-mcp/main/.well-known/mcp/server-card.json
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。