The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
npx ecc-install --profile fullFair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
npx n8nAn open-source AI agent that brings the power of Gemini directly into your terminal.
npx @google/gemini-cli[!NOTE] More frameworks, utilities, and other developer tools are available at https://github.com/punkpeye/awesome-mcp-devtools
- Nyrok/flompt
π βοΈ - Visual AI prompt builder MCP server. Decompose any prompt into 12 semantic blocks and compile to Claude-optimized XML. Tools:
decompose_prompt,compile_prompt. Setup:claude mcp add flompt https://flompt.dev/mcp/
βοΈ π - AI Agent Mission Control with 200+ MCP tools. Manage agents, experiments, workflows, crews, skills, and more via stdio + HTTP/SSE. Self-hosted, open-source (AGPL-3.0). Remote server: https://fleetq.net/mcp
π π π - Source-available, self-hosted AI workflow automation platform. Build multi-agent, RAG, and tool-using pipelines on a visual canvas, then expose any workflow as an MCP server (stdio/SSE/Streamable HTTP), or call external MCP servers from the agent node.Supports Claude Code, Codex, Cursor, Windsurf, Mcp
Carries strong trust indicators from repository metadata
83984 GitHub stars recorded
MCP is an open protocol that enables AI models to securely interact with local and remote resources through standardized server implementations. This list focuses on production-ready and experimental MCP servers that extend AI capabilities through file access, database connections, API integrations, and other contextual services.
ποΈ β official implementation
programming language
scope
operating system
[!NOTE] Confused about Local π vs Cloud βοΈ?
- Use local when MCP server is talking to a locally installed software, e.g. taking control over Chrome browser.
- Use cloud when MCP server is talking to remote APIs, e.g. weather API.
ποΈ - A Gin-like framework for building MCP servers in Go. Struct-tag auto schema, middleware chain, auth, tool groups, adapters for Gin/OpenAPI/gRPC, async tasks, Inspector UI.
ποΈ π π πͺ π§ - Minimal Go wrapper on the official modelcontextprotocol/go-sdk for stdio MCP servers: struct-tag JSON Schema inference, tinymcp library, reference binary tiny-go-mcp, ~5MB static builds. For teams that want go-sdk compliance with minimal boilerplate (go get github.com/kioie/tiny-go-mcp-server/tinymcp@v1.0.0).
π π - File-based Coordination Protocol: behavior governance layer for multi-agent teams. 45 MCP tools (write_task, write_report, write_issue, write_review, lifecycle claim/submit/approveβ¦). Agents coordinate via structured Markdown files (_lifecycle/) β no message broker, no database, just the filesystem. Official MCP Registry: io.github.joinwell52-AI/fcop (v3.2.5). pip install fcop-mcp
π¦ π - Durable, agent-native AI runtime with native MCP client + server and A2A support. Rust core for performance, Python authoring for ergonomics. Features graph-based workflows, durable execution, and multi-agent coordination.
π π - When tool count exceeds LLM context limits, accuracy collapses (248 tools β 12%). graph-tool-call builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy to 82% with 79% fewer tokens. Zero dependencies. Also works as an MCP Proxy β aggregate multiple MCP servers behind 3 meta-tools.
π π - MCP server that exposes RocketRide AI pipelines as tools for Claude, Cursor, and Windsurf. Self-hosted, open-source pipeline tool with multi-LLM support.npx -y obsidian-mcp-seekstone (also: npx -y seekstone)
π π π πͺ π§ - Japan-specific utilities for AI agents: era β Western year conversion (什ε8εΉ΄ β 2026), kanji-to-romaji transliteration, 7-digit postal code lookup, national holiday calendar, hiragana β katakana conversion, full-width β half-width normalization, and statistical Japanese name splitting. 9 tools, MIT licensed, installable via uvx japan-utils-mcp.