"Information on agent swarm architecture" matching MCP servers:

An MCP server that enables AI agents to compile, refine, and interlink knowledge into a persistent wiki, replacing RAG with structured, curated knowledge.

MCP server enabling AI agents to directly query and manage Power BI datasets, reports, and workspaces via DAX, with built-in data security policies and support for both Power BI Desktop and Service.

A real MCP server exposing data-analyst tools (SQL querying, schema introspection, stats, charting) over a sales database, with a Gemini agent that discovers and calls those tools at runtime via the standard MCP protocol.

Enables conversational patent data analysis through a set of tools for trend analysis, clustering, word cloud generation, and more. Allows natural language queries to explore patent datasets with structured results and visualizations.

Enables AI agents to read and manipulate networks, tables, visual styles, and more in a live Cytoscape Web session through natural language, by connecting over Chrome DevTools Protocol.

Turns structured JSON content into resolved, audited infographic plans and renders them as SVG or executable Figma Plugin API scripts, exposing theme packs, grammars, planning, auditing and export tools over stdio. Also lets hosts inspect theme provenance and layout decisions so different tools produce identical frames.

Generates editable Excalidraw diagram files from natural language descriptions of systems and architectures.

A clean-room SHARP-on-MCP compliant FHIR R4 MCP server that enables AI agents to interact with any FHIR R4 endpoint using SHARP context headers, without server-side OAuth. It provides clinical tools, lab results, imaging, and interactive MCP-UI dashboards.

Enables AI agents and LLM platforms to create and manage live 3D isometric sessions, upsert agents, update progress and status, trigger speech bubbles, and remove agents through stateful MCP tools over STDIO or HTTP.

Enables AI agents to securely connect to your own Power BI or Fabric tenant using your Azure identity, with tools to inspect workspaces and models, run read-only DAX, validate and deploy your own reports, take page screenshots, and enforce guardrails that protect shared resources.

Enables AI agents to log trades from chart screenshots, validate them against custom strategy rules, import statements from MT5/TradingView and other brokers, and review R-based statistics in a local dashboard.

Generates hand-drawn Excalidraw diagrams from natural language prompts or structured descriptions, with tools for creating, listing, and opening diagrams directly in the browser.

Enables natural-language querying of F&S idea data in Joule Work Desktop, supporting idea search, detail retrieval, and dashboard KPIs.

Enables natural language sales analysis by connecting to a SQLite database, generating charts, and exporting results to CSV/Excel.

MCP server providing construction job costing data and interactive visualizations for a fictitious general contractor, enabling queries on projects, budgets, cost codes, change orders, and cash flow.

An MCP server that answers natural-language questions over CSV, Excel, and SQL data by providing deterministic tools for loading, profiling, querying, cleaning, statistical analysis, visualization, and reporting. It enables LLMs to plan and interpret while all computation is done exactly through MCP tools.

Enables an AI agent to build, solve, sweep and verify FEMM 5 finite element models across magnetics, electrostatics, heat flow and current flow, backed by physics health checks and closed-form estimates. It exposes 88 tools in 12 groups covering geometry, materials, meshing, post-processing and experiments, plus a catalog of 677 FEMM scripting commands.

Enables evidence-backed business decisions by connecting questions to experiment and metric data, applying statistical analyses, and producing rollout, hold, or investigate verdicts with reproducible audit traces.

Enables AI assistants and editors to profile, clean, and analyze messy CSV/Excel files directly through MCP tools such as profile_dataset, clean_dataset, and list_sheets.

Provides live earthquake data from the USGS feed, enabling users to query recent seismic activity and view interactive earthquake widgets within the chat.

Provides local, deterministic Four Pillars (Bazi) chart calculation via MCP tools, with JSON and PNG outputs, no API key or network required.

Enables plain-English analysis of game telemetry through tools for schema inspection, SQL queries, metric/KPI retrieval, anomaly sweeps, and synthetic data loading.

Provides tools to inspect dataset schema, profile, preview, and execute read-only SQL queries on uploaded CSV/Excel files.

Enables natural-language Q&A, human-approved actions, and dashboard generation over a data ontology via MCP.

Enables AI agents to query and manage ERP procurement data, including suppliers, parts, inventory, and purchase orders, with human approval for write operations.

Enables agents to read and resolve layered feedback, propose and make decisions with evidence, and access trial ledgers and judgment views for experiment-driven work.

MCP server for generating and editing PowerPoint-native framework diagrams from paper descriptions. Supports spec-based generation, incremental edits, snapshot rollback, and structure validation while preserving manual modifications.

This MCP server scrapes Amazon product details and reviews, manages a local JSON database, and visualizes intelligence data through a rich dashboard.

Provides 19 tools for discovery, data analysis, configuration, and simulation, enabling an agent to drive digital twin workflows with session persistence and knowledge graph capabilities.

Open-source mind maps and whiteboard your agent draws on live: 22 tools for mind maps, notes, shapes, tables, charts, connectors, comments and HTML/PDF export; boards are local files.