# Context Guardian (pypi · context-guardian)

Compacting proxy for OpenAI-compatible backends, with MCP tools to search the archived history.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- pypi · `context-guardian`: 66/100 (this document), [markdown](https://verifymcp.io/servers/luminarisoftwares-context-guardian/context-guardian.md), [page](https://verifymcp.io/servers/luminarisoftwares-context-guardian/context-guardian)

## Channel facts

- Registry: `pypi`
- Package: `context-guardian`
- Version: `0.10.0`
- 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 2026-10-17.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 0 of 19 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - 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 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 163 tokens (~54/item across 3 items; 3 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**: 80/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 40% 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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; 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 Context Guardian MCP server?

Context Guardian runs locally as a PyPI package, launched with uvx context-guardian. 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 luminarisoftwares-context-guardian -- uvx context-guardian
```

### Cursor

```json
{
  "mcpServers": {
    "luminarisoftwares-context-guardian": {
      "command": "uvx",
      "args": [
        "context-guardian"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "luminarisoftwares-context-guardian": {
      "command": "uvx",
      "args": [
        "context-guardian"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add luminarisoftwares-context-guardian -- uvx context-guardian
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "luminarisoftwares-context-guardian": {
      "type": "local",
      "command": [
        "uvx",
        "context-guardian"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add luminarisoftwares-context-guardian --command uvx --arg context-guardian
```

### Hermes

```yaml
mcp_servers:
  luminarisoftwares-context-guardian:
    command: "uvx"
    args: ["context-guardian"]
```

### Netclaw

```json
{
  "McpServers": {
    "luminarisoftwares-context-guardian": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "context-guardian"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add luminarisoftwares-context-guardian -t stdio -c uvx -a context-guardian
```

### Other

```json
{
  "mcpServers": {
    "luminarisoftwares-context-guardian": {
      "command": "uvx",
      "args": [
        "context-guardian"
      ]
    }
  }
}
```

## 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.

### 2026-10-15 (score 66)

First indexed and scored.

## MCP tools (3)

### `guardian_status` (~44 tokens)

Proxy status

Context Guardian's live status from the running proxy: window and budget, compactions, tokens saved, rejected summaries, calibration. Reads GUARDIAN_HOST:GUARDIAN_PORT.

### `search_spans` (~65 tokens)

Search archived spans

Case-insensitive search of the conversation text compaction archived. One line per hit: span file, message index and role, snippet.

Input parameters:

- `max` (integer)
- `run` (string): only this proxy run id
- `term` (string, required): text to find

### `read_span` (~54 tokens)

Read one archived span

The summary and original messages of one span, by run id and index (as search_spans prints them). Long spans are cut at 20000 characters.

Input parameters:

- `index` (integer, required)
- `run` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/luminarisoftwares-context-guardian/context-guardian#diagnostics

## Score history

- 2026-10-17: 66
- 2026-10-16: 66
- 2026-10-15: 66

## Common questions

### What is the Context Guardian MCP server?

Context Guardian is an MCP server listed in the public MCP registry as io.github.LuminariSoftwares/context-guardian. Compacting proxy for OpenAI-compatible backends, with MCP tools to search the archived history. This page covers its PyPI package (context-guardian).

### Is the Context Guardian MCP server safe to use?

Context Guardian scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. 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 Context Guardian MCP server expose?

Context Guardian exposes 3 tools: guardian_status, search_spans, read_span. Their descriptions and schemas cost roughly 163 tokens of context every time the server is loaded.

### Is the Context Guardian MCP server still maintained?

Context Guardian is still listed as active in the MCP registry. We last reached this channel on 17 October 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 Context Guardian MCP server under?

Context Guardian 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

- PyPI project: https://pypi.org/project/context-guardian/
- Socket report: https://socket.dev/pypi/package/context-guardian
- Repository: https://github.com/LuminariSoftwares/context-guardian
- Changelog RSS feed: https://verifymcp.io/servers/luminarisoftwares-context-guardian/context-guardian.xml
- Changelog JSON feed: https://verifymcp.io/servers/luminarisoftwares-context-guardian/context-guardian.json
- HTML version of this page: https://verifymcp.io/servers/luminarisoftwares-context-guardian/context-guardian