# AgentGuard (npm · @agentguard-run/mcp)

Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-26

## Components

- npm · `@agentguard-run/mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/merchantguard-agentguard/agentguard-run-mcp.md), [page](https://verifymcp.io/servers/merchantguard-agentguard/agentguard-run-mcp)

## Channel facts

- Registry: `npm`
- Package: `@agentguard-run/mcp`
- Version: `0.3.1`
- 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 2026-09-26.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 100 dependencies flagged as unhealthy.
- **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 (SEE LICENSE IN LICENSE) isn't a recognized OSI-approved license.
  - Actively maintained (last published 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1021 tokens (~170/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - 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**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 83% 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 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 AgentGuard MCP server?

AgentGuard runs locally as an npm package, launched with npx -y @agentguard-run/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 merchantguard-agentguard -- npx -y @agentguard-run/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "merchantguard-agentguard": {
      "command": "npx",
      "args": [
        "-y",
        "@agentguard-run/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "merchantguard-agentguard": {
      "command": "npx",
      "args": [
        "-y",
        "@agentguard-run/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add merchantguard-agentguard -- npx -y @agentguard-run/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "merchantguard-agentguard": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@agentguard-run/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add merchantguard-agentguard --command npx --arg -y --arg @agentguard-run/mcp
```

### Hermes

```yaml
mcp_servers:
  merchantguard-agentguard:
    command: "npx"
    args: ["-y", "@agentguard-run/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "merchantguard-agentguard": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@agentguard-run/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add merchantguard-agentguard -t stdio -c npx -a -y @agentguard-run/mcp
```

### Other

```json
{
  "mcpServers": {
    "merchantguard-agentguard": {
      "command": "npx",
      "args": [
        "-y",
        "@agentguard-run/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 65, 0)

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

### 2026-09-21 (score 65)

First indexed and scored.

## MCP tools (6)

### `spend_decide` (~251 tokens)

Gate a model call BEFORE it runs. Pass metadata only (model, token counts, endpoint URL), never prompt content. Returns allow/block plus an Ed25519-signed, content-free receipt with model and hosting provenance (weights origin, jurisdiction, retention). Unknown self-hosted models need set_model_cost first (fail-closed). Optional agent_id, task_id and workflow_id accept identifiers only; spend_decide binds them into the signed actor. Read-only and cost-configuration tools accept these fields without recording a spend decision.

Input parameters:

- `agent_id` (string): Optional agent identifier; signed as actor.agentId on spend_decide
- `endpoint_url` (string): Endpoint URL. Unrecognized endpoints route as self-hosted (zero retention, your jurisdiction).
- `input_tokens` (integer, required): Projected input tokens
- `model` (string, required): Model name, e.g. llama-3.1-8b-instruct or gpt-5-mini
- `output_tokens` (integer, required): Projected output tokens
- `task_id`: Optional task identifier; signed as actor.taskId on spend_decide
- `workflow_id`: Optional workflow identifier; signed as actor.workflowId on spend_decide

### `verify_receipt` (~171 tokens)

Independently verify an AgentGuard signed receipt. Returns valid true/false. Tampering with any signed field makes verification fail. Optional agent_id, task_id and workflow_id accept identifiers only; spend_decide binds them into the signed actor. Read-only and cost-configuration tools accept these fields without recording a spend decision.

Input parameters:

- `agent_id` (string): Optional agent identifier; signed as actor.agentId on spend_decide
- `public_key_hex` (string): Signer public key (64 hex characters). Defaults to this server signer.
- `receipt_json` (string, required): The signed receipt entry as a JSON string
- `task_id`: Optional task identifier; signed as actor.taskId on spend_decide
- `workflow_id`: Optional workflow identifier; signed as actor.workflowId on spend_decide

### `export_receipts` (~140 tokens)

Export the tenant decision ledger, including earlier process runs, as a hash-chained array of signed receipts with a chain verification result. Memory mode exports this process only. Optional agent_id, task_id and workflow_id accept identifiers only; spend_decide binds them into the signed actor. Read-only and cost-configuration tools accept these fields without recording a spend decision.

Input parameters:

- `agent_id` (string): Optional agent identifier; signed as actor.agentId on spend_decide
- `task_id`: Optional task identifier; signed as actor.taskId on spend_decide
- `workflow_id`: Optional workflow identifier; signed as actor.workflowId on spend_decide

### `set_model_cost` (~176 tokens)

Register a cost for a model with no built-in pricing (required for self-hosted models: AgentGuard fails closed on unknown costs). Cents per 1,000 tokens. Optional agent_id, task_id and workflow_id accept identifiers only; spend_decide binds them into the signed actor. Read-only and cost-configuration tools accept these fields without recording a spend decision.

Input parameters:

- `agent_id` (string): Optional agent identifier; signed as actor.agentId on spend_decide
- `input_cents_per_ktok` (number, required)
- `model` (string, required)
- `output_cents_per_ktok` (number, required)
- `task_id`: Optional task identifier; signed as actor.taskId on spend_decide
- `workflow_id`: Optional workflow identifier; signed as actor.workflowId on spend_decide

### `provenance_preview` (~154 tokens)

Preview the provenance AgentGuard would attest for a model and endpoint WITHOUT spending: model identity, weights origin country (China-origin families flagged), hosting jurisdiction, retention posture. Optional agent_id, task_id and workflow_id accept identifiers only; spend_decide binds them into the signed actor. Read-only and cost-configuration tools accept these fields without recording a spend decision.

Input parameters:

- `agent_id` (string): Optional agent identifier; signed as actor.agentId on spend_decide
- `endpoint_url` (string)
- `model` (string, required)
- `task_id`: Optional task identifier; signed as actor.taskId on spend_decide
- `workflow_id`: Optional workflow identifier; signed as actor.workflowId on spend_decide

### `spend_status` (~129 tokens)

Show the active policy: caps, tenant, enforcement mode, decisions so far this session, and the signer identity. Optional agent_id, task_id and workflow_id accept identifiers only; spend_decide binds them into the signed actor. Read-only and cost-configuration tools accept these fields without recording a spend decision.

Input parameters:

- `agent_id` (string): Optional agent identifier; signed as actor.agentId on spend_decide
- `task_id`: Optional task identifier; signed as actor.taskId on spend_decide
- `workflow_id`: Optional workflow identifier; signed as actor.workflowId on spend_decide

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/merchantguard-agentguard/agentguard-run-mcp#diagnostics

## Score history

- 2026-09-26: 65
- 2026-09-25: 65
- 2026-09-24: 65
- 2026-09-23: 65
- 2026-09-22: 65
- 2026-09-21: 65

## Common questions

### What is the AgentGuard MCP server?

AgentGuard is an MCP server listed in the public MCP registry as io.github.MerchantGuard/agentguard. Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls. This page covers its npm package (@agentguard-run/mcp).

### Is the AgentGuard MCP server safe to use?

AgentGuard scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 26 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 AgentGuard MCP server expose?

AgentGuard exposes 6 tools: spend_decide, verify_receipt, export_receipts, set_model_cost, provenance_preview, spend_status. Their descriptions and schemas cost roughly 1,021 tokens of context every time the server is loaded.

### Is the AgentGuard MCP server still maintained?

AgentGuard is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- npm package: https://www.npmjs.com/package/@agentguard-run/mcp
- Socket report: https://socket.dev/npm/package/@agentguard-run/mcp
- Repository: https://github.com/MerchantGuard/agentguard-mcp
- Website: https://agentguard.run/
- Changelog RSS feed: https://verifymcp.io/servers/merchantguard-agentguard/agentguard-run-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/merchantguard-agentguard/agentguard-run-mcp.json
- HTML version of this page: https://verifymcp.io/servers/merchantguard-agentguard/agentguard-run-mcp