"Finding the Top 10 Most Frequently Pulled Packages from Nexus Repository" matching MCP servers:

Enables Claude to orchestrate tasks across 27 AI providers, run multi-agent plans, and conduct multi-model councils for decision-making.

MCP server that provides a citation-first memory layer for AI agents, enabling verified search across Git-backed repositories and optional conversation memory. It exposes tools for doctor, sync, search, get, init, and ingest, returning JSON results with verified citations or abstain status.

Enables AI agents to search, read, and traverse a local knowledge base of Markdown files using full-text search and relationship graph, reducing token usage.

Enables natural-language analysis of GitHub repositories by exposing repository metadata, source code retrieval, search, and file reading as MCP tools, with answers grounded in the actual repository content.

Enables any MCP client to search, browse, download, and manage Nexus Mods content—games, mods, files, comments, collections, and user preferences—through a unified REST and GraphQL interface with caching and OAuth2 support.

NEXUS enhances AI coding agents with semantic code indexing, context engineering, change impact analysis, persistent memory, safe execution, and deterministic orchestration through 31 MCP tools.

Nexus Memory gives every MCP-compatible agent one persistent, self-hosted shared memory with hybrid retrieval, drift detection, and anti-poisoning features.

A self-hostable, multi-MCP personal-assistant framework with multi-provider LLM orchestration, a real safety model, and a production-grade test suite. Nexus Core is the engine behind a Telegram-based personal assistant: it takes a message (text or voice), routes it through an LLM, lets the model call tools exposed by a fleet of Model Context Protocol servers, gates anything destructive behind exp

Enables MCP-capable agents to read, file, slice, and map a shared Workflowy outline, giving them the same live context a human sees—including source code mapped from disk—without exports or copies.

MCP server that wraps the nexus CLI, giving AI agents cross-session memory, semantic search, preference learning, and smart context injection.

Acts as an MCP gateway aggregating multiple child MCP servers into a single namespaced interface, with an optional memory layer that caches tool results to reduce redundant calls.

Enables Claude Code to read and update tasks in the Nexus/TaskBridge project management system through its public API.

Enables coding agents to query a parsed graph of a repository and to recall what earlier sessions learned about it, both stored in FalkorDB behind one traversal. It exposes eight MCP tools over stdio for locating symbols, tracing calls and impact paths, and writing or recalling user- and repo-scoped facts, procedures, and handoffs.

A personal MCP bridge that lets ChatGPT drive a local Codex CLI, translating instructions into Codex app-server threads and returning compact summaries of what Codex did.

Provides intelligent codebase analysis, dependency scanning, architecture detection, security vulnerability scanning, and automatic documentation generation for modern development teams.

A fully working MCP server built from scratch in plain Node.js, implementing tools, resources, prompts, notifications, and sampling according to the MCP specification, designed to connect to Claude Desktop or any MCP client.

A local MCP server for Nexus Mods mod discovery, research, and downloading, backed by the v2 GraphQL API and the website's DownloadPopUp widget.

MCP server for the Plugin Federation Nexus control plane, enabling coding agents and humans to inspect catalogs, plugins, proposals, and run governance actions via GitHub SSO or OIDC.

Unified MCP server: hybrid search + code graph + semantic memory. 10 tools, <350MB RAM, fully local. No API keys.

Exposes the Nexus Mods API to AI agents so they can search and inspect mods, browse authors' catalogues, and upload or publish mod files from a local archive in a few aggregated tool calls. It handles authentication, caching, reporting quotas, and the multi-step v3 upload flow, while gating write and publish operations behind opt-in permissions.

A zero-dependency, file-based persistent memory system for AI agents with tiered memory, Ebbinghaus decay, and keyword retrieval.

Enables hybrid web search and intelligent content extraction, combining semantic search with documentation-optimized reading that strips noise and returns clean, token-efficient context for AI agents.

Enables AI harnesses to connect to a single MCP endpoint that routes to multiple downstream MCP servers, discovering and executing capabilities on demand while keeping tool schemas out of context.

Enables structured learning with a verified loop: define goals as observable claims, learn through teach-lab-test-gate per claim, and get independently graded by an adversarial examiner to ensure genuine progress.

Service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents via MCP. Versioned Markdown store, pub-sub notifications, and diff-aware update protocol.

Enables safe local MCP-based control of ArcMap Desktop 10.8, allowing read-only inspection of map documents, layers, datasets, and execution of allowlisted geoprocessing tools through ArcPy.

A fully local, open-source MCP server that replaces Azure AI Foundry, enabling model management, inference, evaluation, and RAG using Ollama without any cloud dependencies.

MCP server that lets AI models invoke CLI agents (Gemini, Codex, Claude, OpenCode) as tools — with parallel execution, retries, and structured output parsing.

A local digital asset hub for multi-AI assistant collaboration, offering real-time meeting rooms and structured project vaults with zero-configuration setup.

A local stdio MCP server with recording and tracking tools that lets Codex and Claude Code agents log chat activity, tasks, and delegations onto a loopback-only visual Kanban board with animated mascots. It enables observing work in progress while leaving conversation and execution in the originating client, without hosting models or running AI itself.