MCP server - Opfor

Opfor can run as an MCP server, exposing its workflow as tools that any MCP-compatible assistant (Cursor, Claude Desktop, Windsurf) can call. Your assistant runs a full red-team from chat — no terminal required.

This is different from attacking an MCP server as a target. Here, opfor is the MCP server. To test an MCP server, see MCP mode in the CLI.

How it works

The assistant calls three tools in sequence:

opfor_list_evaluators

Discover available evaluator IDs and suites. Call this first when you haven’t named specific evaluators.

opfor_setup

Configure a target and write opfor.config.json. Returns the config path.

opfor_run

Generate attacks on the fly, run them, judge responses, and write HTML + JSON reports.

No pre-generated attack file is needed — opfor_run handles generation, execution, and reporting in one shot.

Install

git clone https://github.com/KeyValueSoftwareSystems/agent-opfor.git
cd opfor
npm install
npm run build

Once published to npm, you can skip the clone and run it via npx (see below).

Register the server

Cursor
Claude Desktop
npx (published)

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-scoped):

{
  "mcpServers": {
    "opfor": {
      "command": "node",
      "args": ["/absolute/path/to/opfor/runners/mcp/dist/index.js"]
    }
  }
}

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "opfor": {
      "command": "node",
      "args": ["/absolute/path/to/opfor/runners/mcp/dist/index.js"]
    }
  }
}

Once @agent-opfor/mcp is on npm, no clone or global install is needed:

{
  "mcpServers": {
    "opfor": {
      "command": "npx",
      "args": ["-y", "@agent-opfor/mcp"]
    }
  }
}

The server reads API keys from your project’s .env automatically — no env block needed in the config.

Usage

Once registered, just talk to your assistant:

Red team my chatbot at http://localhost:4000/chat

It calls opfor_list_evaluators → opfor_setup → opfor_run and returns a findings summary in chat, with reports saved to disk.

Tools reference

`opfor_list_evaluators`

No parameters. Returns every evaluator ID, severity, standards map, and all predefined suites.

`opfor_setup`

Configures a run and writes opfor.config.json. Returns the config path to pass to opfor_run.

Target

Parameter	Type	Required	Description
`target_name`	string	Yes	Human-readable name
`target_kind`	`agent` \| `mcp`	Yes	`agent` for HTTP/chatbot, `mcp` for servers

Agent target (target_kind = "agent"):

Parameter	Type	Required	Description
`agent_endpoint`	string	For HTTP	URL to attack
`agent_request_format`	`auto` \| `openai` \| `json`	No	Defaults to `auto`
`agent_target_api_key`	string	No	Auth token for the target
`agent_script_path`	string	For scripts	Path to a local `.js`/`.py` script
`agent_description`	string	No	What the agent does

MCP target (target_kind = "mcp"):

Parameter	Type	Required	Description
`mcp_transport`	`stdio` \| `url`	No	Defaults to `stdio`
`mcp_command`	string	For stdio	Command to start the server
`mcp_args`	string[]	No	Arguments for the command
`mcp_env`	object	No	Env vars for the server process
`mcp_url`	string	For url	Server URL (SSE / Streamable HTTP)

Evaluators, LLM, and run settings

Evaluator selection (pick one):

Parameter	Type	Description
`suite_id`	string	Suite ID (e.g. `owasp-mcp-top10`)
`evaluator_ids`	string[]	Specific evaluator IDs

LLM configuration:

Parameter	Type	Required	Description
`attack_llm`	object	Yes	LLM for generating attacks
`judge_llm`	object	No	LLM for judging (defaults to `attack_llm`)

LLM object: { provider, model, api_key_env, base_url? }.Run settings:

Parameter	Type	Description
`effort`	`adaptive` \| `comprehensive`	Defaults to `adaptive`
`turns`	number (1–10)	Turns per attack; `1` = single-turn (default)
`output_dir`	string	Where to write the config (default `.`)
`config_path`	string	Full config path (overrides `output_dir`)

`opfor_run`

Runs the full evaluation from a config produced by opfor_setup.

Parameter	Type	Required	Description
`config_path`	string	Yes	Path to the `opfor.config.json`
`output_dir`	string	No	Report directory (default: config dir)
`effort_override`	`adaptive` \| `comprehensive`	No	Override config effort
`turns_override`	number (1–10)	No	Override config turns

API key resolution

The server resolves keys in order:

The env var named in the LLM config’s api_key_env
The provider’s default env var (e.g. OPENAI_API_KEY for openai)

It loads .env from the working directory automatically — keys never go in the MCP config JSON.

Providers

Supported providers and their default env vars.

​How it works

​Install

​Register the server

​Usage

​Tools reference

​opfor_list_evaluators

​opfor_setup

​opfor_run

​API key resolution

Providers

How it works

Install

Register the server

Usage

Tools reference

`opfor_list_evaluators`

`opfor_setup`

`opfor_run`

API key resolution