"A server for orchestrating intelligent agents to solve spatial reasoning tasks in 3D environments" matching MCP servers:

MCP server that silently monitors state changes in structured data sources (e.g., government open data) and provides a pull-based channel for AI agents to retrieve real mutations since their last cursor.

An MCP server that gives AI agents genuine 3D spatial understanding of Autodesk Fusion 360, enabling exact measurements, collision analysis, and free-space placement search, plus Fusion-native parametric authoring for clean, human-editable models.

This MCP server wraps the SOLVE-IT digital forensics knowledge base, enabling LLMs to query techniques, weaknesses, mitigations, and their relationships through a set of MCP tools.

Enables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.

An Iceberg-native geospatial MCP server powered by DuckDB that provides tools for spatial SQL queries, catalog discovery, and data management. It enables LLM agents to interact with Apache Iceberg lakehouses to perform complex spatial analysis, joins, and aggregations.

Adds a deep_reasoning tool that consults stronger reasoning models (e.g., DeepSeek R1) to produce full reasoning traces for complex problems, helping the agent shape and cross-check its answers.

A universal Model Context Protocol implementation that serves as a semantic layer between LLMs and 3D creative software, providing a standardized interface for interacting with various Digital Content Creation tools through a unified API.

Enables coding agents to visually inspect and diagnose 3D files (meshes and Gaussian splats) for defects like flipped normals or floaters, without GPU dependencies.

An MCP server that brings difficulty-adaptive, multi-path reasoning to Claude Code. It implements the Actor-Critic-Planner-Reflexion (ACPR) pipeline for deep research synthesis.

A persistent semantic memory system for LLMs with time-based decay, automatic memory capture, and spatial navigation tools for exploring knowledge graphs.

A small Model Context Protocol server that exposes a personal task tracker to any MCP-compatible client. Tasks live in a local SQLite database; no cloud, no surprises.

A 66-tool reasoning pipeline that intercepts prompts to classify intent, check past mistakes, and generate execution plans, enabling any LLM to think harder and avoid repeating errors.

Enables task management through natural language commands in English or Spanish. Supports creating, listing, updating, completing, and deleting tasks with local SQLite storage.

An MCP server that exposes 218 Blender tools for full 3D modeling pipelines, with a LangGraph agent layer for planning, executing, observing, and reviewing modeling tasks with evidence-based verification.

MCP server for generating print-ready 3D models from text descriptions via a multi-agent pipeline, enabling AI assistants to create and optimize STL files.

Enables AI assistants to manage Notion tasks, projects, and courses through MCP, allowing creation, retrieval, and filtering of tasks.

Provides AI agents with deterministic symbolic math capabilities through 21 tools for algebra, calculus, transforms, and DSP, preventing hallucinations by delegating computations to a SymPy engine.

A local Model Context Protocol server that turns one or more reference images into 3D GLB assets, with pluggable backends for Hunyuan3D-2mv, Stable Fast 3D, and SPAR3D.

MCP server that connects AI agents to KOMPAS-3D CAD, enabling automated 3D document operations through deterministic COM/API7 calls.

MCP server for deep algorithmic and mathematical reasoning, wrapping any OpenAI-compatible LLM endpoint to return only the final distilled answer without reasoning traces. Supports per-call model and endpoint overrides, defaulting to vibethinker-3b via LM Studio.