Hashgrid DNA (local)
Search that learns from feedback, over text and images: embeds locally, sends DNA only vectors.
Servidor MCP · de hashgrid.ai
Resumen
Hashgrid DNA (local) es un servidor MCP publicado por hashgrid.ai. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-19. Según nuestra pasada por los marketplaces del 2026-10-20.
Qué pide
- Se ejecuta en tu equipo
- Secretos: 3
- Ajustes: 5
Requiere: HASHGRID_API_KEY (secreta), OPENAI_API_KEY (secreta), VOYAGE_API_KEY (secreta)
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como servidor MCP local: paquete PyPI
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --env "HASHGRID_API_KEY=<YOUR_HASHGRID_API_KEY>" --env "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" --env "VOYAGE_API_KEY=<YOUR_VOYAGE_API_KEY>" --transport stdio sdk -- uvx --with "fastembed>=0.7" hashgrid mcp[mcp_servers.sdk]
command = "uvx"
args = ["--with", "fastembed>=0.7", "hashgrid", "mcp"]
[mcp_servers.sdk.env]
HASHGRID_API_KEY = "<YOUR_HASHGRID_API_KEY>"
OPENAI_API_KEY = "<YOUR_OPENAI_API_KEY>"
VOYAGE_API_KEY = "<YOUR_VOYAGE_API_KEY>"{
"mcpServers": {
"sdk": {
"command": "uvx",
"args": [
"--with",
"fastembed>=0.7",
"hashgrid",
"mcp"
],
"env": {
"HASHGRID_API_KEY": "<YOUR_HASHGRID_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"VOYAGE_API_KEY": "<YOUR_VOYAGE_API_KEY>"
}
}
}
}Sustituya los valores entre corchetes angulares por los suyos. Mostramos los nombres de los ajustes, nunca valores.
Ajustes opcionales que también indica: HASHGRID_EMBEDDER, HASHGRID_INDEX.
Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 1.1.0 | Forks (GitHub): 0 Estrellas (GitHub): 4 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Qué cambió
- Official MCP Registry: publicó la versión 1.1.0 (antes 1.0.0)
- Official MCP Registry: cambiaron las variables de entorno (ahora 5): cambió la marca de secreta u obligatoria en HASHGRID_API_KEY
- Pasó a ser un producto que seguimos
- Official MCP Registry: apareció
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
A search engine that learns from feedback, over embeddings: one tool per API route.
-
ls-search io.github.CalBearKen/ls-search
Disposable private vector search + semantic RAG for AI agents. x402 pay-per-call, no account.
-
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
-
Use OpenMayhem text, embedding and media models with explicit cost controls.
-
Build searchable AI research knowledge bases with hybrid vector search directly in Claude Desktop.
-
Connect to Hugging Face Hub and thousands of Gradio AI Applications
-
Semantic nearest-neighbour search over your datasets, plus indices and projections.
-
Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
-
Alibaba Cloud DashScope — Qwen
Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.
-
MCP server that exposes GraphQL operations as tools for AI models.
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
Peer network patterns for Claude Code agent specialization. Peers gives Claude instances structured identity, discovery, messaging, and handoff protocols so specialist reviewers…
-
together-ai-skills
A collection of skills that teach coding agents how to use the Together AI platform, including chat completions, image generation, video, audio, embeddings, fine-tuning, batch…
-
Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across…
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
Publicado en Claude Code: claude-plugins-official (5)
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across…
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
Publicado en Claude: knowledge-work-plugins (5)
-
Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across…
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
General life-sciences research workflows with query routing, evidence synthesis, and optional parallel subagent analysis across genetics, omics, biology, chemistry, structure…
-
Predict structures, screen molecules and proteins, and design binders.
Publicado en Community GitHub marketplaces (5)
-
Self-learning vector database — HNSW, FlashAttention-3, Graph RAG, hybrid search, DiskANN, and Brain AGI
-
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI…
-
Ollama REST API skill - run and manage local LLMs with chat, generate, embeddings, and custom model creation
-
Connect Codex to a self-hosted AI gateway with provider-free prompt enhancement and fifteen governed MCP tools.
-
Persistent knowledge graph and MCP server for AI workflows with git-tracked project context.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Publicado en Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Add Grok voice to an app: realtime speech-to-speech, speech-to-text dictation, text-to-speech read-aloud, and a log-driven fix loop for voice sessions.
-
Search company knowledge and draft verified answers.
Publicado en Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Production-ready RAG service to search and retrieve data from your documents.
-
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
Analyze documents, images, videos, and audio.
Publicado en Official MCP Registry (5)
-
A search engine that learns from feedback, over embeddings: one tool per API route.
-
ls-search io.github.CalBearKen/ls-search
Disposable private vector search + semantic RAG for AI agents. x402 pay-per-call, no account.
-
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
-
Use OpenMayhem text, embedding and media models with explicit cost controls.
-
Build searchable AI research knowledge bases with hybrid vector search directly in Claude Desktop.
Publicado en npm registry (MCP servers) (5)
-
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
-
easytable-mcp io.github.chrischall/easytable-mcp
easyTable restaurant reservations for Claude — availability, and create/modify/cancel bookings
-
One workspace for every AI coding assistant. Shared tasks, memory, and governance.
-
Browser-local and CLI static evidence for deployed AI model artifacts.
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Official MCP Registry. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.