Strale for AI agents
Strale is a developer platform combining reusable API capabilities, trust checks, and EUR wallet-backed execution, letting teams run vetted business workflows through one API. 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 Strale.
Search the capability catalog
Search Strale's catalog for a capability that matches a workflow before wiring it into an integration.
Check a wallet balance first
Check the EUR wallet balance, a read-only step, before approving a capability that spends funds.
Run a capability after preflight
Preflight a capability to confirm its inputs and cost, then run it only after the user approves.
11 Strale actions, graded by risk.
Every Strale action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
9Look things up. Allowed by default.
- strale.get_solutionGet Solution
- strale.get_executionGet Execution
- strale.get_capabilityGet Capability
- strale.list_solutionsList Solutions
- strale.search_catalogSearch Catalog
- strale.list_executionsList Executions
- strale.list_capabilitiesList Capabilities
- strale.get_wallet_balanceGet Wallet Balance
- strale.list_wallet_transactionsList Wallet Transactions
write
2Create and change things. Allow, or ask the user first.
- strale.run_capabilityRun Capability
- strale.preflight_capabilityPreflight Capability
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Strale in three steps.
- 01Your users connect StraleThey add their Strale api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “run Capability” can wait for the user to approve.
- 03Any agent can actYour agent calls Strale through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('strale', { read: 'allow', write: 'ask', // run_capability destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Strale connects.
Users add their Strale 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 Strale 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 Strale from any agent.
Strale and Arc0, answered.
Can I use Strale with Claude, ChatGPT or Cursor?
Yes. Connect Strale 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 Strale actions you allow.
How do users connect Strale?
Users add their Strale 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 Strale actions can my agent take?
11 in total: 9 read, 2 write and 0 destructive, such as “run Capability”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Strale?
Yes. Allow read actions and deny writes in the Strale policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Strale too?
Yes. The same Strale connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Strale into your agent.
Your users connect Strale once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan