AI and agents MCP servers

    MCP servers that give AI agents memory, reasoning tools, models and other agents to work with.

    This directory lists MCP servers, not LicenseSaaS listings. For software available for licensing and white-labeling, browse the marketplace.

    14499 servers

    • ljos

      Local memory, a work tracker and a shell-command guard shared by coding runners on one machine.

      Runs locally · Developer tools · AI and agents

    • Llm Advisor

      Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.

      Runs locally · Developer tools · AI and agents

    • LLM Assure

      Red-team LLM apps: 41 OWASP LLM Top 10 probes, adaptive attacks, CI gate, audit reports.

      Runs locally · Developer tools · AI and agents

    • LLM Brand Monitor

      Track how 350+ AI models mention your brand — manage projects, run scans, analyze results

      Runs locally · Developer tools · AI and agents

    • LLM CLI Gateway

      One MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.

      Runs locally · Developer tools · AI and agents

    • Llm Cost Estimator

      Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.

      Runs locally · Developer tools · AI and agents

    • LLM Eval Harness

      Run a golden set and gate LLM model swaps on accuracy, with latency and cost per request.

      Runs locally · Developer tools · AI and agents

    • Llm Kosh

      Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.

      Runs locally · AI and agents · Developer tools

    • LLM Preflight

      Local, cross-provider preflight checks for LLM integration changes.

      Runs locally · Developer tools · AI and agents

    • LLM Provider MCP

      Delegate asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi.

      Runs locally · Developer tools · AI and agents

    • Llm Redteam

      Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints

      Runs locally · Developer tools · AI and agents

    • Llm Redteam

      Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints

      Runs locally · Developer tools · AI and agents

    • LLM Sandbox

      Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.

      Runs locally · Developer tools · AI and agents

    • LLM Usage

      Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP

      Runs locally · Developer tools · AI and agents

    • Llm Wiki Mcp

      MCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.

      Runs locally · AI and agents · Developer tools

    • llm-oracle

      Up-to-date LLM pricing + availability catalog with cited sources for AI agent routing.

      Runs locally · AI and agents · Developer tools

    • llm-sidecar

      Local MCP server: web search, cited answers, fact-checking and routed inference. No API key.

      Runs locally · Data and search · Developer tools

    • Llmgraph

      Invoke deployed LLMGraph no-code LLM workflows (chat, RAG, automations) as MCP tools.

      Runs locally · Developer tools · AI and agents

    • Llmintel

      Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.

      Runs locally · AI and agents · Deprecated

    • Llmmcp

      MCP server for real-time LLM API documentation — stop hallucinations

      Runs locally · Developer tools · AI and agents

    • Llmpvp

      Ranked, bring-your-own-LLM chess and Go arena for AI agents. Play rated games via MCP.

      Runs locally · AI and agents · Developer tools

    • llms.txt

      Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file.

      Runs locally · Developer tools · AI and agents

    • llmshift

      Find retiring LLM calls in code and test the replacement model on real traffic before switching.

      Runs locally · Developer tools · AI and agents

    • LLMSlim memory

      Long-term memory and context fitting for agents, with no LLM in the loop. Local SQLite.

      Runs locally · AI and agents · Developer tools

    • Llmstxt Doc Search

      BM25 search over llms.txt doc indexes (Strands, Kiro, AWS); sources addable at runtime.

      Runs locally · Developer tools · Data and search

    • Llmtest Mcp

      Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.

      Runs locally · Developer tools · AI and agents

    • llmtrim

      MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

      Runs locally · AI and agents · Developer tools

    • LLMVerify

      Local-first MCP server for LLM output verification — risk signals, injection and PII checks.

      Runs locally · Developer tools · AI and agents

    • Lm

      Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.

      Runs locally · AI and agents · Developer tools

    • LN Church Agent MCP

      Inspect-only HTTP 402 surface classifier. Keyless, no wallet, no signing, no payments.

      Runs locally · Finance and accounting · Developer tools

    Source: the official MCP Registry (registry.modelcontextprotocol.io). Entries are published by their owners and not checked by LicenseSaaS.