# agentguard — policy proxy for agent tool calls (remote · agentwares-agentguard.vercel.app)

Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.

- Trust score: 75/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- remote · `agentwares-agentguard.vercel.app`: 75/100 (this document), [markdown](https://verifymcp.io/servers/agentwares-agentguard-cloud/api-mcp.md), [page](https://verifymcp.io/servers/agentwares-agentguard-cloud/api-mcp)

## Channel facts

- Endpoint: `https://agentwares-agentguard.vercel.app/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1129 tokens (~161/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 7 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 supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the agentguard — policy proxy for agent tool calls MCP server?

agentguard — policy proxy for agent tool calls is a hosted endpoint at https://agentwares-agentguard.vercel.app/api/mcp, so there is nothing to install locally. 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 --transport http agentwares-agentguard-cloud 'https://agentwares-agentguard.vercel.app/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "agentwares-agentguard-cloud": {
      "url": "https://agentwares-agentguard.vercel.app/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "agentwares-agentguard-cloud": {
      "type": "http",
      "url": "https://agentwares-agentguard.vercel.app/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.agentwares-agentguard-cloud]
url = "https://agentwares-agentguard.vercel.app/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agentwares-agentguard-cloud": {
      "type": "remote",
      "url": "https://agentwares-agentguard.vercel.app/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add agentwares-agentguard-cloud --url 'https://agentwares-agentguard.vercel.app/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  agentwares-agentguard-cloud:
    url: "https://agentwares-agentguard.vercel.app/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "agentwares-agentguard-cloud": {
      "Transport": "http",
      "Url": "https://agentwares-agentguard.vercel.app/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add agentwares-agentguard-cloud -t streamable-http -u 'https://agentwares-agentguard.vercel.app/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "agentwares-agentguard-cloud": {
      "type": "http",
      "url": "https://agentwares-agentguard.vercel.app/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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 75, +1)

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

### 2026-09-23 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-21 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 69, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 128 → 161
- [functional] Server version: 0.1.1 → 0.2.0
- [functional] New tool “agentguard_spend_report”

### 2026-09-13 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (7)

### `agentguard_get_pricing` (~96 tokens)

Machine-readable pricing for agentguard hosted: bands (Starter/Pro/Team) with included tool calls per month, the 80% soft alert and 150% hard stop, features, the free trial allowance, and `per_call` — buying tool calls outright at POST /api/v1/calls from a prepaid balance, which is the one purchase here an unattended agent can complete. Same data as /pricing.json.

### `agentguard_spend_report` (~317 tokens)

Read an agent log and report what it spent: totals, calls by tool and by class, estimated
dollars by rail, loops, the largest single run, and — for every overspend — the agentguard
band whose cap would have stopped it, the exact cap, and the call that would have tripped
it.

Needs no account and no key. The log is read in the request and discarded; nothing is
stored. Accepts an agentwares audit export (`agentwares.audit/v1`), a Claude Code session
\`.jsonl`, or a CSV/JSONL of tool calls with any of `tool`, `ts`, `class`, `amount_usd`,
\`rail`, `run_id`, `model`, `input_tokens`, `output_tokens`.

Caps come from the proxy's own default policy, so a band named here refuses exactly what
it says it refuses. Buying that band is a checkout a person completes; the calls-only
purchase an unattended agent can complete is in `agentguard_get_pricing` instead.

Input parameters:

- `detail` (string): `concise` (default) returns the totals, the top ten tools, the rails, the loops and every overspend. `full` adds the complete per-tool breakdown and the window. Ask for `full` only when you are going…
- `log` (string, required): The log itself, verbatim — JSON, JSONL or CSV. Not a path and not a URL: this server does not fetch anything.

### `agentguard_create_proxy` (~150 tokens)

Create a hosted agentguard proxy in front of an MCP server. Returns the proxy id, the per-customer MCP URL and the proxy key (shown once). Point your agent's MCP client at the URL with `Authorization: Bearer <key>`. Requires an account key.

Input parameters:

- `mode` (string): dry-run records what the policy would have blocked and lets every call through; enforce actually blocks. Start in dry-run.
- `slug` (string, required): short name, a-z 0-9 -
- `upstreamName` (string): name used to namespace tools when you add more upstreams later
- `upstreamUrl` (string, required): Streamable HTTP URL of the MCP server to protect

### `agentguard_set_policy` (~96 tokens)

Replace a proxy's policy (YAML: mode, upstreams, classify, caps, loop, dry_run, approvals, alerts, chaos, drift). Validated before saving; takes effect within 30 seconds. Requires an account key.

Input parameters:

- `policyYaml` (string, required): the complete policy document; it replaces the current one rather than merging
- `proxyId` (string, required): the proxy id returned by agentguard_create_proxy

### `agentguard_get_run` (~105 tokens)

The incident-shaped report for one run: counts (calls, reads, writes, faked, blocked, spend), the call timeline with decisions, dry-run mutations (what would have changed), ledger entries and the audit-chain verification. Requires an account key.

Input parameters:

- `proxyId` (string, required): the proxy id returned by agentguard_create_proxy
- `runId` (string, required): the X-Run-Id your agent sent with the calls; one run is one agent session

### `agentguard_export_audit` (~101 tokens)

Export a run's hash-chained audit entries (prev_hash, hash, redacted args) with the Merkle root, for disputes and questionnaires. Verify offline with sha256(prev_hash + canonical(entry)). Requires an account key.

Input parameters:

- `proxyId` (string, required): the proxy id returned by agentguard_create_proxy
- `runId` (string, required): the X-Run-Id your agent sent with the calls; one run is one agent session

### `agentguard_recommend_allowlist` (~81 tokens)

Least-privilege recommendation from the proxy's recorded calls: the minimal tool allowlist, argument keys used per tool, and the upstream tools never used (remove them first). No LLM call here; apply it in the dashboard. Requires an account key.

Input parameters:

- `proxyId` (string, required): the proxy id returned by agentguard_create_proxy

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/agentwares-agentguard-cloud/api-mcp#diagnostics

## Score history

- 2026-09-25: 75
- 2026-09-24: 74
- 2026-09-23: 74
- 2026-09-22: 73
- 2026-09-21: 73
- 2026-09-20: 72
- 2026-09-19: 72
- 2026-09-18: 71
- 2026-09-17: 71
- 2026-09-16: 70
- 2026-09-15: 70
- 2026-09-14: 69
- 2026-09-13: 70
- 2026-09-12: 69
- 2026-09-11: 66
- 2026-09-10: 66
- 2026-09-09: 65
- 2026-09-08: 65
- 2026-09-07: 64

## Common questions

### What is the agentguard — policy proxy for agent tool calls MCP server?

agentguard — policy proxy for agent tool calls is an MCP server listed in the public MCP registry as io.github.agentwares/agentguard-cloud. Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls. This page covers its hosted endpoint (https://agentwares-agentguard.vercel.app/api/mcp).

### Is the agentguard — policy proxy for agent tool calls MCP server safe to use?

agentguard — policy proxy for agent tool calls scores 75 out of 100 on VerifyMCP. 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 — policy proxy for agent tool calls MCP server expose?

agentguard — policy proxy for agent tool calls exposes 7 tools: agentguard_get_pricing, agentguard_spend_report, agentguard_create_proxy, agentguard_set_policy, agentguard_get_run, and 2 more. Their descriptions and schemas cost roughly 946 tokens of context every time the server is loaded.

### Does the agentguard — policy proxy for agent tool calls MCP server require authentication?

No. We connected to agentguard — policy proxy for agent tool calls without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the agentguard — policy proxy for agent tool calls MCP server still maintained?

agentguard — policy proxy for agent tool calls 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.

## Links

- Remote endpoint: https://agentwares-agentguard.vercel.app/api/mcp
- Repository: https://github.com/agentwares/servers
- Website: https://agentwares-agentguard.vercel.app/
- Changelog RSS feed: https://verifymcp.io/servers/agentwares-agentguard-cloud/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/agentwares-agentguard-cloud/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/agentwares-agentguard-cloud/api-mcp