21risk for AI agents
21RISK is a compliance and risk management platform built around checklists, audits and corrective actions. Risk and quality teams use it to track and report on operational compliance. 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.
What agents do in 21risk.
Pull a compliance summary
Retrieve the current compliance status for an organization across its checklists and audits in one lookup.
Review risk model categories
List the risk model categories configured for an organization to see how audits are classified.
Generate a report snapshot
Pull a report showing audit and action completion for a property over a chosen period.
8 21risk actions, graded by risk.
Every 21risk action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- 21risk.get_itemsGet Items (BETA)
- 21risk.get_reportsGet Reports
- 21risk.get_complianceGet Compliance
- 21risk.get_propertiesGet Properties
- 21risk.get_risk_modelsGet Risk Models
- 21risk.get_organizationsGet Organizations
- 21risk.get_items_per_monthGet Items Per Month
- 21risk.get_riskmodel_categoriesGet RiskModel Categories
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
21risk in three steps.
- 01Your users connect 21riskThey add their 21risk api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls 21risk through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('21risk', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How 21risk connects.
Users add their 21risk 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 21risk 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
Use 21risk from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
21risk and Arc0, answered.
Can I use 21risk with Claude, ChatGPT or Cursor?
Yes. Connect 21risk 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 21risk actions you allow.
How do users connect 21risk?
Users add their 21risk 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.
Which 21risk actions can my agent take?
8 in total: 8 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in 21risk?
Yes. Allow read actions and deny writes in the 21risk policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call 21risk too?
Yes. The same 21risk connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug 21risk into your agent.
Your users connect 21risk once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan