IBM X-Force Exchange for AI agents

IBM X-Force Exchange is a threat intelligence sharing platform for researching security threats and aggregating intelligence. Security teams fold it into their existing checks rather than relying on it alone. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Security and identityAPI keyMCP + RESTexchange.xforce.ibmcloud.com
AUDIT LOG · IBM X-FORCE EXCHANGEPOLICY: acme-support
09:41:07 · claude · u_8f2read
ibm_x_force_exchange.get_version
Get Current API Version✓ allowed · 212ms
09:41:08 · claude · u_8f2read
ibm_x_force_exchange.get_userprofile
Get User Profile Information✓ allowed · 164ms
09:41:09 · claude · u_8f2write
ibm_x_force_exchange.post_auth_api_key
Generate API Key and Password✓ approved · approved by user
EVERY IBM X-FORCE EXCHANGE CALL, ON THE RECORD
01 · USE CASES

What agents do in IBM X-Force Exchange.

01

Look up a URL's threat category

Check a suspicious URL's category classification before deciding whether to block it.

02

Pull recent public collections

Pull recently published threat intelligence collections to brief the security team.

03

Check an IP's risk profile

Look up a reported IP address's category, read-only, as part of an incident investigation.

02 · ACTIONS

7 IBM X-Force Exchange actions, graded by risk.

Every IBM X-Force Exchange action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

6

Look things up. Allowed by default.

  • ibm_x_force_exchange.get_version
    Get Current API Version
  • ibm_x_force_exchange.get_userprofile
    Get User Profile Information
  • ibm_x_force_exchange.get_ipr_categories
    Get IPR Category List
  • ibm_x_force_exchange.get_url_categories
    Get URL Category List
  • ibm_x_force_exchange.get_casefiles_public
    Get Latest Public Collections
  • ibm_x_force_exchange.get_casefiles_public_paginated
    Get Public Collections Paginated

write

1

Create and change things. Allow, or ask the user first.

  • ibm_x_force_exchange.post_auth_api_key
    Generate API Key and Password

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

IBM X-Force Exchange in three steps.

  1. 01Your users connect IBM X-Force ExchangeThey add their IBM X-Force Exchange api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “generate API Key and Password” can wait for the user to approve.
  3. 03Any agent can actYour agent calls IBM X-Force Exchange through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('ibm_x_force_exchange', {
  read: 'allow',
  write: 'ask',        // post_auth_api_key
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How IBM X-Force Exchange connects.

Users add their IBM X-Force Exchange api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same IBM X-Force Exchange connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use IBM X-Force Exchange from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

IBM X-Force Exchange and Arc0, answered.

Q01

Can I use IBM X-Force Exchange with Claude, ChatGPT or Cursor?

Yes. Connect IBM X-Force Exchange to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the IBM X-Force Exchange actions you allow.

Q02

How do users connect IBM X-Force Exchange?

Users add their IBM X-Force Exchange api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which IBM X-Force Exchange actions can my agent take?

7 in total: 6 read, 1 write and 0 destructive, such as “generate API Key and Password”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in IBM X-Force Exchange?

Yes. Allow read actions and deny writes in the IBM X-Force Exchange policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call IBM X-Force Exchange too?

Yes. The same IBM X-Force Exchange connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug IBM X-Force Exchange into your agent.

Your users connect IBM X-Force Exchange once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan