Persistent memory for coding agents: what one session learns, the next one is told. One local binary, no daemon, no LLM in the loop.
Analytics SDK for Model Context Protocol Servers
MCP server providing AI-powered content workflows for marketing sites — alt text auditing, SEO descriptions, schema.org generation
MCP server for real interactive terminal sessions — REPLs, SSH, databases, Docker
Installer for the TRTC Agent Skills suite (Chat, Call, RTC Engine, Live, Conference) plus manual SDK runtime log troubleshooting and knowledge base, with one-command MCP setup for Claude Code / Cursor
Replicate MCP.
MCP server for traql — AML risk scoring for crypto addresses and transactions on Ethereum, BSC, TRON, TON and Bitcoin.
Pure-ESM Node.js MCP server with automatic tool discovery, Streamable HTTP and stdio transports, TLS, Zod schemas, injectable context, bearer authentication, and generic OAuth2 support.
Runs an agent, such as opencode or one in your own process over an Effect AI language model, and streams every agent's turns in one format.
Framework-aware technical SEO and AI-discoverability (GEO) audits for your codebase, in your editor.
Universal Cloud-to-Local Agent Bridge & MCP Microkernel in Rust. Offload token-heavy code execution, testing, and file operations to any local LLM (Ollama, vLLM, LM Studio) at $0 cost.
lsp-hub MCP bundle: ArkTS/HarmonyOS project intelligence over stdio, backed by an external LSP hub.
Enterprise Model Context Protocol server for Testomat.io API with analytics tools
Context for coding agents: checks a GitHub or Linear issue is ready before your agent starts it.
Frase MCP Server — The complete content platform for AI agents. Research, write, optimize, and host SEO & GEO-optimized content with built-in AI search visibility monitoring. Includes Frase CMS for au
Standalone MCP connector for AppCrane — the self-hosted deployment platform for AI-built apps. Serves the appcrane_* tool catalog for offline introspection and proxies real tool calls to your AppCrane
MCP server for the slab trading-card API — lets a local AI agent search the catalog, read pricing, and manage a collection.
Your code review comments from Reado, the read-first IDE, as context and tools for your agent.
Enhanced Linux filesystem access with symlinks, permissions, and chmod support
Read and resolve human feedback pinned on your live prototype, straight from your coding agent.
Stop flooding your agent's prompt with MCP tools: MCPtoCodeMode puts every MCP server behind 3 tools and a sandbox, for Codex, Claude Code, Cursor, Grok, OpenCode, Pi, or any MCP client.
MCP server for ebi5 — your coding agent pushes little apps straight to your phone. Pair with a code from your ebi5 portal.
Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.
Workit Cursor plugin — shared MCP transport, native hooks, and sixteen method skills
Local-first repository governance and verification tools for AI coding agents.
Workit OpenCode plugin — native tools, adaptive policy, and sixteen method skills
Policy-checked, audited agent access to Postgres, MySQL, SQLite, MongoDB and OpenAPI REST APIs.
MCP server exposing OpenInputBridge (Interception-compatible kernel-level input) as SendInput()-alternative tools for GUI/native-app test automation.
MCP server that hands your Notepix browser annotations (and their screenshots) straight to an AI coding agent.
MCP server for SearXNG web search.
Official TrustyCap SDK for TypeScript and JavaScript. The production backend a working application still needs: Managed Storage, Managed Data, Managed Jobs, Reliable Webhooks, Transactional Messaging,
Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and security.
Audits any live MCP server URL or GitHub repo on Glama's 6-dimension TDQS rubric and compiles drop
F5 Distributed Cloud Terraform provider docs, 270+ OpenAPI specs, and subscription info for AI.
Semantic code intelligence + refactoring MCP for TypeScript/JS: one LSP-backed execute tool — call graphs, impact analysis, symbol dependencies, atomic multi-file refactors
Use Llama AI Chat to test Meta Llama 4 Maverick on code review, long PDFs, and screenshots.
Gesamtes Verzeichnis
IDEs, git, Linting und Codeanalyse. 8,505 Server, die meistgenutzten zuerst. Jeder öffnet die Seite des Herausgebers.