Verified directory

MCP Server Directory

Search Registry metadata and see exactly what our independent monitoring has verified.

65,485 matching servers

Local only llmledger io.github.pouriaetab/llmledger Which AI model, and what it costs: LiteLLM prices, Arena ratings and price history. — latency— 24h packageNot checked Not checked llmmcp io.github.zero-abd/llmmcp MCP server for real-time LLM API documentation — stop hallucinations — latency— 24h packageNot checked Local only LLMnesia com.llmnesia/mcp Search your AI chat history from Claude, Cursor, Codex, and other MCP clients. — latency— 24h packageNot checked Local only llm-oracle io.github.weiseer/llm-oracle Up-to-date LLM pricing + availability catalog with cited sources for AI agent routing. — latency— 24h packageNot checked Local only llmpvp io.github.EnioAguiar/llmpvp Ranked, bring-your-own-LLM chess and Go arena for AI agents. Play rated games via MCP. — latency— 24h packageNot checked Local only llm-redteam io.github.4hmetuyar/llm-redteam Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints — latency— 24h packageNot checked Local only llm-redteam io.github.GuardBee/llm-redteam Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints — latency— 24h packageNot checked Local only llms.txt io.github.basitalisandhu/mcp-llms-txt Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file. — latency— 24h packageNot checked Local only llmscout io.github.RudrenduPaul/llmscout Zero-config SEO and GEO checker: 21 technical-SEO and generative-engine checks for a live site. — latency— 24h packageNot checked Local only LLMScribe io.github.AMRITO-KUNDU/llmscribe Local project map, search and file reader for AI agents. — latency— 24h packageNot checked Local only llmshift io.github.DeChuks-hub/llmshift Find retiring LLM calls in code and test the replacement model on real traffic before switching. — latency— 24h packageNot checked Local only LLMSlim memory io.github.Thanatos9404/llmslim Long-term memory and context fitting for agents, with no LLM in the loop. Local SQLite. — latency— 24h packageNot checked Local only llmstxt-doc-search io.github.praveenc/llmstxt-doc-search BM25 search over llms.txt doc indexes (Strands, Kiro, AWS); sources addable at runtime. — latency— 24h packageNot checked Local only llmtest-mcp io.github.tjacquesson/llmtest-mcp Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models. — latency— 24h packageNot checked Local only llm-toll-mcp io.github.6mickswagger9/llm-toll-mcp x402 paid API for AI agents. USDC on Base. CDP facilitator. — latency— 24h packageNot checked Local only llmtrim io.github.fkiene/llmtrim MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost. — latency— 24h packageNot checked Local only LLMVerify io.github.subodhkc/llmverify Local-first MCP server for LLM output verification — risk signals, injection and PII checks. — latency— 24h packageNot checked Local only llmwiki io.github.atomicstrata/llmwiki Compile documents into a cited knowledge wiki. Retrieve evidence, query, and review via local MCP. — latency— 24h packageNot checked Local only llm-wiki-mcp io.github.flsteven87/llm-wiki-mcp MCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time. — latency— 24h packageNot checked Local only llmxray io.github.LogneBudo/llmxray What went wrong with your own Ollama calls, in sentences with the fix. Local, read-only. — latency— 24h packageNot checked Local only llvm-ir-mcp io.github.mrfentmen/llvm-ir-mcp LLVM IR MCP: 20 real tools to read, check, lint, scaffold, build and run LLVM IR code. — latency— 24h packageNot checked Local only llvm-mcp io.github.mrfentmen/llvm-mcp LLVM MCP: 20 real tools to read, check, lint, scaffold, build and run LLVM code. — latency— 24h packageNot checked Local only llvm-tablegen-mcp io.github.mrfentmen/llvm-tablegen-mcp LLVM TableGen MCP: 20 real tools to read, check, lint, scaffold, build and run LLVM TableGen code. — latency— 24h packageNot checked Local only lm io.github.houtini-ai/lm Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model. — latency— 24h packageNot checked