Enables AI clients to interact with Toreva governed objects through policy-checked Solana wallet actions, simulations, and transaction preparation.
Also known as toreva/kit, @toreva/mcp
- Stars
- 0
- Tools
- 7
- Downloads, 30 days
- —
- Latest version
- 0.2.0
- Last commit
- Nov 16, 2026
- License
- —
What is Toreva Kit MCP?
Toreva Kit enables AI clients to interact with Toreva governed objects through policy-checked Solana wallet actions, simulations, and transaction preparation. It exposes 7 tools, such as toreva_establish_agent_wallet, toreva_read_or_scan, toreva_simulate_action.
Summary generated from the project's README
About Toreva Kit MCP server
Kit provides a connection between AI clients and Toreva governed objects through policy-checked Solana wallet actions. Developers can integrate this server into local environments using Claude Desktop, Cursor, or OpenClaw. The setup requires running a login command to generate a token or providing a RELAY_AUTH_TOKEN from a secret store. This server operates over stdio and allows users to bring their own compute, meaning model execution happens on the developer's own account rather than through Toreva's hosted infrastructure.
The server includes specific tools for managing agent interactions and verifying outcomes. Users can establish agent wallets with hard limits, simulate actions before they are finalized, and prepare unsigned transactions. Every interaction with the gateway relay results in a receipt, which can be fetched or explained to provide proof of the outcome. This system is designed for developers building agent fleets or individual integrations where security and verifiable receipts are required for every object read or write.
Written from the project's README. Every use case is checked against a quote from it.
How to install Toreva Kit MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Toreva Kit MCP in Claude Code
$ claude mcp add kit -- npx -y @toreva/mcpInstall Toreva Kit MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"kit": {
"command": "npx",
"args": [
"-y",
"@toreva/mcp"
]
}
}
}Install Toreva Kit MCP in VS Code
.vscode/mcp.json
{
"servers": {
"kit": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@toreva/mcp"
]
}
}
}Install Toreva Kit MCP in VS Code CLI
$ code --add-mcp '{"name":"kit","type":"stdio","command":"npx","args":["-y","@toreva/mcp"]}'Install Toreva Kit MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"kit": {
"command": "npx",
"args": [
"-y",
"@toreva/mcp"
]
}
}
}Install Toreva Kit MCP in Codex
$ codex mcp add kit -- npx -y @toreva/mcpInstall Toreva Kit MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.kit] command = "npx" args = ["-y", "@toreva/mcp"]
Install Toreva Kit MCP in Gemini CLI
$ gemini mcp add -s user kit npx -- -y @toreva/mcpInstall Toreva Kit MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"kit": {
"command": "npx",
"args": [
"-y",
"@toreva/mcp"
]
}
}
}Toreva Kit MCP tools 7
Detected from the READMEtoreva_establish_agent_wallettoreva_read_or_scantoreva_simulate_actiontoreva_prepare_unsigned_transactiontoreva_explain_actiontoreva_get_receipttoreva_refuse_action
| toreva_establish_agent_wallet | — | |
| toreva_read_or_scan | — | |
| toreva_simulate_action | — | |
| toreva_prepare_unsigned_transaction | — | |
| toreva_explain_action | — | |
| toreva_get_receipt | — | |
| toreva_refuse_action | — |
Configuration
RELAY_AUTH_TOKEN
| Name | Description | |
|---|---|---|
| RELAY_AUTH_TOKEN | — |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachabletoreva/kit is public and reachablegithub.com/toreva/kit ↗Pass
- Package names this repository as its source@toreva/mcp names toreva/kit as sourcenpmjs.com/package/@toreva/mcp ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-11-13github.com/toreva/kit ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @toreva/mcpPass
- No critical advisory in the package or its dependencies100 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model7 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubtoreva kit
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.
The Three Doors
Door 1: MCP
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 doctor
Restart the client, then ask it about your Toreva objects or receipts. Supported
client config targets are claude-desktop, cursor, and openclaw.
Door 2: Customer-Owned Fleet
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.
Door 3: Hosted Compute
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.
How Answers Land
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.
MCP Tools
| Tool | What it does |
|---|---|
toreva_establish_agent_wallet |
Create the agent wallet with hard limits |
toreva_read_or_scan |
Read or scan a main wallet or agent wallet |
toreva_simulate_action |
Test an action before anything is prepared |
toreva_prepare_unsigned_transaction |
Prepare an unsigned transaction after simulation |
toreva_explain_action |
Explain an action or receipt |
toreva_get_receipt |
Fetch one receipt |
toreva_refuse_action |
Refuse an unsafe action and return a refusal receipt |
Install
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-mcp
For runner-owned environments:
RELAY_AUTH_TOKEN=your_token toreva-mcp
For local development:
pnpm install
pnpm --filter @toreva/mcp build
RELAY_AUTH_TOKEN=your_token node packages/mcp/dist/index.js
Package
@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.
Packages
| Package | What |
|---|---|
@toreva/mcp |
MCP server for agent integration |
@toreva/types |
Shared schemas and types |
@toreva/sdk |
TypeScript client library |
@toreva/cli |
Command-line interface |
Verify
pnpm test
pnpm --filter @toreva/mcp build
Regulatory notice
This 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.
License
MIT — see LICENSE
Toreva Kit MCP questions
How do I add Toreva Kit MCP to Claude Code?
Run claude mcp add kit -- npx -y @toreva/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Toreva Kit MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Toreva Kit MCP provide?
It exposes 7 tools, including toreva_establish_agent_wallet, toreva_read_or_scan, toreva_simulate_action, toreva_prepare_unsigned_transaction, toreva_explain_action.
Does this connector handle money transfers?
No, no money moves through this connector.
Which AI clients are supported?
The supported client configuration targets are Claude Desktop, Cursor, and OpenClaw.
How do I authenticate the MCP server?
You can use the token generated by the 'toreva login' command or provide an explicit RELAY_AUTH_TOKEN from your secret store.