Agent Security

io.github.mdfifty50-boopPublished by GitHub account mdfifty50-boopv0.1.3Updated Oct 24, 2026

Security scanning and threat detection for AI agents

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Lets an assistant scan MCP configurations and agent setups for security issues, prompt injection, leaked secrets, and permission problems.

What you can do
Provides security analysis tools for AI agent workflows: scan_mcp_config checks MCP server configurations for dangerous commands, exposed secrets, network exposure, and container misconfigurations; detect_prompt_injection analyzes text across seven attack categories; scan_secrets finds API keys, tokens, private keys, database URIs, and credentials; validate_scope_contract checks actions against tool allowlists and file-access boundaries; audit_agent_permissions compares configurations to role profiles; detect_tool_poisoning looks for hidden instructions in tool definitions; and generate_security_report produces prioritized remediation reports. It also exposes OWASP LLM Top 10 and MCP…
When to use it
Useful when reviewing or hardening MCP server configurations, auditing what an agent is allowed to do, or checking untrusted text and tool definitions for injection or poisoned instructions before an agent acts on them.
Requirements
Runs locally over stdio as an npm package; needs Node.js 18 or newer and the Model Context Protocol SDK. No accounts, API keys, or environment variables are declared.
Before you install
The README lists paid plans (Free, Starter, Pro, Enterprise) with monthly prices, so some features may require payment. The tools analyze configuration and text that may contain live credentials; treat any secrets passed in as sensitive.

Installation

In SourceWeft

  1. Open Agent Security 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

Agent Security MCP Server

Security scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows. Built on the Model Context Protocol (MCP).

Tools

ToolDescription
scan_mcp_configScan MCP server configurations for security issues (dangerous commands, exposed secrets, network exposure, container misconfigs)
detect_prompt_injectionAnalyze text for prompt injection attempts across 7 attack categories with context-aware risk scoring
validate_scope_contractCheck if agent actions comply with scope contracts (tool allowlists, file access, boundary constraints)
scan_secretsDetect leaked API keys, tokens, private keys, database URIs, and credentials in text or code
audit_agent_permissionsAudit agent configurations against role-based expectations and flag principle of least privilege violations
generate_security_reportGenerate comprehensive security assessment reports with prioritized remediation plans
detect_tool_poisoningAnalyze MCP tool definitions for hidden instructions that could manipulate agent behavior (OWASP Agentic Top 10)

Resources

ResourceURIDescription
OWASP LLM Top 10security://owasp-llm-top10OWASP Top 10 for LLM Applications (2025)
MCP Security Checklistsecurity://mcp-security-checklistSecurity checklist for MCP server deployments

Installation

bash
cd agent-security-mcpnpm install

Usage

As a standalone server

bash
npm start

In Claude Desktop / MCP client configuration

json
{  "mcpServers": {    "agent-security": {      "command": "node",      "args": ["/path/to/agent-security-mcp/src/index.js"]    }  }}

With npx (after publishing)

json
{  "mcpServers": {    "agent-security": {      "command": "npx",      "args": ["@asl-throne/agent-security-mcp"]    }  }}

Detection Coverage

Prompt Injection (7 categories, 20+ patterns)

  • Instruction Override -- "ignore previous instructions", "disregard all rules", "new instructions:"
  • Identity Manipulation -- "you are now", "pretend you are", "act as", DAN/jailbreak
  • System Prompt Extraction -- "repeat your system prompt", "show your instructions"
  • Data Exfiltration -- "send this to", "post to webhook", "email everything to"
  • Delimiter Attacks -- ```system, [INST], <|im_start|>system, XML tag injection
  • Encoded Injection -- Base64 payloads, unicode zero-width characters, hex escapes
  • Privilege Escalation -- "sudo mode", "disable safety", "bypass filters"

Secret Detection (25+ patterns)

  • AI Provider Keys -- OpenAI (sk-), Anthropic (sk-ant-)
  • Cloud Credentials -- AWS (AKIA*), GCP (AIza*), Azure connection strings
  • Source Control -- GitHub PATs (ghp_, github_pat_), OAuth tokens (gho_*)
  • Payment -- Stripe live/test keys (sk_live_, sk_test_)
  • Communication -- Slack tokens/webhooks, Telegram bot tokens
  • Database -- PostgreSQL, MongoDB, MySQL, Redis connection URIs
  • Cryptographic -- RSA/EC/OpenSSH private keys, generic PEM blocks
  • JWT -- JSON Web Tokens
  • Generic -- api_key=, secret=, password=, .env file patterns

Permission Audit (6 role profiles)

  • Researcher -- Read + search + web only
  • Analyst -- Read + search only
  • Developer -- Read + write + execute
  • Reviewer -- Read only, no network
  • Orchestrator -- Read + write + task spawning
  • Monitor -- Read only, no network, no write

Pricing

PlanPriceServersFeatures
Free$01 serverSingle scan, basic report
Starter$49/month3 serversContinuous scanning, weekly reports
Pro$199/month20 serversReal-time alerts, CI/CD integration, Slack notifications
Enterprise$799/monthUnlimitedCustom policies, EU AI Act compliance reporting, SSO, dedicated support

Requirements

  • Node.js >= 18.0.0
  • @modelcontextprotocol/sdk >= 1.12.0

License

MIT

Source: README.md at commit c160878

Tools

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

Version history

1
  1. v0.1.3LatestSep 16, 2026

Score

40% 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

    Declare a license in the repository or the registry entry.