ActionGuard Protocol Inspector Agent

io.github.lsendelPublished by GitHub account lsendelv1.0.0Updated Nov 4, 2026

Diff and poisoning detection for MCP servers: catch schema drift and prompt poisoning.

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Remote MCP server that audits MCP servers and AI agent endpoints for reliability, security and schema drift, and checks tools against a pinned hash.

What you can do
  • Run a five-stage live reliability, security and schema audit of an MCP or agent endpoint, returning a graded scorecard
  • Compare an MCP server's tool schemas and descriptions against a pinned dual-hash baseline to detect drift or poisoned descriptions
When to use it
Useful when you maintain or depend on MCP servers and want to catch silent tool-schema changes or tampered tool descriptions before agents act on them, for example as a pre-release or CI-style check.
Requirements
A remote endpoint at actionguard.ai over streamable HTTP; no authentication, environment variables or headers are declared. The target MCP or agent endpoint must be reachable from the service, and a pinned hash is needed for drift checks.
Before you install
The service probes third-party endpoints from its own infrastructure, so target URLs are shared with a third party. Drift checks depend on a pinned hash you must supply and keep current. The README also describes paid API keys, a proxy gateway and monitoring, which are separate from these two tools.

Installation

In SourceWeft

  1. Open ActionGuard Protocol Inspector Agent in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.lsendel%2Factionguard/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "actionguard-protocol-inspector-agent": {
      "type": "http",
      "url": "https://actionguard.ai/mcp"
    }
  }
}

README

ActionGuard.ai

[ActionGuard Verified] [Glama Quality Score] [Smithery] [CI Tests] [License: MIT] [Edge: Cloudflare]

Drift and poisoning detection for MCP servers.
"SSL Labs for MCP servers. Know when your tools change, not just when they go down."
Diff detection for MCP tools: catch silent schema drift and poisoned tool descriptions before your autonomous agents run them.

Live Production Services

Quickstart

1. GitHub Actions CI Gate

Block breaking changes and unannounced schema mutations before they hit production:

yaml
name: CIon: [pull_request]
jobs:  verify-agent-tools:    runs-on: ubuntu-latest    steps:      - name: Verify Upstream MCP Tools        uses: lsendel/actionguard@v1        with:          target_url: 'https://github.mcp.modelcontextprotocol.io/mcp'          pinned_hash: '81d36f5215b689d6f100cfe77096fbe8d113c304c0dd8374d69a84678fb69415'

2. Zero-Trust Runtime Gateway Proxy ("Cloudflare for MCP")

Route agent tool calls through ActionGuard's edge firewall to terminate drifted tools with HTTP 423 Locked:

json
{  "mcpServers": {    "weather": {      "command": "npx",      "args": [        "-y",        "@modelcontextprotocol/server-weather",        "--proxy",        "https://actionguard.ai/proxy/v1?target=https%3A%2F%2Fapi.weather.com%2Fmcp&pin=a1b2c3d4..."      ]    }  }}

3. Embed Live Status Badges in Your Repository

Show real-time verification and protocol compliance on your MCP server's GitHub repository.

Markdown (Native SVG)
markdown
[![ActionGuard Verified](https://actionguard.ai/badge/<your-domain-or-slug>.svg)](https://actionguard.ai/servers/<your-domain-or-slug>)
Shields.io Endpoint
markdown
[![ActionGuard Verified](https://img.shields.io/endpoint?url=https%3A%2F%2Factionguard.ai%2Fbadge%2F<your-domain-or-slug>.json)](https://actionguard.ai/servers/<your-domain-or-slug>)
  • Domain Verified Badge: Gold (#f59e0b) badge ⭐ A • Domain Owner displayed when domain ownership is claimed via DNS TXT or .well-known/actionguard-verification.
  • Reliability Grades: Dynamic color coding based on cryptographic dual-hash baseline and 5-stage protocol inspection (A+, A, B, C, D, F).
Claude Desktop & Cursor (claude_desktop_config.json)
json
{  "mcpServers": {    "github": {      "url": "https://actionguard.ai/v1/proxy?target=https://github.mcp.modelcontextprotocol.io/mcp&pin=81d36f5215b689d6f100cfe77096fbe8d113c304c0dd8374d69a84678fb69415"    }  }}
Python (LangChain / CrewAI / httpx)
python
import httpx
GATEWAY = "https://actionguard.ai/v1/proxy"TARGET = "https://github.mcp.modelcontextprotocol.io/mcp"PIN = "81d36f5215b689d6f100cfe77096fbe8d113c304c0dd8374d69a84678fb69415"
# Requests fail with 423 Locked if upstream schema drifts or tool is poisonedclient = httpx.Client(base_url=f"{GATEWAY}?target={TARGET}&pin={PIN}")

3. Run as an MCP Server (Claude Desktop, Cursor, Glama)

You can run ActionGuard natively as a tool inside any MCP client:

Stdio Mode (Claude Desktop claude_desktop_config.json)
json
{  "mcpServers": {    "actionguard": {      "command": "npx",      "args": ["-y", "@actionguard/cli", "mcp"]    }  }}
Streamable HTTP Mode
json
{  "mcpServers": {    "actionguard": {      "url": "https://actionguard.ai/mcp"    }  }}

4. CLI Quick Run

bash
# Run 5-stage live protocol audit against any MCP or A2A endpointnpx @actionguard/cli inspect https://api.myservice.com/mcp
# Compile single actionguard.json to MCP server.json, A2A agent-card.json, and DNS-AID recordsnpx @actionguard/cli compile ./actionguard.json
# Local CI checknpx @actionguard/cli check https://api.myservice.com/mcp --pin <hash>

Core Product Pillars

  1. The 5-Stage Live Inspector ("SSL Labs for Agents"): Zero-signup diagnostic tool running live edge probes against MCP and A2A endpoints, returning an A+ to F scorecard and instant copy-paste fixes.
  2. Dual-Hash Integrity Engine: Distinct cryptographic fingerprints for JSON Schemas (schema_sha256) versus tool descriptions (descriptions_sha256) to catch silent prompt mutations.
  3. Enterprise Dependency Watchlist: Automated 15-minute edge monitoring with instant multi-channel alerts (Slack Block Kit, Discord Embeds, Email via Resend, and signed Webhooks).
  4. Self-Serve Domain Proof (DNS-AID): Cryptographic domain verification via DNS TXT records or well-known challenge files to earn the Gold "⭐ Domain Verified" badge.
  5. Zero-Trust Runtime Firewall: Low-latency proxy (<15ms) that blocks execution before poisoned or drifted payloads reach your LLM.

Infrastructure Architecture

Built entirely on the Cloudflare edge stack for global sub-50ms latency:

  • Cloudflare Workers: Edge probing engine, public API, zero-trust proxy, and dynamic SVG badges.
  • Cloudflare D1: High-performance relational edge database for accounts, catalog, subscriptions, and API keys.
  • Cloudflare R2: Content-addressed, immutable storage for historical snapshot payloads, raw schemas, and audit logs.
  • Continuous Monitoring: 15-minute cron trigger with automatic drift detection and Resend email / Slack dispatch.

Monorepo Packages

text
├── packages/│   ├── core/         # @actionguard/core — Dual-hash, linter, compiler, and probes│   └── cli/          # @actionguard/cli — actionguard command line tool└── apps/    └── worker/       # Cloudflare Worker — Web Inspector, API, proxy, and D1/R2 storage

Documentation

License

MIT © ActionGuard.ai

Source: README.md at commit 7a2b41b

Tools

2

actionguard_inspect

Run a 5-stage continuous reliability, security, and schema audit of an MCP server or AI agent endpoint.

Parametersurlrequired

actionguard_check_drift

Verify whether an MCP server's tools schema or descriptions have drifted from a pinned Dual-Hash.

ParametersurlrequiredpinnedSchemaHashrequired

Version history

1
  1. v1.0.0LatestOct 21, 2026

Score

90% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.