Explore

trace-mcp is a framework-aware code intelligence MCP server that indexes a repo into a dependency/knowledge graph once, then serves tools like get_change_impact and plan_turn to agents, cutting PR-review input tokens by 72.7%. Works with Claude Code, Cursor, Codex, and any MCP client.

MCP | TypeScript · mcp-server · code-intelligence

Local-first project management app with a CLI, web UI, MCP server, and skills for coding agents. Agents can manage tasks and project knowledge while their actions are recorded in an activity feed.

AI Tools | Go · AI agents · project management

Apache-2.0 robotics simulator for AI coding agents: Newton physics with wgpu rendering, a 38-endpoint HTTP/JSON harness and a first-party 37-tool MCP server so Claude Code or Cursor can program, run and debug simulated robots. Ships ROS 2 sidecar, URDF/STEP digital twins and 52 demo worlds.

MCP | Python · robotics-simulation · mcp-server

OWASP Agent Memory Guard is a Python runtime defense layer that sits between an AI agent and its memory store, screening writes/reads for prompt injection, memory poisoning, secret leakage, protected-key tampering and self-reinforcement loops. It enforces YAML policies, emits audit events and ships drop-in integrations

AI Tools | Python · agent-memory · ai-security

Provider-agnostic CLI that scaffolds a structured multi-agent coding harness into your repo: shared task backlog, role-based agents, SQLite audit trail, health gate, and a local MCP server that Claude Code, OpenCode, Codex, or Grok can connect to. Stored locally, no cloud or API keys beyond your existing AI tool.

AI Agents | TypeScript · multi-agent · agent-harness

Local-first Kubernetes desktop workspace built with Tauri v2, React 19, and a pure-Rust core for SREs. Its main AI angle is a built-in MCP server that exposes cluster capabilities over stdio or loopback HTTP, with destructive tools confirmation-gated. Dependencies:

MCP | TypeScript · kubernetes · mcp-server

A Rust framework for building tool-using LLM agents, with streaming support across seven protocols, built-in tools, MCP and OpenAPI integrations, sub-agents, and session management. Includes a terminal coding-agent example.

AI Frameworks | Rust · agent loop · tool calling

Blade Code is a TypeScript CLI/Web/headless AI coding agent with 20+ built-in file, search, shell, git and browser tools, MCP and Skills extensibility, subagent orchestration, persistent memory, and unified access to 38+ LLM providers via pi-ai.

AI Coding | TypeScript · cli · coding-agent

Pi/Oh My Pi extension that adds Claude Code-style auto mode: it intercepts agent tool calls and blocks them via permission rules, deterministic hard-deny checks, or an LLM classifier. Includes slash commands, a status line, and read-only diagnostics. Not a sandbox.

AI Coding | TypeScript · auto-mode · guardrails

Embody embeds Envoy, an MCP server exposing 68 tools so AI coding assistants can build, wire, parameterize, and debug live TouchDesigner networks. It also externalizes networks to diffable TDXN YAML for version control and restoration.

MCP | Python · mcp-server · touchdesigner

A TypeScript Nuxt module for creating MCP servers inside Nuxt apps. It discovers tools, resources, prompts, and apps from files, and provides multiple endpoints, validation, and a DevTools inspector.

MCP | TypeScript · MCP server · Nuxt module

A free macOS Apple Silicon workbench for AI safety and interpretability research. Run local MLX models, capture activations, train probes and SAEs, run interventions, and script or automate studies via a Python SDK, HTTP API and MCP bridge.

AI Tools | Swift · ai-safety · interpretability

Rust web-crawling engine that turns sites into clean Markdown and structured metadata, with 14 language bindings plus an MCP server and agent skills for feeding AI agents and RAG pipelines. SSRF-safe, robots-aware, optional headless-browser rendering.

AI Tools | Rust · web-crawling · web-scraping

NVIDIA NeMo Relay is a multi-language agent runtime (Rust core, Python/Node bindings) that adds scopes, middleware, lifecycle events, and plugin-based observability to existing agent stacks. It exports ATOF events, ATIF trajectories, and OpenTelemetry traces without changing your framework or app code.

AI Agents | Rust · agent-runtime · observability

Self-hostable, Apache-2.0 agentic service that runs long-lived AI agent sessions with durable replayable event logs in Postgres, human tool approvals, governed credentials and knowledge, and sandboxes or your own enrolled machines. Ships an API, web app, workers and TypeScript/React SDK.

AI Agents | TypeScript · agents · agent-runtime

AiCode is an Android app that turns a phone into an AI coding workstation: a multi-provider AI agent with file, shell and search tools, an embedded Alpine Linux/PRoot terminal, code editor, Git UI, MCP support and parallel subagents, plus optional remote SSH execution.

AI Coding | Kotlin · android · ai-agent

LISA is a local-first personal AI agent with persistent identity, memory, scheduled autonomous actions, and chat integrations. It supports multiple model providers, MCP, a web UI, a knowledge base, and orchestration of coding-agent CLIs.

AI Agents | TypeScript · autonomous-agent · personal-assistant

Local-first memory engine for coding agents, exposing MCP tools and a self-hosted WebUI. Stores durable code-aware context with bi-temporal history, hybrid retrieval, knowledge graph, and token-efficient recall across sessions and repositories.

AI Agents | Python · agent-memory · local-first

YantrikDB is a Rust cognitive memory engine for AI agents: a vector/knowledge store that consolidates duplicates, detects contradictions, and decays stale memories. Ship it as an embeddable library, HTTP/HA cluster, or MCP server with 15 memory tools.

RAG | Rust · agent-memory · cognitive-memory

Official Search1API MCP server with tools for web and news search, page crawling, sitemap discovery, and trending topics. Connect remotely over HTTP with OAuth 2.1 or an API key, or run locally via npm.

MCP | TypeScript · MCP server · web search

Python SDK and CLI for creating and managing Substack posts, with an optional MCP server exposing the same workflows to AI agents. Draft creation is separate from publishing and includes safeguards for destructive or publishing actions.

MCP | Python · MCP server · Substack

Hermes Dojo is a Hermes Agent skill that closes the self-improvement loop: it reads session logs, ranks failing or missing skills, patches or creates them, runs GEPA self-evolution, and reports measured improvement over time.

Skills | Python · agent-skills · self-improvement

HomeClaw is a macOS menu bar app plus stdio MCP server and CLI that exposes HomeKit accessories, scenes, and automations to Claude Desktop, Claude Code, and OpenClaw over a Unix socket. Use it to control lights, locks, and thermostats from an AI assistant or terminal.

MCP | Swift · mcp-server · homekit

MCP server that exposes SerpApi's Google, Bing, DuckDuckGo, YouTube, Amazon, eBay and other search engines through one `search` tool, with JSON or Markdown output, per-engine schema resources, and an optional MCP Apps UI. Runs hosted or self-hosted over HTTP or stdio.

MCP | Python · mcp-server · search-api

Astro + Cloudflare Pages template for SEO-driven game wiki sites: static, zero-JS, Lighthouse 4x100, AdSense slots, i18n. It bundles AI content skills and an MCP ops tool, but the product itself is a website template, not an AI system.

AI Tools | TypeScript · astro · cloudflare-pages

Self-hosted enterprise platform for deploying DeepSeek Harness agents with a user workspace, admin console, document retrieval, MCP and Skills integrations, workflow governance, and Docker Compose services. Browser and code agents require the separately distributed MOVO Desktop.

AI Agents | Python · enterprise agents · self-hosted

A Rust MCP server that gives coding agents persistent identities, searchable threaded messaging, and advisory file reservations for coordinating parallel work. Includes a Git-backed archive, SQLite indexing, an operator TUI, web UI, and robot CLI.

MCP | Rust · multi-agent coordination · coding agents

Eclipse IDE plugin that exposes the whole workspace as an MCP server over Streamable HTTP, letting Claude Code, Copilot CLI or Codex read, edit, refactor, build, test and debug Java projects through Eclipse APIs. Ships eclipse-ide, eclipse-coder, eclipse-runner, eclipse-context and eclipse-git endpoints plus a built-in

MCP | Java · eclipse · mcp-server

Token-authenticated Notion MCP server for Claude, Cursor, VS Code and other MCP clients. Exposes 47 Notion operations behind 3 tools (94% less schema context) with batch mutations, idempotency, rate-limit retry and markdown round-trip; runs headless via stdio, HTTP or Docker.

MCP | TypeScript · notion · mcp-server

A TypeScript client that runs agent-browser in disposable Vercel Sandboxes. It provides persistent browser sessions, command execution, screenshots, file transfer, and proxy support for agent-driven web automation.

AI Tools | TypeScript · browser automation · computer use

A local-first MCP server, Python client, and CLI that let AI agents edit video through typed, guardrailed tools built around FFmpeg. Supports trimming, captions, repurposing, quality checks, and reviewable edit receipts.

MCP | Python · video editing · video automation

ToolHive Studio is an Electron desktop UI for discovering, installing and running MCP servers in isolated containers, then auto-wiring them into AI clients such as Claude Code, Cursor and Copilot. Adds secret management, a registry browser, playground and HTTP/SSE proxy.

MCP | TypeScript · mcp-server · mcp-client

Unofficial self-hosted Perplexity server exposing MCP tools and OpenAI-compatible endpoints, with multi-account token pooling, load balancing, heartbeat health checks, and deep-research task jobs.

MCP | Python · perplexity · openai-compatible

Type-safe full-stack framework for APIs and React Server Components running on Node, Bun, and Cloudflare Workers. Routes can be exposed as MCP tools for LLMs, with OpenAPI generation, SSE streaming, Zod validation, and a typed fetch client.

MCP | TypeScript · react · rsc

CLI/TUI batch translation fork of AiNiee powered by LLM APIs (OpenAI, Anthropic, Gemini, DeepSeek, local models). Handles 20+ file formats at 100+ async concurrency, with profiles, task queue, RAG glossary reference, plugins, web dashboard and an optional MCP server.

AI Tools | Python · translation · llm

GHOST is a Kotlin Android agent that runs Google Gemma locally via LiteRT-LM as an on-device assistant. It grounds each inference in live telemetry (RAM, thermals, sensors, screen and notification context), with a shake-summoned overlay, TTS, tool calls, and MCP support.

AI Agents | Kotlin · android · on-device-llm

A local-first, multi-agent newsroom that turns documents into a cross-linked Markdown wiki. Separate writer and reviewer roles, automated checks, contradiction tracking, and a reground loop help keep pages reliable and current.

AI Agents | Python · multi-agent · knowledge-base

Minimal TypeScript reference implementation of the Operational Ontology pattern: semantic objects and links over external systems plus actions that enforce preconditions, audit refusals, and write back. Serves the model as MCP tools so AI agents act under the same business rules.

MCP | TypeScript · ontology · operational-ontology

Chinese-language documentation hub (98 guides) for wiring LLM APIs into tools: base URL/key setup for chat clients, coding agents (Claude Code, Codex, Cursor, Cline), local model servers and RAG platforms, plus billing checks and 401/404/429 troubleshooting.

AI Tools | Python · chinese · tutorials

PMAT is a Rust MCP server and CLI that gives AI coding agents deterministic code intelligence: context generation, technical-debt grading, mutation testing, semantic search and git-history RAG over 20+ tools, served over stdio or HTTP with shared tool registry.

MCP | Rust · mcp-server · code-analysis

A TypeScript SDK for running Claude Code, OpenCode, and Codex as interactive server processes inside local or cloud sandboxes. It provides a unified API for sandbox providers, streaming events, approvals, and background work.

AI Coding | TypeScript · coding agents · sandboxing

An AI agent for JupyterLab with a chat interface and CLI. It uses MCP tools to inspect and edit notebooks, execute code, manage files, and help diagnose errors.

AI Agents | Jupyter Notebook · JupyterLab · notebooks

A local MCP server that gives AI clients tools to research crypto tokens using web search and data from CoinGecko, CoinMarketCap, and DeFiLlama. Includes structured research planning, source fetching, and saved resources; most data access requires no API key.

MCP | TypeScript · crypto research · Web3

A read-only MCP server that exposes WHOOP recovery, sleep, HRV, strain, and workout data to Claude, Codex, and GitHub Copilot. Includes tools, resources, and prompt templates for querying personal health trends.

MCP | TypeScript · WHOOP · health data

MultiZen is a desktop Chromium profile manager with a local MCP server for agent-driven browser automation. Profiles retain separate cookies, fingerprints, and proxies, with a human handoff for CAPTCHA and 2FA.

MCP | TypeScript · browser automation · MCP server

A modular Go MCP server that bundles search, documentation, GitHub, code, and utility tools for AI coding agents. Tools can be enabled or disabled by configuration, and the server supports OpenTelemetry observability.

MCP | Go · MCP server · developer tools

An MCP server and coding-agent plugin that routes reviews and questions to GPT, Gemini, Grok, and OpenRouter models. It provides specialist reviewers, multi-model debates and consensus, plus analytics on model usefulness.

MCP | JavaScript · MCP server · multi-agent

An MCP server providing local-first, user-owned AI work identity and memory (preferences, lessons, decisions, playbooks) in inspectable JSON/Markdown files. Any MCP coding tool can read the same approved context, with preview, redaction, and approval controls over writes.

MCP | Python · mcp-server · ai-memory

A collection of portable agent rules, skills, prompt templates and MCP/Claude configs for agentic coding tools like Claude Code and Cline. Useful as a copy-paste starting point for context engineering and workflow setup.

Skills | Python · agent-skills · agent-rules

A TypeScript MCP server that exposes typed Discord operations to AI clients, with permission checks, safety controls, and resumable guild-building workflows. Supports local or bearer-protected HTTP deployment.

MCP | TypeScript · Discord · MCP server

AKB is a self-hostable organizational knowledge base for AI agents, exposed through MCP and REST APIs. It provides permissioned vaults, document and file storage, a URI-based knowledge graph, and hybrid semantic plus BM25 search on PostgreSQL.

MCP | Python · agent memory · knowledge base

A Ruby gem that exposes 45 read-only Rails codebase inspection tools through MCP or a CLI. It gives coding agents ground truth about schemas, models, routes, source, tests, and conventions, including static inspection when the app cannot boot.

MCP | Ruby · MCP server · Rails

Zero-auth HTTP chat and key-value notes for AI agents: every write, including appends, is a plain GET returning text/plain, so an agent with only webfetch is a full peer. Also ships an MCP server, an installable agent skill, /llms.txt API reference, and optional did:key signed writes.

AI Agents | Python · agent-infrastructure · multi-agent

Evener is a Go coding agent that loops over read, write, run and search tools using native LLM tool-calling across OpenAI, Anthropic, Google and many other providers. It ships a hub web UI for concurrent sessions, a TUI, MCP support, subagents, skills, plugins and a non-interactive CLI for CI.

AI Coding | Go · coding-agent · cli

Rust code-intelligence tool that parses code into a deterministic dependency graph and exposes symbol search, call traversal, architecture maps, and impact analysis through CLI and MCP interfaces. Supports multiple languages via Tree-sitter.

MCP | Rust · code intelligence · MCP server

Rust MCP server that gives AI agents a hidden, agent-owned Linux X11 desktop and workspace-owned Chrome over loopback CDP, so agents can do GUI and web automation without touching your real desktop, mouse, or browser sessions.

MCP | Rust · mcp-server · linux

A Java ME Claude chat client for Nokia Series 40 phones, backed by a small Go server that handles modern Claude API requests, web search, pairing, and chat storage. Includes a custom TLS setup for older phones.

AI Tools | Java · Claude · chat client

MCP server giving Claude Desktop, Cursor and other MCP hosts local PDF workflows: view, fill and sign forms, merge/split/reorder pages, extract text or CSV data, and render pages. Runs locally with scoped file access; optional Lumin e-signing is the only external step.

MCP | JavaScript · pdf · claude-desktop

Coddy is a general-purpose ReAct agent shipped as one static Go binary. It exposes the same sessions through a console TUI, an ACP server for editors, an OpenAI-compatible HTTP API with web UI, a Telegram gateway, cron scheduler and swarm relay, with rules, skills, subagents, hooks, MCP, memory and any OpenAI-compatibl

AI Agents | Go · single-binary · tui

Prism Coder is a local-first MCP server that gives coding agents (Claude Code, Cursor, Codex) persistent cross-session memory: handoff notes, open TODOs, knowledge-graph recall, drift detection, and offline Ollama tool-routing with a token-savings meter.

MCP | TypeScript · mcp-server · agent-memory

MCP server plus EasyEDA Pro extension that lets MCP-capable agents read and edit real schematic and PCB documents: generate schematics, resolve components, place and route boards, run DRC, and roll back via document checkpoints.

MCP | TypeScript · easyeda · jlcpcb

A Claude Code skill workflow for auditing research papers for self-consistency, fabrication, citation problems, and evaluation flaws. LLM auditors propose evidence-anchored findings; a deterministic adjudicator produces the verdict.

Skills | Python · agent-skills · research-integrity

A self-hosted AI assistant runtime with multi-agent coordination, business skills, memory, and integrations for chat and work tools. Includes sandboxed execution, credential isolation, approvals, audit trails, and local MLX inference on Apple silicon.

AI Agents | TypeScript · self-hosted · AI assistant

Docker Compose bundle that deploys a full local AI stack: Ollama for LLMs, LiteLLM gateway, AnythingLLM chat UI, embeddings/RAG, Whisper STT, Kokoro TTS, Docling parsing, and an MCP Gateway. Includes lightweight stack variants, optional HTTPS and CUDA GPU acceleration.

AI Frameworks | Shell · self-hosted · docker-compose

MCP server wrapping OpenFate's deterministic Bazi engine: Four Pillars charts, True Solar Time and timezone correction, branch interaction detection, and reverse Bazi lookup. Gives agents stable JSON instead of letting the LLM compute calendrical math. Runs locally over stdio via npx.

MCP | TypeScript · mcp-server · bazi

Neuro SAN is a Python library and HTTP server for building data-driven multi-agent networks defined in HOCON. Agents can call LangChain-based CodedTools, use per-agent or fallback LLMs, expose the network via MCP, and ship with tracing and test tooling.

AI Agents | Python · multi-agent · agent-networks

JToon is a Java library for encoding and decoding TOON, a compact structured-data format for LLM contexts. It supports Java objects, JSON input, Jackson annotations, configurable delimiters, and strict decoding.

AI Tools | Java · TOON · serialization

Companion repo for a book on context engineering: runnable Python/JS/Java/Jupyter examples covering RAG, agent memory, tools and MCP servers, multi-agent orchestration, prompting patterns, evals, and governance. A hands-on reference for building reliable LLM systems.

AI Tools | Python · context-engineering · llm

Local-first MCP server that gives AI agents persistent memory: auto-capture, semantic search over SQLite embeddings, overnight consolidation, a confidence-tracked fact store, and optional AES-encrypted USB sync. Works with Claude, ChatGPT (via REST gate), and local LLM hosts.

MCP | Python · agent-memory · mcp-server

Official Hostinger MCP server exposing ~396 tools across VPS, domains, DNS, hosting, mail, WordPress, ecommerce and billing. Supports hosted remote OAuth endpoint plus local stdio/HTTP install via npm. MIT, TypeScript.

MCP | TypeScript · mcp-server · hostinger

A Rust MCP server and SDK that exposes Obsidian and Markdown vaults to AI clients through tools for search, note editing, graph analysis, metadata queries, and vault health checks.

MCP | Rust · MCP server · Obsidian

Swift port of the Vercel AI SDK offering one provider-agnostic API for streaming text, structured outputs, tool calling, MCP tools, and middleware across 38 providers via SwiftPM. Built for iOS/macOS apps needing OpenAI, Anthropic, Google and others from Swift.

AI Frameworks | Swift · sdk · llm

MCP server that wraps existing LSP servers (gopls, rust-analyzer, pyright, tsserver) into agent-native workflows: 65 tools for batch analysis, speculative editing, and multi-step refactor skills across 30+ CI-verified languages, with token-compact GCF output.

MCP | Go · mcp-server · lsp

Self-hosted server operations panel with an SRE agent that inspects live logs, files, and metrics, then performs scoped actions. High-risk changes require approval; crash diagnosis supports reviewed patches and rollback.

AI Agents | TypeScript · SRE agent · server operations

Kokoro Engine is a cross-platform Tauri/Rust desktop runtime for AI virtual characters: Live2D rendering, LLM chat, TTS/STT, vision, MCP tool calls, and SQLite-backed long-term memory with hybrid vector+FTS retrieval. Extendable via a QuickJS MOD sandbox and SillyTavern card import.

AI Agents | Rust · live2d · virtual-character

Ever Works is a TypeScript monorepo agentic runtime: give it a prompt and configurable multi-step AI agent pipelines autonomously research, write, code and deploy sites or directories. Ships Web UI, NestJS API, CLI and MCP server with pluggable AI, search, Git and deployment providers.

AI Agents | TypeScript · agentic-runtime · autonomous-agents

A curated collection of articles, papers, tools, and best practices for context engineering in AI agents and LLM applications, including retrieval, memory, compression, MCP, and coding-agent workflows.

AI Agents | context engineering · LLMs

Cross-platform chat assistant that reads visible conversations, analyzes context, and drafts ranked replies in a floating window. Users review OCR and suggestions before copying or filling a draft; sending remains manual. Android currently cannot capture WeChat chats.

AI Tools | Python · chat assistant · reply drafting

Hayhooks deploys Haystack pipelines and agents as REST APIs, MCP tools, and A2A agents. It also supports OpenAI-compatible streaming endpoints, optional Chainlit and Open WebUI integrations, and OpenTelemetry tracing.

MCP | Python · MCP server · MCP tools

An MCP server for Bambu Lab printers that exposes printer controls, status, AMS inventory, camera snapshots, and print-job management. It also supports STL manipulation and slicing workflows using BambuStudio and other slicers.

MCP | TypeScript · 3D printing · Bambu Lab

Runner is a native Rust desktop app for running terminal coding agents (Claude Code, Codex, Copilot CLI, pi) together on one task. It adds roles, crews, live per-agent PTY terminals, a replayable mission feed, MCP/skill management, and a CLI for scripted control.

AI Agents | Rust · multi-agent · agent-orchestration

Local, deterministic CLI-output compressor that sits between your terminal and AI coding assistants, using 36 format-aware processors to cut tool output tokens by 60-99% while preserving errors, diffs and stack traces. Installs as a Claude Code / Antigravity plugin; no network calls or extra model inference.

AI Coding | Python · token-optimization · context-window

Electron/Svelte desktop app that monitors local AI agents (processes, files, network, behavior) and offers local security reviews plus opt-in policy-controlled execution and MCP action tools. Windows-first, monitor-only by default, no telemetry.

AI Agents | JavaScript · agent-monitoring · ai-security

Demo agent that navigates a Neo4j graph one hop at a time using TypeSafe's system_one structured-decision API: each hop returns a probability distribution over outgoing relationships, and top-k beam search (log-prob ranked) finds best paths. Includes reusable library, notebooks, and a Streamlit visualizer.

AI Agents | Jupyter Notebook · neo4j · knowledge-graph

TypeScript framework for building MCP servers, bundling typed tool/resource/prompt builders, auth, tenant storage, logging/tracing, linting, and a CLI scaffold. Ships Agent Skills and CLAUDE.md/AGENTS.md so coding agents can build, test, and publish servers.

MCP | TypeScript · mcp-server · framework

A configuration system for Claude Code, Codex, and other coding agents: architectural principles, Python enforcement hooks, installable skills, and rules for multi-agent orchestration, context handoff, and agent security. Drop-in kits for global or project-local install.

AI Coding | Python · claude-code · codex

Self-hosted AI-native document workspace for legal teams: agents, MCP tool orchestration, plugin/skill marketplace, embedded LibreOffice editing with tracked changes, OCR, RAG, and evidence-chain review. Java/Spring backend, Vue + Electron desktop, optional local models via Ollama.

AI Tools | Java · ai-workspace · legaltech

Rust browser engine built on embedded Servo that renders pages and extracts Markdown, schema-driven JSON, or PNG screenshots with no Chromium or API key. Ships as CLI, Rust/Python/Node libraries, HTTP API, built-in MCP server, and agent skill for feeding agents web content.

AI Tools | Rust · web-scraping · headless-browser

Production-grade C++ SDK implementing the Model Context Protocol for building MCP servers and clients. Supports stdio, HTTP+SSE, Streamable HTTP, WebSocket and TCP transports, with a C API for Python, TypeScript, Go, Rust, Java and C# bindings, plus TLS, rate limiting and observability.

MCP | C++ · cpp · sdk

WebReaper is a self-hosted .NET scraper with a CLI and library for crawling sites, producing Markdown, and extracting structured data with optional LLM support. It also provides MCP servers and a Claude Code skill for agent-driven scraping.

AI Tools | C# · web scraping · web crawling

A local-first mobile agent app for iOS and Android that connects to services such as DeepSeek, Claude, Codex, and GLM. On iOS, agents can work with files and Git in a bounded workspace, with tool approvals and change review; Android agent tools are not yet available.

AI Agents | Objective-C++ · mobile agent · local-first

MCP server exposing NCBI E-utilities, PMC, and Europe PMC as 11 tools plus a resource and prompt: literature search, article metadata, full-text retrieval with Unpaywall fallback, citation formatting, MeSH lookup, and ID conversion. Runs over STDIO, Streamable HTTP, or a hosted endpoint.

MCP | TypeScript · mcp-server · pubmed

A DSH (DeepSeek Harness) web plugin that adds sidebar panels and a dsh-panel CLI to manage MCP servers (stdio/HTTP) in cordis.patch.yml and manage agent skills (add, scope, group, enable/disable) on disk. Changes hot-reload via DSH file watchers and HMR.

MCP | JavaScript · skills · dsh-plugin

A weekly updated, categorized ranking of 400 MCP servers. Browse projects by use case and compare quality scores based on metrics collected from GitHub and package managers.

MCP | MCP servers · curated list

Umbrella collection of ~24 Agent Skills plus a Bash safety hook that work across Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and Antigravity. Covers MCP/settings/hooks management, prompt engineering, bug-fix and planning protocols, research tooling, and destructive-command guarding.

Skills | Python · agent-skills · claude-code

MCP server exposing 20 tools over an index of 580K+ D365FO X++ symbols (classes, tables, forms, EDTs, labels, security). It grounds AI assistants like GitHub Copilot and Claude Code by proving every method, field, label and form pattern against your real metadata before code is written.

MCP | TypeScript · mcp-server · d365fo

FrontMCP is a TypeScript-first framework for building production MCP servers: decorator-based @Tool/@Resource/@App classes with DI, OAuth/JWKS auth, sessions, Streamable HTTP/SSE transport, plugins, OpenAPI adapters, React UI and a CLI. Same code ships to Node, Vercel, Lambda or Cloudflare Workers.

MCP | TypeScript · mcp-server · framework

A categorized directory of Model Context Protocol servers, clients, SDKs, and tools. Use it to discover MCP integrations across development, data, cloud, productivity, and other areas.

MCP | Python · Model Context Protocol · curated list

Self-hosted, agent-first AEO/GEO platform (CLI, MCP, API, web UI) that tracks brand mentions and citations across AI answer engines, crawls sites for technical SEO health, and runs competitor visibility analysis on SQLite with BYOK provider keys.

AI Tools | TypeScript · aeo · geo

MCP server that gives AI agents agentic RAG over one PDF or a whole folder: hybrid BM25 + semantic search, selective page reads, tables, images, chart data, OCR and CJK/multi-column reading order, with a persistent SQLite cache. Ships 13 tools plus STDIO and HTTP transports.

MCP | Python · mcp-server · agentic-rag