mcp-supply-guard
Enables supply-chain integrity for MCP tools by locking tool-definition hashes after review and detecting added, removed, modified, or risky tool definitions.
README
🧬 mcp-supply-guard
MCP tool-definition supply-chain integrity. 2026 security data point: 43% of MCP servers have command injection vulnerabilities, and tool definitions can mutate after approval — a rug-pull vector. This library locks a baseline of tool-definition content hashes after review, then verifies later loads: flagging added / removed / modified tools, plus a risk scan for command-execution danger signals.
Zero dependencies. Pure Python stdlib.
Quick Start
pip install mcp-supply-guard
Usage
from mcp_supply_guard import load_tools, fingerprint, verify, scan_risk
baseline = [fingerprint(t) for t in load_tools("approved.json")] # lock after review
report = verify(load_tools("current.json"), baseline)
print(report.clean) # False if any tool added/modified
for f in report.findings:
print(f.kind, f.tool, f.message)
risks = scan_risk(load_tools("current.json"))
CLI
mcp-supply-guard lock approved.json baseline.json
mcp-supply-guard verify current.json baseline.json --json # CI exit 1 on added/modified
mcp-supply-guard risk current.json --json
tools.json
{"tools": [{"name": "search", "description": "Search the index",
"inputSchema": {"type": "object", "properties": {"q": {"type": "string"}}}}]}
Findings
| Kind | Severity | Meaning |
|---|---|---|
added |
error | tool added after baseline locked |
modified |
error | definition hash changed (rug-pull vector) |
removed |
warning | baseline tool missing now |
risky |
error/warning | command-execution danger signals in description/schema |
License
MIT © wwb-bill
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.