Spydra for AI agents

Spydra runs tokenized asset stores on public blockchains, tracking tokens, investors, and payouts for businesses issuing digital securities or real-world assets. 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.

Connect Spydra See the 10 actions ↓

E-commerceAPI keyMCP + RESTspydra.app

AUDIT LOG · SPYDRAPOLICY: acme-support

09:41:07 · claude · u_8f2read

spydra.list_assets

List Assets✓ allowed · 212ms

09:41:08 · claude · u_8f2read

spydra.get_asset

Get Asset✓ allowed · 164ms

EVERY SPYDRA CALL, ON THE RECORD

01 · USE CASES

What agents do in Spydra.

Check an asset's token status

Get an asset's status counts to see how many tokens are issued, sold, or pending.

List investor transactions before a payout

List an investor's transactions as a read-only check before approving a payout against their holdings.

List available token sales

List active token sales across the account to see which offerings are currently open.

02 · ACTIONS

10 Spydra actions, graded by risk.

Every Spydra action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

spydra.get_asset
Get Asset
spydra.list_assets
List Assets
spydra.list_chains
List Chains
spydra.list_countries
List Countries
spydra.list_investors
List Investors
spydra.list_token_sales
List Token Sales
spydra.list_asset_tokens
List Asset Tokens
spydra.list_investor_tokens
List Investor Tokens
spydra.get_asset_status_counts
Get Asset Status Counts
spydra.list_investor_transactions
List Investor Transactions

write

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

No write actions.

destructive

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

No destructive actions.

03 · HOW IT WORKS

Spydra in three steps.

01Your users connect SpydraThey add their Spydra 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 Spydra 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('spydra', {
  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

04 · AUTH AND DATA

How Spydra connects.

Users add their Spydra 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 Spydra 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 Spydra from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More e-commerce apps.

Baselinker106 actions

Shippo95 actions

Shipengine66 actions

Proabono64 actions

ALL E-COMMERCE APPS →

07 · FAQ

Spydra and Arc0, answered.

Q01

Can I use Spydra with Claude, ChatGPT or Cursor?

Yes. Connect Spydra 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 Spydra actions you allow.

Q02

How do users connect Spydra?

Users add their Spydra 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 Spydra actions can my agent take?

10 in total: 10 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Spydra?

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

Q05

Can my own backend call Spydra too?

Yes. The same Spydra connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Spydra into your agent.

Your users connect Spydra once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

Connect Spydra Browse all apps →

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