How to Connect Archer IRM to Gemini via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Archer IRM, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Archer IRM + Gemini

Read Archer IRM (formerly RSA Archer) GRC data through its REST and Content APIs: applications, levels, fields and values lists, plus risk, control, finding and incident records searched with OData. Session login with an Archer account.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

ARCHER_URL, ARCHER_INSTANCE, ARCHER_USERNAME, ARCHER_PASSWORD

Step 1 — Get credentials

1. Ask your Archer administrator for a dedicated API account that logs in with a password and has read access to the applications the AI should query. Every call runs with that account's permissions.
2. Set ARCHER_URL to the address you open Archer on, with https:// and without /apps or a trailing slash, for example https://yourcompany.archerirm.com for Archer SaaS. On-premise installs often live under a virtual directory: include it, as in https://archer.example.com/RSAarcher.
3. Set ARCHER_INSTANCE to the instance name you enter on the Archer login page (often a number for Archer SaaS). An administrator also finds it in Archer Control Panel or Administration → Installation Settings.
4. Set ARCHER_USERNAME and ARCHER_PASSWORD. Fill in ARCHER_USER_DOMAIN only if the account belongs to a user domain; leave it empty otherwise.
5. With single sign-on, an administrator must select Allow manual bypass for the instance in Archer Control Panel, or the REST login is refused.
6. Install the connector and run archer_list_applications. It lists the applications the account can see, such as the risk register, findings, controls, incidents, policies and vendors.

Read-only: this first version only reads. The AI cannot create, change or delete records in Archer.

Sessions: the connector logs in with the account and logs in again on its own when Archer's session timeout (often 20 to 30 minutes) ends the session.

How it finds records: archer_list_content_endpoints shows the levels the account can read, each with its alias, and archer_query_records searches one of them using readable field names, at most 1,000 records per call. Aliases are case-sensitive. archer_list_application_fields and archer_get_values_list turn field and value ids into readable names.

Reports: Archer serves saved reports and statistic searches only through its SOAP web services, which this connector does not call. Ask the AI to rebuild the report as a query with archer_query_records instead.

Common errors: 401 means the login or the session failed, so check the account, the instance name and, with single sign-on, the manual bypass. 403 means the account lacks the permission for that application. An answer with IsSuccessful set to false and validation messages means Archer refused the request.

The connector does not write to Archer, run saved reports or statistic searches, or use Archer's SOAP web services.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Gemini

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Gemini CLI reads MCP servers from ~/.gemini/settings.json (on Windows %USERPROFILE%\.gemini\settings.json). Add:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart gemini.
3. Run /mcp inside Gemini CLI (or gemini mcp list in your shell): anythingmcp should show as connected.
4. Start prompting: Gemini CLI can now call the Archer IRM tools.

Available tools

Example prompts

• "List the applications in our Archer instance and tell me which ones hold risks, findings and incidents."
• "Show me all open findings whose due date has passed, grouped by owner."
• "Which risks in the risk register are rated high, and who owns each of them?"
• "Rebuild our monthly incident report: incidents opened last month by category and status."

FAQ

Where does Gemini CLI look for MCP servers? In ~/.gemini/settings.json for your user, or in .gemini/settings.json inside a project. gemini mcp list shows each server and whether it connects.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT