Directories by Enterprise DNA
New in the directories
Every collection stays current. This is the freshest end of the index: agents, skills, MCP servers, frameworks, apps, and models added most recently, newest first.
60 recent entries across the browsable collections.
This week 60
DeepSeek Flash Latest
DeepSeek
This model always redirects to the latest model in the DeepSeek Flash family.
DeepSeek Pro Latest
DeepSeek
This model always redirects to the latest model in the DeepSeek Pro family.
DeepSeek V4.1 Flash
DeepSeek
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters o
Ling 3.0 Flash VL
Inclusionai
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception an
Ling 3.0 Flash VL (free)
Inclusionai
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception an
Schematron V2 Small
Inference Net
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instruction
Schematron V2 Turbo
Inference Net
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must
Codestral 2508 (batch)
Mistral
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correc
Ministral 3 8B 2512 (batch)
Mistral
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
Mistral Large 3 2512 (batch)
Mistral
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apa
Mistral Medium 3.1 (batch)
Mistral
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at signifi
Mistral Small 4 (batch)
Mistral
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoni
GPT Astra Latest
OpenAI
This model always redirects to the latest model in the GPT Astra family.
GPT Luna Latest
OpenAI
This model always redirects to the latest model in the GPT Luna family.
GPT Sol Latest
OpenAI
This model always redirects to the latest model in the GPT Sol family.
GPT Terra Latest
OpenAI
This model always redirects to the latest model in the GPT Terra family.
Ternary Bonsai 2 27B
Prism Ml
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token cont
Qwen3.8 27B (free)
Qwen
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks
Fugu Max
Sakana
Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model train
Fugu Ultra v2
Sakana
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language mode
Pareto
Unbiased
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
GLM 5.3 FlashX
Z Ai
GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and l
fal
Various
Easiest & most cost-effective way to use Gen AI. fal.ai is how devs integrate dozens of generative media models. FLUX, Kling, Hailuo +1000 more
Best for: Developers who need quick access to many generative media models
Paper2Agent
Various
Paper2Agent
26zl/cybersec-toolkit
Various
One command installs 670+ security tools on Linux & Termux. Its authorization-gated MCP server works with Claude Code, OpenCode, Codex, Gemini CLI, Ollama-backed agents and other M
Best for: Security practitioners on Linux or Termux who want an AI agent ready with a broad offensive and defensive toolset
402signalhq/402signal
Various
Pre-flight check and signed evidence for agent payments (x402 and MPP): confirm the endpoint is live and the price and recipient match before your agent pays.
Best for: Developers building agents that pay via x402 or MPP and need pre-payment verification.
activeing123/mcptoon
Various
MCP tool discovery burns 71,929 tokens. mcptoon drops it to 581 (−99.2%, measured). Zero dependencies.
Best for: Developers using MCP who want to cut token overhead during tool discovery.
adsagents/adsagent-ai-skills
Various
AdsAgent hosted MCP for Meta, Google Ads & TikTok — public Chatgpt/Claude/Cursor/Grok skill pack + install URLs (Model Context Protocol).
Best for: Developers who want to control ad accounts through AI chat assistants
agent-easy-use/mobile-easy-use
Various
Runtime access for AI coding agents to observe and control Android and iOS apps. Built on Frida, with MCP and Skills.
Alternative to Mobile Next Mobile Mcp
Best for: AI coding agents needing runtime mobile app control
aggrete/aggrete
Various
[](https://glama.ai/mcp/servers/Aggrete/aggrete) 🐍 🏠 ☁️ - Policy proxy that governs what AI assistants can reach and do: refuses forbidden tool calls before the upstream is conta
Best for: Developers who need a lightweight policy gate for AI assistant tool calls
agmonetti/mathmethods-mcp
Various
MCP server for numerical methods and dynamic systems: root finding, integration, ODEs, Monte Carlo, 1D/2D dynamical systems, and combat models.
Best for: Developers who want numerical methods accessible through MCP
AIops-tools/Identity-AIops
Various
Governed AI-ops for Keycloak + authentik identity providers: users, sessions, auth events, OAuth cli
Best for: Developers needing scripted identity operations across Keycloak and authentik
aiulms/codelattice
Various
面向 AI 编程的本地代码图谱分析工具
Alternative to Oraios Serena, Repowise Dev Repowise
Best for: Early adopters seeking a local, Rust-based code graph tool for AI coding context
alexar76/warden
Various
WARDEN — MCP security firewall: vets an MCP server's tool definitions against static-scan rules, a signed threat feed, origin and tool-def pinning before any tool reaches the model
Best for: Developers building MCP servers who need a lightweight pre-model security check
andrewchmr/mxprobe
Various
Email verification for AI agents: send, hold or kill with the reason. CLI, MCP server and hosted API.
Best for: Developers building AI agents that need to check email deliverability risk before sending
antonorlov/mcp-postgres-server
Various
MCP server for PostgreSQL. Works with VS Code, Cursor, Claude Code, Codex, and Windsurf.
Best for: Developers using AI coding tools who need direct PostgreSQL access
ARADIA-systems/aradia-mcp-server
Various
[](https://glama.ai/mcp/servers/ARADIA-systems/aradia-mcp-server) 🎖️ 📇 ☁️ 🏠 🐧 - Turnkey on-premise private Agentic AI systems by ARADIA on dedicated NVIDIA DGX hardware (Spark,
Best for: Enterprises needing private, on-premise agentic AI on NVIDIA DGX systems
arsentev-ai/contextburn
Various
How much of what your coding agent spends is actually work: the share of paid tokens that became output, not context re-reading. Local, no network calls.
Best for: Developers who want to quantify coding agent token waste
artgas1/yandex-metrika-mcp
Various
MCP-сервер к API Яндекс Метрики: полное покрытие — 108 методов Stat, Management и Logs, инструменты порождены из спеки
Best for: Developers building MCP-based integrations with Yandex Metrika who need complete API coverage.
asyntai/mcp-bridge
Various
Connect any local MCP client to your Asyntai account. Bridges stdio to the hosted Asyntai MCP server and handles the OAuth sign-in.
Best for: Developers using local MCP clients who need access to Asyntai's hosted MCP server.
Atomic-Mail/atomic-mail-agentic
Various
Let your agents read, send, and react to email autonomously, without human involvement
Best for: Developers building email-automation agents in TypeScript
Avazbek22/DevProjex
Various
Build safe, token-efficient codebase context for LLMs, AI chats, and coding agents — local-first GUI, TUI, CLI, and a read-only MCP server with Smart Ignore, secret/PII redaction,
Alternative to Repowise Dev Repowise
Best for: Developers who need safe, token-efficient codebase context for LLM workflows.
axionquant/mcp-server
Various
MCP server for AxionQuant. Give AI agents and LLM apps natural-language access to real-time and historical stock prices, fundamentals, SEC filings, earnings, news, sentiment, and a
Best for: Developers building financial AI assistants or LLM apps that need market data.
bguillow-rgb/percolate-mcp
Various
MCP server for the Percolate specialty coffee database — read-only catalog, brew recipes, and pairings for AI assistants
Best for: Developers building AI assistants that need curated specialty coffee reference data
BotHireAgent/BotHireMCPServer
Various
MCP server for BotHire — the machine-to-machine labor market where AI agents hire each other and pay agent-to-agent in USDT/USDC (x402, gasless, multi-chain: Base, Arbitrum, BNB, S
Best for: Developers prototyping agent-to-agent hiring and payments on BotHire
BoxBoxmari/my-pi
Various
Local-first MCP runtime for coding agents with bounded filesystem access, safe writes, AST search, LSP navigation, and Git tooling.
Alternative to Oraios Serena, Repowise Dev Repowise
Best for: Developers building local-first coding agents with MCP
Bristlecone-Logic/bristlecone-logic
Various
Deterministic guardrails and M2M security rails for autonomous AI agents: pre-socket SSRF defense, zero-overhead JSON repair, and sandboxed AST math verification.
Best for: Developers building Python-based autonomous agents that need deterministic safety rails
Capital-W-Holdings/us-property-parcel-real-estate-debt
Various
US real estate debt with the source cited (maturities on 19,821 FHA and CMBS loans in 52 states, 11,956 LIHTC endings, 4,721 HUD expiries), plus family offices, independent sponsor
Best for: Developers building US real estate debt or investment matching tools.
chryaner/terrarium
Various
Real, disposable computers in seconds, for you and your AI agent - fork, break, and revert full VMs from the CLI or over MCP
Best for: Developers and AI agents that need isolated, revertible full VMs on demand.
churichard/fluxmail
Various
Self-hosted email CLI / API / MCP server for AI agents and apps
Best for: Developers building AI agents that need self-hosted email access.
cliwant/mcp-sam-gov
Various
Keyless-first MCP server — 150 tools for US federal + state/local (SLED) government contracting, spending, regulation & partner vetting. SAM.gov, USAspending, Grants.gov, OFAC, FDI
Best for: Developers building MCP clients that need broad U.S. government data access without API keys.
cloudsealed/cloudsealed-mcp
Various
MCP server exposing CloudSealed's billing-waste anomaly detector and architecture risk scorer as tools for AI agents (Claude Code, Cursor, etc.).
Best for: Developers using AI agents who want CloudSealed's cost and risk insights in their workflow
CreativeClawCo/creative-claw-marketplace
Various
CreativeClaw Marketplace
Best for: Developers looking to explore or contribute to an early-stage JavaScript marketplace project.
crisphive/crisphive-mcp
Various
Field operations over MCP — constraint-based scheduling on a deterministic solver, manageable from Claude or ChatGPT. Match crews to jobs by location, skills & availability; bookin
Best for: Builders prototyping field service scheduling for home services using Claude or ChatGPT
CTRLRun/ctrlrun
Various
The execution safety layer for AI agents.
Best for: Developers prototyping safety controls for Python-based AI agents.
Daksh-create349/Contradiction-MCP
Various
Autonomous Model Context Protocol (MCP) engine for factual consistency, version reconciliation, and conflict resolution across engineering knowledge bases.
Best for: Teams building MCP-based workflows that need automated consistency checks in engineering knowledge bases.
danielenricocahall/lorcana-mcp
Various
MCP server for the Disney Lorcana TCG — card search, deck validation, deck stats, and Dreamborn/Pixelborn deck import/export for Claude and other MCP clients.
Best for: Lorcana TCG players and deck builders using MCP clients
denis-samatov/yandex-workspace-mcp
Various
MCP server for Yandex Disk & Wiki — security-first, read-only by default, audit-logged
Best for: Developers needing secure read-only MCP access to Yandex Disk and Wiki.
denisok-ai/magicmaster-mcp
Various
Audio mastering for AI agents via MCP: LUFS/True Peak targets, Suno/Udio AI-fingerprint removal. Hosted server https://magicmaster.pro/mcp
Best for: AI agent builders who need automated audio mastering and Suno or Udio cleanup.
djrobson5/agentmd-mcp
Various
MCP server: convert PDF, DOCX, HTML, and URLs to clean, LLM-ready markdown
Alternative to Microsoft Markitdown
Best for: Developers building LLM pipelines that need quick document-to-markdown conversion via MCP.