Fde Agent

io.github.minjikim89Published by GitHub account minjikim89v1.0.0Updated Oct 24, 2026

Diagnose AI workflows for failure, security, and handoff risks — RED/AMBER/GREEN per node.

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

A remote MCP server that runs a pre-mortem on an agentic AI workflow, returning per-node RED/AMBER/GREEN risk ratings for failure, security and handoff.

What you can do
Diagnose an agentic AI workflow: analyze its nodes and return RED/AMBER/GREEN risk ratings across failure, security and handoff axes, grounded in an incident ontology. Supply the workflow either as a built-in sample (legal or loan) or as an inline Markdown or BPMN node inventory.
When to use it
Useful when reviewing an agentic AI workflow before launch or a change, to spot risky nodes and handoff points, or to get a quick structured risk read on a sample workflow.
Requirements
A remote streamable HTTP endpoint; no package, account, API key or header is declared. The workflow must be given as a built-in sample name or an inline Markdown/BPMN node inventory.
Before you install
The workflow description you submit is sent to a third-party remote service, so avoid including confidential process details or secrets. It only analyzes and reports; it does not change your workflow.

Installation

In SourceWeft

  1. Open Fde 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.minjikim89%2Ffde-agent/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": {
    "fde-agent": {
      "type": "http",
      "url": "https://fde-mcp.mj-mcp-tools.workers.dev/mcp"
    }
  }
}

Tools

1

diagnose_workflow

Diagnose an AI workflow for failure / security / handoff risks

FDE Agent pre-mortem: analyze an agentic AI workflow and return per-node RED/AMBER/GREEN risk across failure, security, and handoff axes, grounded in an incident ontology. Provide a built-in sample ('legal' or 'loan') or inline Markdown/BPMN node inventory.

Parametersbpmnsample

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

83% 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

    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.