# io.github.DSHCorrectover/agent-runtime-guard (npm · agent-runtime-guard)

Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.

- Trust score: 67/100 (medium)
- Change this week: +31
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- npm · `agent-runtime-guard`: 67/100 (this document), [markdown](https://verifymcp.io/servers/dshcorrectover-agent-runtime-guard/agent-runtime-guard.md), [page](https://verifymcp.io/servers/dshcorrectover-agent-runtime-guard/agent-runtime-guard)

## Channel facts

- Registry: `npm`
- Package: `agent-runtime-guard`
- Version: `1.0.0`
- 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 2026-10-18.

- **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.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (Elastic-2.0) isn't a recognized OSI-approved license.
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 562 tokens (~112/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.DSHCorrectover/agent-runtime-guard MCP server?

io.github.DSHCorrectover/agent-runtime-guard runs locally as an npm package, launched with npx -y agent-runtime-guard. 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 dshcorrectover-agent-runtime-guard -- npx -y agent-runtime-guard
```

### Cursor

```json
{
  "mcpServers": {
    "dshcorrectover-agent-runtime-guard": {
      "command": "npx",
      "args": [
        "-y",
        "agent-runtime-guard"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dshcorrectover-agent-runtime-guard": {
      "command": "npx",
      "args": [
        "-y",
        "agent-runtime-guard"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add dshcorrectover-agent-runtime-guard -- npx -y agent-runtime-guard
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dshcorrectover-agent-runtime-guard": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agent-runtime-guard"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dshcorrectover-agent-runtime-guard --command npx --arg -y --arg agent-runtime-guard
```

### Hermes

```yaml
mcp_servers:
  dshcorrectover-agent-runtime-guard:
    command: "npx"
    args: ["-y", "agent-runtime-guard"]
```

### Netclaw

```json
{
  "McpServers": {
    "dshcorrectover-agent-runtime-guard": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "agent-runtime-guard"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add dshcorrectover-agent-runtime-guard -t stdio -c npx -a -y agent-runtime-guard
```

### Other

```json
{
  "mcpServers": {
    "dshcorrectover-agent-runtime-guard": {
      "command": "npx",
      "args": [
        "-y",
        "agent-runtime-guard"
      ]
    }
  }
}
```

## 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.

### 2026-10-17 (score 67, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-16 (score 67, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-10-14 (score 67, +31)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 69
- [functional] First check of Schema quality: good

### 2026-10-12 (score 36, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-11 (score 36, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-10-06 (score 36)

First indexed and scored.

## MCP tools (5)

### `verify_tool_call` (~167 tokens)

Verify tool call (CCS 7-dimension)

Verify an AI agent tool call against CCS 7 dimensions (Structure, Schema, Security, Identity, Integrity, Latency, Cost) plus semantic attack-chain analysis and math overflow detection. Returns verdict (allowed/denied) with detailed findings. DEFAULT MODE BLOCKS UNSAFE CALLS.

Input parameters:

- `arguments` (object): Tool call arguments to verify
- `caller` (object): Caller identity, e.g. {agent_id: 'agent-001'}
- `metadata` (object): Optional metadata (execution_time_us, cost, request_id, etc.)
- `policy` (object): Optional CCS policy override (allowed_tools, denied_tools, mode, budgets, etc.)
- `tool` (string, required): Tool name as namespace.action, e.g. 'shell.exec' or 'read.file'

### `issue_evidence` (~84 tokens)

Issue signed CCS evidence receipt

Issue a CCS evidence record for a tool call. Evidence is cryptographically bound (content_hash + evidence_hash), tamper-evident, independently verifiable. Issued for allowed AND denied calls.

Input parameters:

- `arguments` (object)
- `caller` (object, required)
- `metadata` (object)
- `policy` (object)
- `tool` (string, required)

### `audit_mcp_config` (~56 tokens)

Audit MCP configuration for security risks

Audit an MCP client/server configuration JSON for security risks: plain HTTP, weak secrets, disabled TLS, missing commands. Returns structured issues with severity.

Input parameters:

- `config` (object, required): MCP configuration JSON (e.g. Claude Desktop config)

### `verify_intent_binding` (~107 tokens)

Verify intent-to-arguments binding (L4)

Verify that actual tool call arguments match a declared intent with zero tolerance. Catches cross-model parameter drift (planner says amount=100, executor writes amount=10000). No LLM needed — pure deterministic comparison. Supports exact match, numeric tolerance, and regex pattern binding modes.

Input parameters:

- `arguments` (object, required): Actual tool call arguments
- `intent` (object, required): Structured intent declaration from the agent framework
- `tool` (string, required): Tool being called, e.g. payments.send

### `verify_receipt` (~148 tokens)

Offline-verify a CCS signed receipt

Offline-verify a CCS Ed25519-signed receipt. Auditors call this with a receipt JSON produced by issue_evidence or verify_intent_binding; it checks the signature against the embedded signer_public_key and reports whether the body was tampered with. Optionally pin an expected signer public key (PEM string or sha256: fingerprint) to reject receipts from untrusted signers.

Input parameters:

- `expected_signer` (string): Optional. Either the expected PEM public key, or a sha256:<hex> fingerprint of the DER SPKI public key.
- `receipt` (object, required): The signed receipt object (must include signer_public_key, signature_alg, signature, and the signed body fields).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/dshcorrectover-agent-runtime-guard/agent-runtime-guard#diagnostics

## Score history

- 2026-10-18: 67
- 2026-10-17: 67
- 2026-10-16: 67
- 2026-10-15: 67
- 2026-10-14: 67
- 2026-10-13: 36
- 2026-10-12: 36
- 2026-10-11: 36
- 2026-10-06: 36

## Common questions

### What is the io.github.DSHCorrectover/agent-runtime-guard MCP server?

io.github.DSHCorrectover/agent-runtime-guard is an MCP server listed in the public MCP registry as io.github.DSHCorrectover/agent-runtime-guard. Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio. This page covers its npm package (agent-runtime-guard).

### Is the io.github.DSHCorrectover/agent-runtime-guard MCP server safe to use?

io.github.DSHCorrectover/agent-runtime-guard scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 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.DSHCorrectover/agent-runtime-guard MCP server expose?

io.github.DSHCorrectover/agent-runtime-guard exposes 5 tools: verify_tool_call, issue_evidence, audit_mcp_config, verify_intent_binding, verify_receipt. Their descriptions and schemas cost roughly 562 tokens of context every time the server is loaded.

### Is the io.github.DSHCorrectover/agent-runtime-guard MCP server still maintained?

io.github.DSHCorrectover/agent-runtime-guard is still listed as active in the MCP registry. We last reached this channel on 18 October 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.DSHCorrectover/agent-runtime-guard MCP server under?

io.github.DSHCorrectover/agent-runtime-guard declares the Elastic-2.0 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/agent-runtime-guard
- Socket report: https://socket.dev/npm/package/agent-runtime-guard
- Repository: https://github.com/DSHCorrectover/agent-runtime-guard
- Changelog RSS feed: https://verifymcp.io/servers/dshcorrectover-agent-runtime-guard/agent-runtime-guard.xml
- Changelog JSON feed: https://verifymcp.io/servers/dshcorrectover-agent-runtime-guard/agent-runtime-guard.json
- HTML version of this page: https://verifymcp.io/servers/dshcorrectover-agent-runtime-guard/agent-runtime-guard