Clarity AI for AI agents
Clarity AI simulates SFDR fund classifications from a fund's name or identifier, helping investment teams check sustainability disclosure rules before filing. 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 Clarity AI.
Check a fund's SFDR classification
Check how a fund would classify under SFDR rules using its ISIN before a filing.
Search for a security
Search for a specific security by name to confirm its identifier before running a check.
Interpret an SFDR result
Interpret a completed SFDR assessment's result before it goes into a compliance report.
6 Clarity AI actions, graded by risk.
Every Clarity AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- clarity_ai.search_securitiesSearch securities
write
5Create and change things. Allow, or ask the user first.
- clarity_ai.sfdr20_checkSfdr20 check
- clarity_ai.sfdr20_check_by_isinSfdr20 check by isin
- clarity_ai.sfdr20_check_by_querySfdr20 check by query
- clarity_ai.interpret_sfdr20_resultInterpret sfdr20 result
- clarity_ai.sfdr20_assess_fund_nameSfdr20 assess fund name
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Clarity AI in three steps.
- 01Your users connect Clarity AIThey add their Clarity AI no auth on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “sfdr20 check” can wait for the user to approve.
- 03Any agent can actYour agent calls Clarity AI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('clarity_ai', { read: 'allow', write: 'ask', // sfdr20_check destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Clarity AI connects.
Clarity AI needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.
The same Clarity AI 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
- No auth
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Clarity AI from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Clarity AI and Arc0, answered.
Can I use Clarity AI with Claude, ChatGPT or Cursor?
Yes. Connect Clarity AI 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 Clarity AI actions you allow.
How do users connect Clarity AI?
Clarity AI needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.
Which Clarity AI actions can my agent take?
6 in total: 1 read, 5 write and 0 destructive, such as “sfdr20 check”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Clarity AI?
Yes. Allow read actions and deny writes in the Clarity AI policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Clarity AI too?
Yes. The same Clarity AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Clarity AI into your agent.
Your users connect Clarity AI once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan