# keygrant (pypi · keygrant)

Run commands with API keys injected per call — values never enter model context.

- Trust score: 56/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- pypi · `keygrant`: 56/100 (this document), [markdown](https://verifymcp.io/servers/bazingaedward-keygrant/keygrant.md), [page](https://verifymcp.io/servers/bazingaedward-keygrant/keygrant)

## Channel facts

- Registry: `pypi`
- Package: `keygrant`
- Version: `0.1.9`
- 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 2026-10-18.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - 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.
  - No production dependencies, so there is no dependency health to assess.
- **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 (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 84/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 217 tokens (~108/item across 2 items; 2 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 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.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "exec_with_secrets" implies "exec" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 2 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.

## Install

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

keygrant runs locally as a PyPI package, launched with uvx keygrant. 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 bazingaedward-keygrant -- uvx keygrant
```

### Cursor

```json
{
  "mcpServers": {
    "bazingaedward-keygrant": {
      "command": "uvx",
      "args": [
        "keygrant"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "bazingaedward-keygrant": {
      "command": "uvx",
      "args": [
        "keygrant"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add bazingaedward-keygrant -- uvx keygrant
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add bazingaedward-keygrant --command uvx --arg keygrant
```

### Hermes

```yaml
mcp_servers:
  bazingaedward-keygrant:
    command: "uvx"
    args: ["keygrant"]
```

### Netclaw

```json
{
  "McpServers": {
    "bazingaedward-keygrant": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "keygrant"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add bazingaedward-keygrant -t stdio -c uvx -a keygrant
```

### Other

```json
{
  "mcpServers": {
    "bazingaedward-keygrant": {
      "command": "uvx",
      "args": [
        "keygrant"
      ]
    }
  }
}
```

## 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.

### 2026-10-18 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 55, +1)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.10
- [functional] Package version: 0.1.6 → 0.1.9

### 2026-10-14 (score 54, +15)

- [security regression] Malware scan: pass → unverified
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: 0
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100

### 2026-10-12 (score 39)

First indexed and scored.

## MCP tools (2)

### `list_secrets` (~43 tokens)

List the names and descriptions of secrets available in the local vault. Values are never returned. Use exec_with_secrets to run a command that needs one of these secrets.

### `exec_with_secrets` (~174 tokens)

Run a shell command with the named secrets injected as environment variables (reference them as %NAME% / $env:NAME / $NAME inside the command). The user must approve access via a native dialog that shows the full command; approval covers that exact command string for 15 minutes, so reuse the identical command for retries. Commands over 2000 characters are refused: put long logic in a script. A denial is final — never retry it. Output is returned with any plaintext secret values redacted. This is the ONLY way to use a secret; values never appear in conversation context.

Input parameters:

- `command` (string, required): Shell command to run (executed via cmd /c on Windows).
- `cwd` (string): Optional working directory.
- `secrets` (array, required): Names of vault secrets to inject as env vars.

## Diagnostics

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

## Score history

- 2026-10-18: 56
- 2026-10-17: 55
- 2026-10-16: 54
- 2026-10-15: 54
- 2026-10-14: 54
- 2026-10-13: 39
- 2026-10-12: 39

## Common questions

### What is the keygrant MCP server?

keygrant is an MCP server listed in the public MCP registry as io.github.bazingaedward/keygrant. Run commands with API keys injected per call, values never enter model context. This page covers its PyPI package (keygrant).

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

keygrant scores 56 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 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 keygrant MCP server expose?

keygrant exposes 2 tools: list_secrets, exec_with_secrets. Their descriptions and schemas cost roughly 217 tokens of context every time the server is loaded.

### Is the keygrant MCP server still maintained?

keygrant is still listed as active in the MCP registry. We last reached this channel on 18 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 keygrant MCP server under?

keygrant declares the Apache-2.0 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/keygrant/
- Socket report: https://socket.dev/pypi/package/keygrant
- Repository: https://github.com/bazingaedward/keygrant
- Website: https://keygrant.app/
- Changelog RSS feed: https://verifymcp.io/servers/bazingaedward-keygrant/keygrant.xml
- Changelog JSON feed: https://verifymcp.io/servers/bazingaedward-keygrant/keygrant.json
- HTML version of this page: https://verifymcp.io/servers/bazingaedward-keygrant/keygrant