MCP Frameworks
SDKs and templates for writing MCP servers. As of 2026-11-21, 18 indexed products offer it (15 with full profiles), in 3 forms: 16 MCP servers, 1 Agent skill, 1 SaaS product. 5 were published in the last 90 days, against 2 in the 90 days before. Arcade has the most GitHub stars, 34% of the total across 15 products with their own repository.
CapabilitySegment label: Thin DERScored as an opportunity
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 16 indexed · 13 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | golfProduction-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents | golf-mcp | 842 | 2mo ago | ||
| 2 | keryxKeryx: The Fullstack TypeScript Framework for MCP and APIs | actionhero | 626 | 11d ago | ||
| 3 | mcpfusionMCP Fusion - The TypeScript framework for secure MCP servers. | vinkius-labs | 256 | 2mo ago | ||
| 4 | MaggAggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime. | sitbon | 143 | 1mo ago | ||
| 5 | turbomcpA full featured, enterprise grade rust MCP SDK | Epistates | 100 | 1d ago | ||
| 6 | awesome-mcp-best-practicesBuild Awesome MCPs with Awesome Best Practices for MCP Servers and MCP Clients | lirantal | 86 | 16d ago | ||
| 7 | awesome-mcp-serversA curated list of Model Context Protocol (MCP) servers and tools. Discover and explore various MCP implementations that enable AI models to connect with external data sources and tools. | habitoai | 24 | 1mo ago | ||
| 8 | awesome-mcp-devtoolsA curated list of 100+ Model Context Protocol (MCP) developer tools — SDKs for 15 languages, frameworks, inspectors, testing and security scanners, proxies, gateways, hosting, and templates for building MCP servers and clients. | Epistates | 13 | 2mo ago | ||
| 9 | vector_mcpA server implementation for the Model Context Protocol (MCP) in Ruby. | sergiobayona | 13 | 1mo ago | ||
| 10 | tinystruct-mcpThe tinystruct-mcp is an extensible MCP server based on tinystruct framework via the Model Context Protocol (MCP). | tinystruct | 11 | 23d ago |
Agent skills 1 indexed · 1 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | anthropics | — | 5d ago |
SaaS products 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | ArcadeTool-calling platform that handles per-user authorisation so agents act in apps like Gmail or Slack on a user behalf; framework for building MCP servers. | Arcade.dev | 1.1k | today |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 16 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 1 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| fastmcp | Ignored |
| mcp sdk | 8 |
| mcp framework | 7 |
| build mcp server | 0 |
| mcp server template | 3 |
| mcp boilerplate | 0 |
Segment statistics
Whole catalogue (18 indexed products). Calculated 2026-11-21.
Thin. Among the smallest 30% of capabilities, and launches are not outpacing the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.233 means stars are spread as if across about 4 equally popular projects — moderately concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Scored as an opportunity
Score breakdownCoverage gap: MCP Frameworks: score 53.3 HEU, competition High, confidence Low. Only 18 indexed products match "MCP Frameworks", against 410 in MCP Development overall.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .