nimbus-mcp
OfficialRelated Servers
Alternatives to nimbus-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that gives AI agents a unified interface to clinical/research EEG workflows: signal processing, source imaging, persistent dataset/EHR storage, and web visualization.50 PyPI1BSD 3-Clause
- AlicenseBqualityBmaintenanceAn MCP server that gives AI assistants conversational access to MNE-Python for analyzing neurophysiology data (EEG, MEG, sEEG, ECoG, fNIRS). Enables plain-language analysis pipelines, from loading recordings to generating figures and explanations.4166 PyPI13MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to read real-time focus state from any BrainFlow-supported EEG headset.1MIT
- FlicenseAqualityCmaintenanceEnables Claude to inspect, configure, run, and modify individual RAG/agent pipeline stages (retrieve, rerank, generate, eval) as structured typed tool calls, and execute the full pipeline end to end.5-

deepset-mcpofficial
AlicenseBqualityBmaintenanceEnables AI agents to build and debug pipelines on the Haystack Enterprise AI platform through 30+ specialized tools, and provides a Python SDK for programmatic access.1104Apache 2.0- AlicenseAqualityCmaintenanceA Model Context Protocol server that provides AI agents with a unified interface for real-time EEG acquisition, replay, processing, visualization, recording, and stimulation from over 66 BrainFlow boards.473BSD 3-Clause
TDQS
Scored across 32 tools
Most tools target distinct actions/resources, but a few pairs overlap: stream_status vs get_live_session both poll a live session, and inspect_dataset vs inspect_file give near-identical exploratory summaries for different sources. Descriptions help disambiguate, but an agent may still hesitate between them.
Names are predominantly consistent snake_case verb_noun (list_nodes, get_template, run_pipeline). Minor deviations like whoami and stream_status break the exact verb_noun pattern but remain readable and conventional.
32 tools is heavy for a single MCP server; several subdomains (streaming, pipelines, datasets, projects, artifacts) could be consolidated. While each tool has a purpose, the set exceeds the 25-tool threshold where navigation becomes cumbersome.
The surface covers major workflows: device streaming, pipeline building/validation/execution, experiments, datasets, projects, and artifacts. Minor gaps exist (no delete/update for projects, pipelines, or artifacts), but agents can work around them.