Search: llm
Search MCP servers and agent skills by name, description, category or topic — 553 results.
mediar-ai/screenpipe
Local-first system capturing screen/audio with timestamped indexing, SQL/embedding storage, semantic search, LLM-powered history analysis, and event-triggered actions - enables building context-aware AI agents through a NextJS plugin ecosystem.
firecrawl/firecrawl-mcp-server
Official Firecrawl server with live browser interaction (`firecrawl_interact`) — navigate, click, type, and scroll on a page before extraction, for JS-heavy or auth-gated sites. Also scrape, crawl, map, search, and extract.
Lum1104/understand-anything
Interactive codebase knowledge graphs via multi-agent LLM analysis
coreyhaines31/ai-seo
Optimize content to appear in AI-generated answers and LLM search results
pydantic/pydantic-ai/mcp-run-python
Run Python code in a secure sandbox via MCP tool calls
antv/mcp-server-chart
A Model Context Protocol server for generating visual charts using [AntV](https://github.com/antvis).
DataEval/dingo
MCP server for the Dingo: a comprehensive data quality evaluation tool. Server Enables interaction with Dingo's rule-based and LLM-based evaluation capabilities and rules&prompts listing.
dbt-labs/dbt-mcp
Official MCP server for [dbt (data build tool)](https://www.getdbt.com/product/what-is-dbt) providing integration with dbt Core/Cloud CLI, project metadata discovery, model information, and semantic layer querying capabilities.
us/crw
fastCRW — open-source (AGPL-3.0), self-hostable Rust web crawler & search API for AI agents. Tools: `scrape`, `crawl`, `map`, and SearXNG-backed `search`. Single ~6MB static binary; reproducible 1K-URL benchmarks faster than hosted alternatives. Hosted MCP at [fastcrw.com/mcp](https://fastcrw.com/mcp) (Streamable HTTP, OAuth) or self-host.
huggingface/hugging-face-evaluation
Model evaluation with vLLM/lighteval and eval tables
basicmachines-co/basic-memory
Persistent, local-first AI memory: a semantic knowledge graph of plain Markdown files that humans and LLMs both read and write. Works with any MCP client, with optional cloud sync and team workspaces.
NVIDIA/Megatron-Bridge/adding-model-support
Guide for adding support for new LLM or VLM models in Megatron-Bridge.
NVIDIA/Megatron-Bridge/perf-sequence-packing
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying the right CP...
NVIDIA/Model-Optimizer/deployment
Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM.
NVIDIA/Model-Optimizer/evaluation
Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL).
NVIDIA/Model-Optimizer/launching-evals
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher.
NVIDIA/NeMo-Evaluator/byob
Create custom LLM evaluation benchmarks using the BYOB decorator framework.
NVIDIA/NeMo-Evaluator-Launcher/launching-evals
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher.
luminati-io/brightdata-mcp
Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Comet-ML/Opik-MCP
Use natural language to explore LLM observability, traces, and monitoring data captured by Opik.
idosal/git-mcp
[gitmcp.io](https://gitmcp.io/) is a generic remote MCP server to connect to ANY [GitHub](https://www.github.com) repository or project for documentation
tinyfish-io/agentql-mcp
MCP server that provides [AgentQL](https://agentql.com)'s data extraction capabilities.
designcomputer/mysql_mcp_server
MySQL database integration with configurable access controls, schema inspection, and comprehensive security guidelines
NeoLabHQ/write-concisely
Applies the famous *The Elements of Style* book principles to make documentation and writing clearer and more professional by eliminating wordiness and improving structure.
NeoLabHQ/code-review
Comprehensive PR code review using specialized agents: bug-hunter, security-auditor, code-quality-reviewer, contracts-reviewer, historical-context-reviewer, test-coverage-reviewer
NeoLabHQ/reflexion
Self-refinement loop that forces the LLM to reflect on previous output and correct itself.
NeoLabHQ/sdd
Spec-driven development workflow that transforms prompts into production-ready implementations through structured planning, architecture design, and LLM-as-a-Judge based quality gates.
NeoLabHQ/ddd
Domain-driven development skills that also include Clean Architecture, SOLID principles, and design patterns.
NeoLabHQ/sadd
Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, controlled development.
NeoLabHQ/kaizen
Applies continuous improvement methodology with multiple analytical approaches, based on Japanese Kaizen philosophy and Lean methodology.
NeoLabHQ/prompt-engineering
Widely used prompt engineering techniques and patterns, including Anthropic best practices and agent persuasion principles.
microsoft/playwright-mcp
Official Microsoft Playwright MCP server, enabling LLMs to interact with web pages through structured accessibility snapshots
Ihor-Sokoliuk/MCP-SearXNG
A Model Context Protocol Server for [SearXNG](https://docs.searxng.org)
LvcidPsyche/auto-browser
Open-source MCP-native browser agent with human takeover via noVNC, reusable auth profiles, and approval/audit rails. Playwright + FastAPI, Docker-based isolated sessions, stdio bridge for Claude Desktop and Cursor.
alinaqi/claude-bootstrap
Opinionated project initialization with security-first guardrails, spec-driven atomic todos, LLM testing patterns, and CLI tool orchestration (gh, vercel, supabase)
jtang613/GhidrAssistMCP
A native Model Context Protocol server for Ghidra. Includes GUI configuration and logging, 31 powerful tools and no external dependencies.
ronak-create/FableCut
Zero-dependency browser video editor that AI agents drive through a JSON timeline. MCP tools to add/patch clips, keyframes, transitions, text animations and filters, import media, and analyze a reference video into an edit blueprint (shots, beats, BPM, drop); the open editor UI live-reloads on every change and exports via ffmpeg.
devflowinc/trieve
Crawl, embed, chunk, search, and retrieve information from datasets through [Trieve](https://trieve.ai)
zinja-coder/jadx-ai-mcp
JADX-AI-MCP is a plugin and MCP Server for the JADX decompiler that integrates directly with Model Context Protocol (MCP) to provide live reverse engineering support with LLMs like Claude.
genomoncology/biomcp
Biomedical research MCP server providing access to PubMed, ClinicalTrials.gov, and MyVariant.info.
redis/mcp-redis
The Redis official MCP Server offers an interface to manage and search data in Redis.
pab1it0/prometheus-mcp-server
Query and analyze Prometheus, open-source monitoring system.