Enables policy-checked interactions with Solana wallets, including establishing agent wallets with configurable limits, reading and scanning wallet data, simulating actions, preparing unsigned transactions, explaining actions, fetching receipts, and refusing unsafe actions.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@toreva-mcp Simulate a transfer of 0.5 SOL to my main wallet"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Connector primitives for Toreva governed objects. Bring your own compute, use the gateway relay, and require receipts for every outcome.
Kit provides SDK, CLI, and MCP connectors for developers connecting their own compute to Toreva governed objects. The setup paths below are developer integrations.
The Day-1 Mac helper scope is Pair and Unpair only, for every user. It must request no Screen Recording or Accessibility permissions and take no jobs. Developer connector setup is separate from helper pairing.
The front door is the object store. MCP clients, SDK callers, CLI users, and customer-owned agent fleets all read and write the same Toreva objects through the gateway relay, and every accepted, pending, or refused outcome returns a receipt.
GitHub can prove which organization and admin are acting. It is not the transport for Toreva work messages. Compute is bound per scope, and the live paths put model execution on the developer's own account.
No money moves through this connector.
For developer integrations, start here. Your AI client connects the Toreva MCP server, your own client subscription does the work, and Toreva receives only the object reads and writes you authorize.
npx toreva init --client=claude-desktop
npx toreva login
npx toreva doctorRestart the client, then ask it about your Toreva objects or receipts. Supported
client config targets are claude-desktop, cursor, and openclaw.
Use this when you need unattended or scheduled agents. A GitHub organization
admin runs agents in their own org, on their own runners, with their own model
credentials. The agents call Toreva through MCP, SDK, or CLI and land answers
back on Toreva objects with receipt_id proof.
Start here: GitHub Org Agent Fleet.
Hosted compute means Toreva runs the agents and carries the marginal model cost. This door is deferred and is not documented as available. Use MCP or a customer-owned fleet today.
Related MCP server: coldstar-signer-mcp
The object store is the receiving system. A work surface prepares a relay
request, sends it to https://gateway.toreva.com/relay, and treats the result
as accepted only when the gateway returns a receipt_id.
For the shared install, invoke, and receipt shapes, see Work-Surface Connector Primitives.
Tool | What it does |
| Create the agent wallet with hard limits |
| Read or scan a main wallet or agent wallet |
| Test an action before anything is prepared |
| Prepare an unsigned transaction after simulation |
| Explain an action or receipt |
| Fetch one receipt |
| Refuse an unsafe action and return a refusal receipt |
The local package runs over stdio. Use either the token written by
toreva login or an explicit RELAY_AUTH_TOKEN from your own secret store.
npm install -g @toreva/mcp
toreva login
toreva-mcpFor runner-owned environments:
RELAY_AUTH_TOKEN=your_token toreva-mcpFor local development:
pnpm install
pnpm --filter @toreva/mcp build
RELAY_AUTH_TOKEN=your_token node packages/mcp/dist/index.js@toreva/mcp is the Rung-1 MCP package. Version 0.2.0 is stdio-local only.
The public metadata is server.json and packages/mcp/package.json.
Package | What |
| MCP server for agent integration |
| Shared schemas and types |
| TypeScript client library |
| Command-line interface |
pnpm test
pnpm --filter @toreva/mcp buildThis software provides tooling for interacting with the Toreva policy service. It does not provide financial advice, investment advice, trading advice, or any other form of advice. Use of this software does not create a fiduciary relationship, advisory relationship, or any other professional relationship between you and Toreva Pty Ltd.
Toreva Pty Ltd is not responsible for modifications made to this software by third parties, including modifications that alter or remove compliance language, disclaimers, or risk warnings. If you use a modified version of this software, you do so at your own risk and are responsible for ensuring your use complies with applicable law.
MIT — see LICENSE
This server cannot be deployed
Pre-sign Solana tx guard for agents: ALLOW/WARN/BLOCK verdict, x402 USDC pay-per-call.
Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
Dry-run Solana txs before agents sign: exact balance changes, intent match, token traps. 25 free/day
