"Conda-Forge" matching MCP servers:

Context Forge is a vendor-neutral continuity layer for AI tools. It stores project context in Markdown and JSON, retrieves task-scoped context, and leaves structured handoffs so another model can continue without being taught the project again.

An advanced MCP server for Cline that leverages EverArt's AI models to generate vector and raster images, supporting flexible storage, multiple formats, and robust image generation capabilities.

Local RAG MCP server for searching meeting notes via the vault_search tool, returning pointers to relevant sections entirely on-device.

Provides hybrid vector+BM25+reranker search and index-refresh tools over agent memory stored in markdown files, enabling forge agents to query memory across session, working, and docs tiers without direct file access.

Enables autonomous agents to perform CAD geometry calculations and retrieve Autodesk API knowledge via MCP, combining a native C++ geometry engine with RAG grounded on Fusion 360, APS/Forge, Revit, and Inventor.

Ingest, query, and generate study materials from documents (PDF, DOCX, Markdown, images, web pages) using vector search, knowledge graph, and study tools through OpenCode chat.

A production-ready MCP server for persistent AI memory across LLMs like Claude and ChatGPT. Provides automatic conversation backup, multi-user support, and multi-storage (PostgreSQL, Redis, Qdrant).

Gives AI agents a shared, cited memory of team knowledge built from docs, tickets, chat and confirmed decisions, exposing search, memory retrieval and source lookup over MCP. Agents can recall relevant conventions and evidence, and save new memories after user confirmation, across Claude Code and Codex sessions.

A feature-rich gateway and proxy that federates MCP, REST, and gRPC services into a unified endpoint for AI clients. It enables virtualization of legacy APIs as MCP-compliant tools while providing built-in security, rate-limiting, and OpenTelemetry observability.