Occludra — MCP Gateway (AI Security Gateway)

ai.occludraPublished by occludra.aiv1.0.0Updated Oct 24, 2026

Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.

VerifiedStreamable HTTPWeb executableSecurity & Monitoring

Overview

AI-generated overview

Remote security and DLP gateway for MCP traffic that scans for tool poisoning and redacts PII in tool arguments and results.

What you can do
  • Acts as a proxy layer in front of MCP tool traffic rather than exposing its own tool set.
  • Scans tool definitions and traffic for tool-poisoning attempts.
  • Redacts personally identifiable information in tool arguments and in tool results.
  • Sits between the assistant and other MCP servers as a security and data-loss-prevention checkpoint.
When to use it
Worth considering when an assistant connects to third-party MCP servers and you want a checkpoint that screens tool definitions for poisoning and strips PII from what flows through tool calls. It is a beta service, so evaluate it before relying on it in production.
Requirements
A remote streamable HTTP endpoint; no local package to install. A bearer token in the Authorization header is required: a project API key in the oah_ format. Beta access is requested by contacting the provider by email.
Before you install
The gateway sits in the path of tool traffic, so arguments and results pass through a third-party service; confirm what it retains. The API key in the Authorization header is a secret and should be scoped and rotated. The service is labeled beta, so behavior and availability may change.

Installation

In SourceWeft

  1. Open Occludra — MCP Gateway (AI Security Gateway) in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. 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/ai.occludra%2Fmcp-gateway/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": {
    "occludra-gateway-ai-security-gateway": {
      "type": "http",
      "url": "https://api.aisecuritygateway.ai/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

67% 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

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.