MCP Server Directory

ATEX AI Gateway io.github.lm203688/atex-ai-gateway

One API key for 6 AI models. Pay-per-use. MCP protocol support with web search.

Model Context Protocol (MCP) server for AI-assisted development of MDK applications.

Independent MCP integration for Autodesk Revit software through a local bridge.

Tabela FIPE io.github.mcp-dir/fipe-mcp

Reference vehicle prices in Brazil (FIPE table), cars, motorcycles and trucks. Browse by brand/model

Notes io.github.mctx-ai/notes

Centralized note store across AI clients: Claude, ChatGPT, Cursor, Codex, Windsurf. Save in one clie

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

Standalone MCP server with PASH compression. Saves ~87% LLM tokens via dynamic tool registration.

structured-output-agent io.github.mikerawsonnz/structured-output-agent

Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Verte

Alephant MCP server for AI cost control, BYO-key routing, 50+ providers, and 320+ models.

Connect Claude to Microsoft Teams — read/send messages, list channels, search chats.

serpmantics io.github.AmauryDvl/serpmantics

French-first SEO: semantic content guides, scoring, E-E-A-T audits for Google, ChatGPT & Claude.

Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside.

Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.

Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.

Write to Figma from any MCP client (Claude Code, Cursor). Complements the read-only official MCP.

Auto-route AI requests to 13 models (Claude, GPT, Gemini, Qwen, DeepSeek). 57% cost savings.

Explore the Claude Code CLI source — browse tools, commands, search code, and more.

Query AI model benchmarks, pricing, and comparisons from rival.tips

Shared knowledge graph, skills, and tool discovery for AI agents through the Model Context Protocol.

Usage-adaptive Obsidian vault search: Hebbian + PageRank + BM25 hybrid ranking.

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.

Gemini 2M context cache for Claude Code — persistent; repeat queries ~8x faster, ~4x cheaper.

CLS++ Memory io.github.rajamohan1950/cls-memory

Cross-LLM persistent memory: store context once, recall it from any AI model.