PluginBench
MCP Server

io.github.joepangallo/web-recon-agent MCP Server

io.github.joepangallo/web-recon-agent

What is the io.github.joepangallo/web-recon-agent MCP server?

Owned-target web security assessment MCP server for authenticated, high-friction apps.

How to install io.github.joepangallo/web-recon-agent

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • MCP_TARGET_ALLOWLIST
    required

    Comma-separated hostnames allowed for scanning. Required.

  • MCP_OWNED_TARGETS

    Comma-separated hostnames you explicitly own to unlock active and owned-aggressive scan modes.

  • MCP_JOB_STORE_PATH

    Optional path for persisted job metadata. Defaults to mcp-jobs.json in the current working directory.

  • MCP_MAX_CONCURRENT

    Optional maximum number of concurrent scan jobs. Defaults to 2.

  • MCP_CONFIG_PATH

    Optional path to a JSON config file that overrides allowlist and concurrency settings.

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "web-recon-agent": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-web-recon-agent"
      ],
      "env": {
        "MCP_TARGET_ALLOWLIST": "<YOUR_MCP_TARGET_ALLOWLIST>",
        "MCP_OWNED_TARGETS": "<YOUR_MCP_OWNED_TARGETS>",
        "MCP_JOB_STORE_PATH": "<YOUR_MCP_JOB_STORE_PATH>",
        "MCP_MAX_CONCURRENT": "<YOUR_MCP_MAX_CONCURRENT>",
        "MCP_CONFIG_PATH": "<YOUR_MCP_CONFIG_PATH>"
      }
    }
  }
}

Related MCP servers

Payment gateway for AI agents with tool discovery, provisioning, metering, and reliability tools.

View repository →

AI software engineer — writes code, opens PRs, reviews code, generates tests, and more.

View repository →

Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend

0
JavaScript
MIT
View repository →

Track AI agent fleet performance, costs, anomalies, and trends.

View repository →

BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.

1
TypeScript
MIT
View repository →

Measured race courses, open to all, and your own runs, Blocks and plans once you sign in.