Bawbel Scanner

io.github.bawbelPublished by GitHub account bawbelv1.1.0Updated Oct 24, 2026

Scan MCP servers and skill files for AVE vulnerabilities. Conformance scoring and threat intel.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A local MCP server that lets an assistant scan MCP servers and skill files for AVE vulnerabilities, score spec conformance, and query threat intelligence.

What you can do
Scan raw text, skill files and remote server cards for AVE vulnerabilities, including credential exposure and unsafe delegation chains, with optional audit mode that shows suppressed findings too. Score a server manifest against the MCP spec with a grade and list of failed checks. Look up, search and list AVE threat intelligence records with severity scores and remediation guidance. Record justified suppressions with reason, reviewer and optional expiry, and detect rug pull drift across a directory of skill files. Read AVE database statistics and individual records as resources.
When to use it
Use it when vetting an MCP server or skill file before adding it to a configuration, when checking content for hardcoded secrets or prompt injection, or when you need AVE threat intelligence and remediation guidance during a security review.
Requirements
Runs locally over stdio, typically launched with uvx from the bawbel-mcp PyPI package. Needs Python 3.10+ and the bawbel CLI on PATH, which is installed automatically with the package. An optional extra installs all detection engines. Network access is needed to fetch remote server cards and query the threat intel API.
Before you install
Scanning a remote server card fetches content from a third-party URL, and threat intel lookups go to an external API. Accepting a finding writes a suppression comment directly into the scanned file, which changes that file and should be reviewed in version control. Audit mode bypasses all suppression layers and may surface findings previously marked as false positives.

Installation

In SourceWeft

  1. Open Bawbel Scanner in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Bawbel MCP Server

Security scanner for MCP servers and agentic AI components, exposed as MCP tools.

Bawbel MCP Server lets any MCP-compatible agent scan servers, check skill files, score conformance, manage justified suppressions, and query the AVE threat intelligence database mid-conversation.

[PyPI version] [PyPI - Python Version] [PyPI - Downloads] [License] [AVE Standard] [MCP Compatible] [Powered by]

Install

bash
pip install bawbel-mcp

Or with all detection engines (YARA, Semgrep, LLM, Magika, Sandbox):

bash
pip install "bawbel-mcp[all]"

Tools

ToolDescription
scan_contentScan raw text content for AVE vulnerabilities
scan_server_cardFetch and scan an MCP server-card before connecting
scan_credsCredential-focused scan (API keys, tokens, passwords, private keys)
scan_chainDelegation chain scan (unsafe sub-agent spawning and inherited permissions)
check_conformanceScore a server manifest against the MCP spec (18 checks, A+ to F)
accept_findingInsert a justified suppression with reason, reviewer, and optional expiry
lookup_aveGet a full AVE record by ID with remediation guidance
search_aveSearch AVE records by keyword
list_aveList all AVE records with optional severity/category filters
check_pinsDetect rug pull drift in a directory of skill files

Resources

ResourceDescription
ave://statsCurrent AVE database statistics
ave://record/{ave_id}Full AVE record for a specific ID

Usage

Claude Desktop

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "bawbel": {      "command": "uvx",      "args": ["bawbel-mcp"]    }  }}

Claude Code

bash
claude mcp add bawbel uvx bawbel-mcp

Cursor / Windsurf

Add to your MCP settings:

json
{  "bawbel": {    "command": "uvx",    "args": ["bawbel-mcp"]  }}

Remote deployment (Streamable HTTP)

bash
uvx bawbel-mcp --transport streamable-http --host 0.0.0.0 --port 8000

Example conversations

Scan a server before connecting:

"Before I add this MCP server to my config, scan it for security issues: https://api.some-mcp-server.com"

Claude calls scan_server_card("https://api.some-mcp-server.com") and reports findings with AVE IDs, AIVSS severity scores, and remediation steps.

Check a skill file:

"Check this skill file content for prompt injection vulnerabilities"

Claude calls scan_content(content) and returns findings including any toxic flow chains detected.

Check for hardcoded credentials:

"Does this skill file contain any hardcoded API keys or secrets?"

Claude calls scan_creds(content) and returns credential findings only.

Check for unsafe delegation:

"Does this skill spawn sub-agents without proper trust boundaries?"

Claude calls scan_chain(content) and returns delegation chain findings.

Accept a false positive:

"Mark AVE-2026-00001 on line 7 of travel.md as a false positive. Reason: internal registry endpoint, not attacker-controlled."

Claude calls accept_finding(...) and writes the justified suppression comment directly into the file. The approval is tracked in version control.

Score a server against the spec:

"Does this server follow the MCP spec? https://api.some-mcp-server.com"

Claude calls check_conformance("https://api.some-mcp-server.com") and returns a score, grade, and list of failed checks.

Look up a vulnerability:

"What is AVE-2026-00041 and how do I fix it?"

Claude calls lookup_ave("AVE-2026-00041") and returns the full record with behavioral fingerprint, IOCs, and remediation steps.

Search for relevant vulnerabilities:

"What AVE records cover credential exfiltration?"

Claude calls search_ave("credential exfiltration") and returns matching records with AIVSS scores and OWASP MCP categories.

Audit mode - see all findings including suppressed:

"Scan this file and show me everything, including suppressed findings."

Claude calls scan_content(content, no_ignore=True) and bypasses all suppression layers.

Requirements

  • Python 3.10+
  • bawbel-scanner>=1.2.2 (installed automatically)
  • fastmcp>=3.0.0 (installed automatically)

The bawbel CLI must be available in PATH. Installing bawbel-mcp installs bawbel-scanner which provides the bawbel CLI.

Related

Apache 2.0. Built by Bawbel.

Source: README.md at commit 52eac38

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts