# AsterMind MCP (npm · @astermind/astermind-mcp)

On-device reranking that cuts RAG context tokens ~67% while keeping a relevant passage.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-26

## Components

- npm · `@astermind/astermind-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/astermindai-astermind-mcp/astermind-astermind-mcp.md), [page](https://verifymcp.io/servers/astermindai-astermind-mcp/astermind-astermind-mcp)

## Channel facts

- Registry: `npm`
- Package: `@astermind/astermind-mcp`
- Version: `0.1.0`
- 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 2026-09-26.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 97 dependencies flagged as unhealthy.
- **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 (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 728 tokens (~72/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 77/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 32% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the AsterMind MCP server?

AsterMind MCP runs locally as an npm package, launched with npx -y @astermind/astermind-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add astermindai-astermind-mcp -- npx -y @astermind/astermind-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "astermindai-astermind-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@astermind/astermind-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "astermindai-astermind-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@astermind/astermind-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add astermindai-astermind-mcp -- npx -y @astermind/astermind-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add astermindai-astermind-mcp --command npx --arg -y --arg @astermind/astermind-mcp
```

### Hermes

```yaml
mcp_servers:
  astermindai-astermind-mcp:
    command: "npx"
    args: ["-y", "@astermind/astermind-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "astermindai-astermind-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@astermind/astermind-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add astermindai-astermind-mcp -t stdio -c npx -a -y @astermind/astermind-mcp
```

### Other

```json
{
  "mcpServers": {
    "astermindai-astermind-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@astermind/astermind-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.

### 2026-09-25 (score 65)

First indexed and scored.

## MCP tools (10)

### `rerank_documents` (~107 tokens)

Rerank documents by relevance

Rank candidate documents/chunks by relevance to a query using an on-device ELM reranker. Best when the query shares vocabulary with the documents (typical RAG). Lexical (TF-IDF) based: strong on keyword overlap, weaker on pure-synonym matches.

Input parameters:

- `documents` (array, required): Candidate documents/chunks to rank.
- `query` (string, required): The user query or question.
- `topK` (integer): Return only the top K (default: all).

### `filter_context` (~105 tokens)

Filter context to relevant docs (token saver)

Drop documents not relevant to the query so you feed the LLM a small, relevant context instead of everything. Reports exact tokens saved using an OpenAI-compatible tokenizer. This is the core token-reduction tool.

Input parameters:

- `documents` (array, required)
- `maxDocs` (integer): Max docs to keep (default 5).
- `minRelevance` (number): Min relevance 0..1 to keep a doc (default 0.5).
- `query` (string, required)

### `compress_context` (~73 tokens)

Compress context into a ready-to-paste block

One-shot token saver: filter candidate documents to what is relevant and return a compact, numbered context block ready to paste into a prompt, plus token-before/after accounting.

Input parameters:

- `documents` (array, required)
- `maxDocs` (integer)
- `minRelevance` (number)
- `query` (string, required)

### `classify_text` (~99 tokens)

Classify text (train-from-examples)

Classify text into your categories using an on-device ELM trained on the labeled examples you provide. Requires at least one example per category. Returns a confidence and honestly flags low-confidence results. Use this to route/label locally instead of paying an LLM to classify.

Input parameters:

- `categories` (array, required): The category labels.
- `examples` (array, required): Labeled training examples (>= 1 per category).
- `text` (string, required): Text to classify.

### `detect_language` (~50 tokens)

Detect language

Coarse language detection over 6 European languages (English, Spanish, French, German, Italian, Portuguese) using an on-device classifier. Runs locally with no API call.

Input parameters:

- `text` (string, required)

### `semantic_search` (~67 tokens)

Search a document set

Return the top documents matching a query from a provided set, scored by an on-device lexical (TF-IDF) reranker. Strong on keyword overlap; not a transformer embedding search.

Input parameters:

- `documents` (array, required)
- `query` (string, required)
- `topK` (integer)

### `generate_embeddings` (~51 tokens)

Generate on-device embeddings

Produce deterministic local char-level embeddings for a list of texts. Good for clustering, dedupe, and near-duplicate detection. Not a substitute for large transformer embeddings on nuanced semantics.

Input parameters:

- `texts` (array, required)

### `compare_texts` (~58 tokens)

Compare two texts (near-duplicate similarity)

Cosine similarity (0..1) between two texts using local embeddings. Best for detecting near-duplicates / paraphrase overlap, not fine-grained semantic ranking.

Input parameters:

- `text1` (string, required)
- `text2` (string, required)

### `count_tokens` (~47 tokens)

Count tokens

Count tokens in a string or array of strings using an OpenAI-compatible BPE tokenizer (o200k/cl100k family). Useful for measuring context size and budgeting.

Input parameters:

- `text` (required)

### `estimate_savings` (~71 tokens)

Estimate token & cost savings

Given the full context vs the filtered context you plan to send an LLM, compute tokens removed, percent saved, and (optionally) dollars saved per call for a given model input price.

Input parameters:

- `filteredContext` (required)
- `fullContext` (required)
- `usdPerMillionInputTokens` (number)

## Diagnostics

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

## Score history

- 2026-09-26: 65
- 2026-09-25: 65

## Common questions

### What is the AsterMind MCP server?

AsterMind MCP is listed in the public MCP registry as io.github.AsterMindAI/astermind-mcp. On-device reranking that cuts RAG context tokens ~67% while keeping a relevant passage. This page covers its npm package (@astermind/astermind-mcp).

### Is the AsterMind MCP server safe to use?

AsterMind MCP scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 26 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AsterMind MCP server expose?

AsterMind MCP exposes 10 tools: rerank_documents, filter_context, compress_context, classify_text, detect_language, and 5 more. Their descriptions and schemas cost roughly 728 tokens of context every time the server is loaded.

### Is the AsterMind MCP server still maintained?

AsterMind MCP is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the AsterMind MCP server under?

AsterMind MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@astermind/astermind-mcp
- Socket report: https://socket.dev/npm/package/@astermind/astermind-mcp
- Repository: https://github.com/AsterMindAI/astermind-mcp
- Website: https://astermindai.com/
- Changelog RSS feed: https://verifymcp.io/servers/astermindai-astermind-mcp/astermind-astermind-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/astermindai-astermind-mcp/astermind-astermind-mcp.json
- HTML version of this page: https://verifymcp.io/servers/astermindai-astermind-mcp/astermind-astermind-mcp