# Bouncer (pypi · bouncer-mcp)

Stdio MCP proxy that denies agent sends to destinations first seen in untrusted tool output.

- Trust score: 83/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `bouncer-mcp`: 83/100 (this document), [markdown](https://verifymcp.io/servers/ezed9-mcp-bouncer/bouncer-mcp.md), [page](https://verifymcp.io/servers/ezed9-mcp-bouncer/bouncer-mcp)

## Channel facts

- Registry: `pypi`
- Package: `bouncer-mcp`
- Version: `0.1.6`
- 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 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 30 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Ezed9/mcp-bouncer).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 9 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 322 tokens (~53/item across 6 items; 4 tools + 2 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**: 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**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (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 Bouncer MCP server?

Bouncer runs locally as a PyPI package, launched with uvx bouncer-mcp serve. 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 ezed9-mcp-bouncer -- uvx bouncer-mcp serve
```

### Cursor

```json
{
  "mcpServers": {
    "ezed9-mcp-bouncer": {
      "command": "uvx",
      "args": [
        "bouncer-mcp",
        "serve"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ezed9-mcp-bouncer": {
      "command": "uvx",
      "args": [
        "bouncer-mcp",
        "serve"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ezed9-mcp-bouncer -- uvx bouncer-mcp serve
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ezed9-mcp-bouncer": {
      "type": "local",
      "command": [
        "uvx",
        "bouncer-mcp",
        "serve"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ezed9-mcp-bouncer --command uvx --arg bouncer-mcp --arg serve
```

### Hermes

```yaml
mcp_servers:
  ezed9-mcp-bouncer:
    command: "uvx"
    args: ["bouncer-mcp", "serve"]
```

### Netclaw

```json
{
  "McpServers": {
    "ezed9-mcp-bouncer": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "bouncer-mcp",
        "serve"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ezed9-mcp-bouncer -t stdio -c uvx -a bouncer-mcp serve
```

### Other

```json
{
  "mcpServers": {
    "ezed9-mcp-bouncer": {
      "command": "uvx",
      "args": [
        "bouncer-mcp",
        "serve"
      ]
    }
  }
}
```

## 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.

### 2026-11-21 (score 83, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-20 (score 68, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-19 (score 83, +1)

- [functional improvement] Security disclosure: unverified → pass

### 2026-11-18 (score 82, +14)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: pass → unverified

### 2026-11-17 (score 68, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-13 (score 83, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-12 (score 68)

First indexed and scored.

## MCP tools (4)

### `bouncer_check_verdict` (~121 tokens)

Evaluate a hypothetical tool call against Bouncer's deterministic security contracts and return the verdict (ALLOW, DENY, or ASK) with the underlying reason, without executing the tool.

Input parameters:

- `args` (object): Arguments passed to the tool call.
- `tool` (string, required): Name of the tool being called (e.g. 'send_email', 'write_file').
- `untrusted_context` (array): List of untrusted strings currently in context (from prior tool outputs).
- `user_policy_yaml` (string): Optional YAML policy with custom contract overrides.

### `bouncer_verify_policy` (~46 tokens)

Validate a YAML policy string against Bouncer's schema and report syntax validity, contract rules count, and covered tools.

Input parameters:

- `policy_yaml` (string, required): YAML content defining tool policies.

### `bouncer_get_active_policies` (~62 tokens)

Inspect all active contract packs (builtin rules for filesystem, gmail, slack, github, gdrive) and user overrides loaded by Bouncer.

Input parameters:

- `pack_name` (string): Optional name of a specific pack to inspect (e.g. 'filesystem').

### `bouncer_audit_summary` (~53 tokens)

Retrieve recent audit log entries from Bouncer showing allowed, denied, and asked tool calls with their timestamps and reasons.

Input parameters:

- `limit` (integer): Maximum number of recent entries to return (default: 20).

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/ezed9-mcp-bouncer/bouncer-mcp#diagnostics

## Score history

- 2026-11-21: 83
- 2026-11-20: 68
- 2026-11-19: 83
- 2026-11-18: 82
- 2026-11-17: 68
- 2026-11-16: 83
- 2026-11-15: 83
- 2026-11-14: 83
- 2026-11-13: 83
- 2026-11-12: 68

## Common questions

### What is the Bouncer MCP server?

Bouncer is an MCP server listed in the public MCP registry as io.github.Ezed9/mcp-bouncer. Stdio MCP proxy that denies agent sends to destinations first seen in untrusted tool output. This page covers its PyPI package (bouncer-mcp).

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

Bouncer scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 Bouncer MCP server expose?

Bouncer exposes 4 tools: bouncer_check_verdict, bouncer_verify_policy, bouncer_get_active_policies, bouncer_audit_summary. Their descriptions and schemas cost roughly 282 tokens of context every time the server is loaded.

### Is the Bouncer MCP server still maintained?

Bouncer is still listed as active in the MCP registry. We last reached this channel on 21 November 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 Bouncer MCP server under?

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

### What did VerifyMCP test on the Bouncer MCP server?

VerifyMCP ran 15 checks on Bouncer, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Bouncer: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/bouncer-mcp/
- Socket report: https://socket.dev/pypi/package/bouncer-mcp
- Repository: https://github.com/Ezed9/mcp-bouncer
- Changelog RSS feed: https://verifymcp.io/servers/ezed9-mcp-bouncer/bouncer-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ezed9-mcp-bouncer/bouncer-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ezed9-mcp-bouncer/bouncer-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ezed9-mcp-bouncer/bouncer-mcp
