MCP.Market

Agent Guard MCP server

by mdfifty50-boop·io.github.mdfifty50-boop/agent-guard·v0.1.3
No reviews yet

Constitutional guardrails and loop detection for AI agents

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

0 stars59 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Guard yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Guard tools (7)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_circuit_breaker

    Check if a proposed action should be allowed or blocked by the circuit breaker. Call this BEFORE executing a tool.

  • detect_loop

    Check if an agent is stuck in an infinite loop. Analyzes action patterns, uniqueness ratio, and repeated signatures.

  • get_health_dashboard

    Get an overview of all monitored agents with their current loop risk scores and status.

  • get_stuck_report

    Get a detailed analysis of why an agent is stuck, including action history, patterns, token waste estimate, and recovery recommendations.

  • log_action

    Log an agent action for loop detection. Maintains a rolling window of the last 50 actions and returns early warnings.

  • register_agent

    Register an agent for loop monitoring. Configure iteration limits and progress thresholds.

  • set_circuit_breaker

    Configure a circuit breaker to auto-terminate or warn when an action pattern repeats too many times.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan12 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 156 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Guard compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 57% of 4,460 AI and agents servers
Tools
7
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
59
more than 49% of 1,538 AI and agents servers with a package

What its tools let an agent do: 5 read · 1 create · 1 change

Install Agent Guard in Claude Code, Cursor or VS Code

Runs npx -y agent-guard-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-guard -- npx -y agent-guard-mcp
Add to Cursor

What the publisher says

From the Agent Guard repository's README, as published. We do not edit it. Read it on GitHub

agent-guard-mcp

MCP server that detects and prevents infinite agent loops — the #1 reliability problem in agentic systems.

Provides circuit breakers, pattern detection, stuck-agent analysis, and recovery recommendations via the Model Context Protocol.

Install

npx agent-guard-mcp

Claude Desktop

Add to claudedesktopconfig.json:

{
  "mcpServers": {
    "agent-guard": {
      "command": "npx",
      "args": ["agent-guard-mcp"]
    }
  }
}

From source

git clone https://github.com/mdfifty50-boop/agent-guard-mcp.git
cd agent-guard-mcp
npm install
node src/index.js

Tools

register_agent

Register an agent for monitoring.

log_action

Log an agent action for loop detection. Maintains a rolling window of the last 50 actions.

Returns early warnings when repeated patterns are detected.

detect_loop

Check if an agent is stuck in an infinite loop.

Returns:

  • is_stuck — boolean
  • confidence — 0.0 to 1.0
  • pattern — healthy, exactrepeat, lowdiversity, or exactrepeatandlowdiversity
  • suggestion — human-readable recovery advice
  • repeated_actions — list of repeated signatures with counts

setcircuitbreaker

Configure automatic intervention when action patterns repeat.

checkcircuitbreaker

Pre-flight check before executing a tool. Call this BEFORE the actual tool call.

Returns proceed: false when the circuit breaker fires (block mode only).

getstuckreport

Detailed analysis of why an agent is stuck.

Returns: action history, pattern analysis, token waste estimate, diversity ratio, top repeated patterns, and recovery recommendations.

gethealthdashboard

Overview of all monitored agents. No parameters.

Returns all agents sorted by risk score with their status (STUCK/HEALTHY), action counts, and circuit breaker config.

Resources

Usage Pattern

1. register_agent — at agent startup
2. Before each tool call:
   a. check_circuit_breaker — should this action proceed?
   b. Execute the tool
   c. log_action — record what happened
3. Periodically:
   - detect_loop — am I stuck?
   - get_health_dashboard — how are all agents doing?
4. On stuck detection:
   - get_stuck_report — what went wrong and how to recover

Tests

npm test

License

MIT

Nothing above is checked by us. What we check is on the safety report.

Agent Guard: common questions

Is Agent Guard MCP server safe?
Mostly: it is graded B (78/100). Read the Agent Guard safety report
How do I install Agent Guard?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Guard need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agent Guard maintained?
The last commit was 194 days ago (2026-04-24). The latest release is v0.1.3.
What can I use instead of Agent Guard?
Servers from other publishers that do the same job: HOL Guard MCP server, Agent-Native Chat MCP server and OpenWorkProof MCP server.
How does Agent Guard compare with other AI and agents MCP servers?
safety score 78/100 (higher than 57% of 4,460 AI and agents servers); tools 7 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Guard

Same job from other publishers: the closest match first, then the best rated.

  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A
  • Shellward
    AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
    A

More from mdfifty50-boop →