# io.github.kakarot-dev/deepmiro (npm · deepmiro-mcp)

Simulate hundreds of AI agents to predict how communities react to events and policies

- Trust score: 71/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `deepmiro-mcp`: 71/100 (this document), [markdown](https://verifymcp.io/servers/kakarot-dev-deepmiro/deepmiro-mcp.md), [page](https://verifymcp.io/servers/kakarot-dev-deepmiro/deepmiro-mcp)

## Channel facts

- Registry: `npm`
- Package: `deepmiro-mcp`
- Version: `0.1.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (108 of 109), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (108 of 109), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (AGPL-3.0-only).
  - Actively maintained (last published 106 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 917 tokens (~91/item across 10 items; 9 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add kakarot-dev-deepmiro -- npx -y deepmiro-mcp
```

### Codex

```bash
codex mcp add kakarot-dev-deepmiro -- npx -y deepmiro-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "kakarot-dev-deepmiro": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "deepmiro-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add kakarot-dev-deepmiro --command npx --arg -y --arg deepmiro-mcp
```

### Hermes

```yaml
mcp_servers:
  kakarot-dev-deepmiro:
    command: "npx"
    args: ["-y", "deepmiro-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "kakarot-dev-deepmiro": {
      "command": "npx",
      "args": [
        "-y",
        "deepmiro-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 71, +4)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 67, +41)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: AGPL-3.0-only

### 2026-07-31 (score 26, −9)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 35, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 53)

First indexed and scored.

## MCP tools (9)

### `create_simulation` (~171 tokens)

Create Simulation

Run a full swarm prediction. Builds a knowledge graph, generates agent personas, runs a multi-agent social media simulation, and generates a prediction report. Streams progress updates. Returns the final report when complete.

Input parameters:

- `agent_count` (integer): Override agent count
- `document_id` (string): ID of a pre-uploaded document (from upload_document tool). Skips file upload and uses server-side sanitized text.
- `platform` (string): Target platform(s). Default: both
- `preset` (string): Simulation preset: quick (10 agents, 20 rounds), standard (20/40), deep (50/72)
- `prompt` (string, required): Scenario description. E.g. 'How will crypto twitter react to a new ETH ETF rejection?'
- `rounds` (integer): Override simulation rounds

### `simulation_status` (~75 tokens)

Simulation Status

Check the progress of a running or completed simulation. Returns phase-aware status with entity names and action content. Phases: building_graph → generating_profiles → simulating → completed.

Input parameters:

- `detailed` (boolean): Include recent agent actions with content in the response
- `simulation_id` (string, required): The simulation ID returned by create_simulation

### `get_report` (~66 tokens)

Get Report

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 of the simulation results.

Input parameters:

- `simulation_id` (string, required): The simulation ID to generate/fetch a report for

### `interview_agent` (~97 tokens)

Interview Agent

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.

Input parameters:

- `agent_id` (integer, required): The agent's numeric ID within the simulation
- `message` (string, required): Question or prompt to send to the agent
- `platform` (string): Which platform persona to interview. Omit for both.
- `simulation_id` (string, required): The simulation ID

### `list_simulations` (~34 tokens)

List Simulations

List past simulation runs with their status and metadata.

Input parameters:

- `limit` (integer): Max results to return (default 20)

### `search_simulations` (~42 tokens)

Search Simulations

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

Input parameters:

- `query` (string, required): Search term — matches against simulation ID, project name, or requirement

### `quick_predict` (~74 tokens)

Quick Predict

Fast, lightweight prediction without running a full simulation. Uses the LLM to simulate swarm behavior and predict outcomes. Returns in seconds. For deeper analysis, use create_simulation instead.

Input parameters:

- `prompt` (string, required): Scenario to predict. E.g. 'How will the public react if Apple announces a $2000 iPhone?'

### `upload_document` (~118 tokens)

Upload Document

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.

Input parameters:

- `file_path` (string, required): Absolute path to the file to upload. Supported: PDF, MD, TXT. Max 10MB. Rejects binary files and unsupported formats.

### `simulation_data` (~219 tokens)

Simulation Data

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.

Input parameters:

- `action_type` (string): Filter actions by type (CREATE_POST, LIKE_POST, etc.)
- `agent_name` (string): Filter actions by agent name
- `data_type` (string, required): What data to retrieve: overview (condensed summary: entities, agents, graph, config, action stats — start here), profiles (full agent personas), config (simulation parameters), actions (agent action…
- `limit` (integer): Max results per page (default 50)
- `offset` (integer): Offset for pagination (default 0)
- `platform` (string): Filter by platform (for actions and posts)
- `simulation_id` (string, required): The simulation ID

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/kakarot-dev-deepmiro/deepmiro-mcp#diagnostics

## Score history

- 2026-08-03: 71
- 2026-08-02: 67
- 2026-08-01: 26
- 2026-07-31: 26
- 2026-07-30: 35
- 2026-07-28: 53
- 2026-07-27: 53

## Links

- npm package: https://www.npmjs.com/package/deepmiro-mcp
- Socket report: https://socket.dev/npm/package/deepmiro-mcp
- Repository: https://github.com/kakarot-dev/deepmiro
- Changelog RSS feed: https://verifymcp.io/servers/kakarot-dev-deepmiro/deepmiro-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/kakarot-dev-deepmiro/deepmiro-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/kakarot-dev-deepmiro/deepmiro-mcp