MCP.so
登录

Deepmiro

@kakarot-dev

代码仓库

关于 Deepmiro

Simulate hundreds of AI agents to predict how communities react to events and policies. Upload any document (PDF, Markdown, text) and DeepMiro spawns a diverse swarm of AI agents that debate, share, and form opinions — then delivers a calibrated prediction report. Free and open-s

#mirofish#deep-research#research#predicting

基本信息

分类

其他

传输方式

stdio

发布者

kakarot-dev

提交者

Axel

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "deepmiro": {
      "command": "npx",
      "args": [
        "-y",
        "deepmiro-mcp"
      ],
      "env": {
        "DEEPMIRO_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

工具

9

Run a swarm prediction — graph build, persona generation, multi-agent simulation, report. IMPORTANT: Enrich the prompt before calling. The engine extracts named entities to create personas. Add specific people, companies, organizations, and opposing viewpoints. Show the enriched prompt to the user for confirmation first. If the user provides a document (PDF, MD, TXT), call upload_document first and pass the returned document_id. Returns immediately with simulation_id. Call simulation_status to wait for completion — each call blocks up to 50s for the next state change, so you only need a few. When status returns state=COMPLETED, the full report is included inline.

Check the progress of a running or completed simulation. Long-polls by default — blocks up to 50s waiting for a state change (phase transition, new round, new actions, completion). When state=COMPLETED, includes the full prediction report inline. Lifecycle: CREATED → GRAPH_BUILDING → GENERATING_PROFILES → READY → SIMULATING → COMPLETED/FAILED/CANCELLED/INTERRUPTED.

Generate and retrieve the prediction report for a completed simulation. If the report hasn't been generated yet, triggers generation (may take 1-3 minutes). Returns a detailed markdown analysis ready to display as an artifact in the side panel. Pass force_regenerate=true to rebuild an already-cached report.

Chat with a specific simulated agent to understand their perspective, reasoning, and predicted behavior. The agent responds in character based on their persona and simulation experience.

List past simulation runs with their status and metadata.

Search past simulations by topic, project name, or simulation ID.

Upload a document for use in simulations. LIMITS: Max 10MB, PDF/MD/TXT only. The server extracts text server-side (PyMuPDF for PDFs). Returns a document_id to pass to create_simulation. NOTE: Only works with local file paths (stdio transport). For remote/hosted mode, the client skill uploads via HTTP instead.

Access simulation data: agent profiles, configuration, action logs, social media posts, round-by-round timeline, per-agent activity stats, and interview history. Paginated — use offset to get more results when has_more is true.

Stop a running simulation. SIGTERMs the subprocess immediately and marks the simulation as stopped. Partial action log is preserved — you can still call get_report or simulation_data on a cancelled simulation for whatever data was produced before cancellation. Use this when a simulation is taking too long, was started by mistake, or is producing bad output you want to abort.

概览

What is DeepMiro?

DeepMiro simulates hundreds of AI agents to predict how communities react to events and policies. Users upload any PDF, Markdown, or text document, and DeepMiro spawns a diverse swarm of agents that debate, share, and form opinions, then delivers a calibrated prediction report.

How to use DeepMiro?

DeepMiro can be self-hosted via Docker Compose or used through the hosted option at deepmiro.org. After installation or sign‑up, use the provided tools (e.g., create_simulation, simulation_status, get_report, interview_agent) to start predictions, monitor progress, fetch reports, or chat with individual agents.

Key features of DeepMiro

  • Open‑source under AGPL-3.0 license.
  • Self‑hosted via Docker Compose.
  • Hosted option available at deepmiro.org.
  • Fully offline with Ollama support.
  • Supports upload of PDF, Markdown, and text files.
  • Allows interviewing any simulated agent post‑simulation.

Use cases of DeepMiro

  • Predict how a community will react to a new policy.
  • Simulate public opinion on a proposed event or change.
  • Analyze the impact of a document by generating a diversity of viewpoints.
  • Get a rapid, lightweight prediction without waiting for a full simulation.
  • Review and compare past simulation results by topic.

FAQ from DeepMiro

How can I run DeepMiro locally?

DeepMiro can be self-hosted using Docker Compose. It also supports Ollama for fully offline operation.

Is there a hosted version available?

Yes, a hosted option is provided at deepmiro.org.

What file formats are supported for input?

DeepMiro supports PDF, Markdown, and plain text files.

What license does DeepMiro use?

DeepMiro is released under the AGPL-3.0 open‑source license.

Can I chat with individual agents after a simulation?

Yes, the interview_agent tool allows you to talk to any simulated agent post‑simulation.

评论

其他 分类下的更多 MCP 服务器

Inbox Zero AI

elie222

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

11.6K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Servers

modelcontextprotocol

Model Context Protocol Servers

88.2K

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K