Connect agentguard — policy proxy for agent tool calls and your agent gets 6 tools, among them agentguard_create_proxy, agentguard_export_audit, agentguard_get_pricing. It answers at https://agentwares-agentguard.vercel.app/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 21 October 2026, succeeded.
Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
agentguard_create_proxy | 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. Inputs: slug, upstreamUrl, upstreamName, mode |
agentguard_export_audit | 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. Inputs: proxyId, runId |
agentguard_get_pricing | 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 |
agentguard_get_run | 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 accoun Inputs: proxyId, runId |
agentguard_recommend_allowlist | 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 Inputs: proxyId |
agentguard_set_policy | 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. Inputs: proxyId, policyYaml |
Every block below points at https://agentwares-agentguard.vercel.app/api/mcp. Pick your client and copy.
claude mcp add --transport http agentguard-policy-proxy-for-agen https://agentwares-agentguard.vercel.app/api/mcp
{
"mcpServers": {
"agentguard-policy-proxy-for-agen": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://agentwares-agentguard.vercel.app/api/mcp"]
}
}
}{
"mcpServers": {
"agentguard-policy-proxy-for-agen": {
"url": "https://agentwares-agentguard.vercel.app/api/mcp"
}
}
}{
"servers": {
"agentguard-policy-proxy-for-agen": {
"type": "http",
"url": "https://agentwares-agentguard.vercel.app/api/mcp"
}
}
}{
"context_servers": {
"agentguard-policy-proxy-for-agen": {
"url": "https://agentwares-agentguard.vercel.app/api/mcp"
}
}
}{
"mcpServers": {
"agentguard-policy-proxy-for-agen": {
"serverUrl": "https://agentwares-agentguard.vercel.app/api/mcp"
}
}
}{
"mcpServers": {
"agentguard-policy-proxy-for-agen": {
"url": "https://agentwares-agentguard.vercel.app/api/mcp"
}
}
}name: agentguard — policy proxy for agent tool calls
version: 0.0.1
schema: v1
mcpServers:
- name: agentguard — policy proxy for agent tool calls
type: streamable-http
url: https://agentwares-agentguard.vercel.app/api/mcp{
"mcpServers": {
"agentguard-policy-proxy-for-agen": {
"httpUrl": "https://agentwares-agentguard.vercel.app/api/mcp"
}
}
}{
"mcpServers": {
"agentguard-policy-proxy-for-agen": {
"type": "http",
"url": "https://agentwares-agentguard.vercel.app/api/mcp"
}
}
}{
"mcpServers": {
"agentguard-policy-proxy-for-agen": {
"url": "https://agentwares-agentguard.vercel.app/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fagentwares-agentguard.vercel.app%2Fapi%2Fmcp&type=streamable_http&id=agentguard-policy-proxy-for-agen&name=agentguard%20%E2%80%94%20policy%20proxy%20for%20agent%20tool%20calls
It answered our last check on 21 October 2026 in 183 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
6, as returned by the server's own tools/list on 13 September 2026: agentguard_create_proxy, agentguard_export_audit, agentguard_get_pricing, agentguard_get_run, agentguard_recommend_allowlist, agentguard_set_policy.
It answered our last check on 21 October 2026 in 183 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agentwares-agentguard.vercel.app/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.agentwares. Endpoint host: agentwares-agentguard.vercel.app. ARD identifier: urn:air:io.github.agentwares:mcp:agentguard-cloud.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.