# io.github.stringsofthemind-oss/once (npm · @once-agent/mcp)

Execution-safety MCP for AI coding agents protecting consequential writes from unsafe retries.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- npm · `@once-agent/mcp`: 73/100 (this document), [markdown](https://verifymcp.io/servers/stringsofthemind-oss-once/once-agent-mcp.md), [page](https://verifymcp.io/servers/stringsofthemind-oss-once/once-agent-mcp)

## Channel facts

- Registry: `npm`
- Package: `@once-agent/mcp`
- Version: `0.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-25.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 5 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 582 tokens (~72/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 69% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the io.github.stringsofthemind-oss/once MCP server?

io.github.stringsofthemind-oss/once runs locally as an npm package, launched with npx -y @once-agent/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add stringsofthemind-oss-once -- npx -y @once-agent/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "stringsofthemind-oss-once": {
      "command": "npx",
      "args": [
        "-y",
        "@once-agent/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "stringsofthemind-oss-once": {
      "command": "npx",
      "args": [
        "-y",
        "@once-agent/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add stringsofthemind-oss-once -- npx -y @once-agent/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "stringsofthemind-oss-once": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@once-agent/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add stringsofthemind-oss-once --command npx --arg -y --arg @once-agent/mcp
```

### Hermes

```yaml
mcp_servers:
  stringsofthemind-oss-once:
    command: "npx"
    args: ["-y", "@once-agent/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "stringsofthemind-oss-once": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@once-agent/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add stringsofthemind-oss-once -t stdio -c npx -a -y @once-agent/mcp
```

### Other

```json
{
  "mcpServers": {
    "stringsofthemind-oss-once": {
      "command": "npx",
      "args": [
        "-y",
        "@once-agent/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-25 (score 73, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-22 (score 72, +1)

- [security regression] Tool safety: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Stability: unverified → 0.07
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.1.2 → 0.1.3

### 2026-09-21 (score 71, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 1.00

### 2026-09-20 (score 60)

First indexed and scored.

## MCP tools (8)

### `once_assess_project` (~94 tokens)

Assess project for unsafe retry paths

Use this first when code performs payments, refunds, payouts, bookings, orders, provisioning, database/API writes, consequential messaging, deployments, MCP writes, or other side effects. Scans the project for likely consequential operations without modifying files.

Input parameters:

- `includeEstimates` (boolean): Include Once scanner estimates in the report.
- `projectPath` (string): Absolute or relative project directory. Defaults to the MCP server working directory.

### `once_explain_risk` (~101 tokens)

Explain retry risk for a consequential operation

Explain why a specific operation may need Once. Use when an agent or developer is deciding whether a payment, refund, booking, order, provisioning action, database/API mutation, webhook, deployment, MCP write, or other external side effect needs execution-safety protection.

Input parameters:

- `operation` (string, required): Plain-language description of the consequential operation.
- `retryScenario` (string): Optional timeout, retry, crash, queue-redelivery, or ambiguous-failure scenario.

### `once_plan_setup` (~64 tokens)

Preview Once setup

Preview how Once would be configured in a project without applying setup. Use after assessing a project and before allowing an agent to install or configure Once.

Input parameters:

- `projectPath` (string)
- `runtimeHttpTargetUrl` (string): Optional HTTPS target for Runtime HTTP replay protection.

### `once_setup_project` (~89 tokens)

Install and configure Once

Apply Once setup to a project. This may install dependencies and modify project files. Call once_plan_setup first, present the plan to the user, and only call this tool after explicit approval.

Input parameters:

- `confirm` (string, required): Explicit confirmation token. Must be exactly SETUP.
- `projectPath` (string)
- `runtimeHttpTargetUrl` (string): Optional HTTPS target for Runtime HTTP replay protection.

### `once_plan_protection` (~66 tokens)

Plan Once protection

Review candidate operations for Once protection without applying code changes. Use after once_assess_project to understand which call sites are patchable and why.

Input parameters:

- `includeAllConfidenceLevels` (boolean): Include all confidence levels rather than the default candidate set.
- `projectPath` (string)

### `once_apply_protection` (~75 tokens)

Apply Once protection

Transactionally apply exactly one PATCHABLE Once protection candidate. This modifies source code and creates a backup. Call once_plan_protection first, show the proposed target to the user, and only proceed after explicit approval.

Input parameters:

- `confirm` (string, required): Explicit confirmation token. Must be exactly APPLY.
- `projectPath` (string)

### `once_verify_connection` (~50 tokens)

Verify Once Cloud connection

Run Once Doctor to verify that ONCE_API_KEY is present, Once Cloud is reachable, the key is accepted, the truth endpoint works, and the safety probe passes. Does not print the API key.

### `once_live_proof` (~43 tokens)

Get Once live-proof evidence and claim boundaries

Return the current demonstrated Once proof, public evidence links, and safe claim boundaries. Use when deciding whether Once has evidence for duplicate suppression rather than relying on marketing language.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/stringsofthemind-oss-once/once-agent-mcp#diagnostics

## Score history

- 2026-09-25: 73
- 2026-09-24: 72
- 2026-09-23: 72
- 2026-09-22: 72
- 2026-09-21: 71
- 2026-09-20: 60

## Common questions

### What is the io.github.stringsofthemind-oss/once MCP server?

io.github.stringsofthemind-oss/once is an MCP server listed in the public MCP registry as io.github.stringsofthemind-oss/once. Execution-safety MCP for AI coding agents protecting consequential writes from unsafe retries. This page covers its npm package (@once-agent/mcp).

### Is the io.github.stringsofthemind-oss/once MCP server safe to use?

io.github.stringsofthemind-oss/once scores 73 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.stringsofthemind-oss/once MCP server expose?

io.github.stringsofthemind-oss/once exposes 8 tools: once_assess_project, once_explain_risk, once_plan_setup, once_setup_project, once_plan_protection, and 3 more. Their descriptions and schemas cost roughly 582 tokens of context every time the server is loaded.

### Is the io.github.stringsofthemind-oss/once MCP server still maintained?

io.github.stringsofthemind-oss/once is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.stringsofthemind-oss/once MCP server under?

io.github.stringsofthemind-oss/once declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@once-agent/mcp
- Socket report: https://socket.dev/npm/package/@once-agent/mcp
- Repository: https://github.com/stringsofthemind-oss/once
- Changelog RSS feed: https://verifymcp.io/servers/stringsofthemind-oss-once/once-agent-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/stringsofthemind-oss-once/once-agent-mcp.json
- HTML version of this page: https://verifymcp.io/servers/stringsofthemind-oss-once/once-agent-mcp