agentguard — policy proxy for agent tool calls is an MCP server published by io.github.agentwares, hosted at agentwares-agentguard.vercel.app. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 7 tools, including okgate_get_pricing, okgate_spend_report, okgate_create_proxy, okgate_set_policy, okgate_get_run.
Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.
107 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Machine-readable pricing for okgate hosted: bands (Starter/Pro/Team) with included tool calls per month, the 80% soft alert and 150% hard stop, features, the free trial allowance, `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 — and `one_time`: reports a person pays for once on Stripe Checkout, such as the $49 EU AI Act Article 50 readiness report. Same data as /pricing.json.
No parameters.
{
"name": "okgate_get_pricing",
"description": "Machine-readable pricing for okgate hosted: bands (Starter/Pro/Team) with included tool calls per month, the 80% soft alert and 150% hard stop, features, the free trial allowance, `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 — and `one_time`: reports a person pays for once on Stripe Checkout, such as the $49 EU AI Act Article 50 readiness report. Same data as /pricing.json.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
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 okgate 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 `okgate_get_pricing` instead.
| Parameter | Type | Description |
|---|---|---|
| log * | string | The log itself, verbatim — JSON, JSONL or CSV. Not a path and not a URL: this server does not fetch anything. |
| 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 to read it. |
{
"name": "okgate_spend_report",
"description": "Read an agent log and report what it spent: totals, calls by tool and by class, estimated\ndollars by rail, loops, the largest single run, and — for every overspend — the okgate\nband whose cap would have stopped it, the exact cap, and the call that would have tripped\nit.\n\nNeeds no account and no key. The log is read in the request and discarded; nothing is\nstored. Accepts an agentwares audit export (`agentwares.audit/v1`), a Claude Code session\n`.jsonl`, or a CSV/JSONL of tool calls with any of `tool`, `ts`, `class`, `amount_usd`,\n`rail`, `run_id`, `model`, `input_tokens`, `output_tokens`.\n\nCaps come from the proxy's own default policy, so a band named here refuses exactly what\nit says it refuses. Buying that band is a checkout a person completes; the calls-only\npurchase an unattended agent can complete is in `okgate_get_pricing` instead.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"log"
],
"properties": {
"log": {
"type": "string",
"minLength": 1,
"description": "The log itself, verbatim — JSON, JSONL or CSV. Not a path and not a URL: this server does not fetch anything."
},
"detail": {
"enum": [
"concise",
"full"
],
"type": "string",
"description": "`concise` (default) returns the totals, the top ten tools, the rails, the loops and every overspend. `full` adds the complete per-tool breakdown and the window. Ask for `full` only when you are going to read it."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Create a hosted okgate proxy in front of an MCP server. Returns the proxy id, the per-customer MCP URL and the proxy key (shown once). Point your agent's MCP client at the URL with `Authorization: Bearer <key>`. Requires an account key.
| Parameter | Type | Description |
|---|---|---|
| mode | string | dry-run records what the policy would have blocked and lets every call through; enforce actually blocks. Start in dry-run. |
| slug * | string | short name, a-z 0-9 - |
| upstreamUrl * | string | Streamable HTTP URL of the MCP server to protect |
| upstreamName | string | name used to namespace tools when you add more upstreams later |
{
"name": "okgate_create_proxy",
"description": "Create a hosted okgate proxy in front of an MCP server. Returns the proxy id, the per-customer MCP URL and the proxy key (shown once). Point your agent's MCP client at the URL with `Authorization: Bearer <key>`. Requires an account key.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"slug",
"upstreamUrl"
],
"properties": {
"mode": {
"enum": [
"dry-run",
"enforce"
],
"type": "string",
"default": "dry-run",
"description": "dry-run records what the policy would have blocked and lets every call through; enforce actually blocks. Start in dry-run."
},
"slug": {
"type": "string",
"maxLength": 40,
"minLength": 2,
"description": "short name, a-z 0-9 -"
},
"upstreamUrl": {
"type": "string",
"format": "uri",
"description": "Streamable HTTP URL of the MCP server to protect"
},
"upstreamName": {
"type": "string",
"maxLength": 32,
"minLength": 1,
"description": "name used to namespace tools when you add more upstreams later"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| proxyId * | string | the proxy id returned by okgate_create_proxy |
| policyYaml * | string | the complete policy document; it replaces the current one rather than merging |
{
"name": "okgate_set_policy",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"proxyId",
"policyYaml"
],
"properties": {
"proxyId": {
"type": "string",
"minLength": 6,
"description": "the proxy id returned by okgate_create_proxy"
},
"policyYaml": {
"type": "string",
"maxLength": 64000,
"minLength": 1,
"description": "the complete policy document; it replaces the current one rather than merging"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}The incident-shaped report for one run: counts (calls, reads, writes, faked, blocked, spend), the call timeline with decisions, dry-run mutations (what would have changed), ledger entries and the audit-chain verification. Requires an account key.
| Parameter | Type | Description |
|---|---|---|
| runId * | string | the X-Run-Id your agent sent with the calls; one run is one agent session |
| proxyId * | string | the proxy id returned by okgate_create_proxy |
{
"name": "okgate_get_run",
"description": "The incident-shaped report for one run: counts (calls, reads, writes, faked, blocked, spend), the call timeline with decisions, dry-run mutations (what would have changed), ledger entries and the audit-chain verification. Requires an account key.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"proxyId",
"runId"
],
"properties": {
"runId": {
"type": "string",
"minLength": 1,
"description": "the X-Run-Id your agent sent with the calls; one run is one agent session"
},
"proxyId": {
"type": "string",
"minLength": 6,
"description": "the proxy id returned by okgate_create_proxy"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| runId * | string | the X-Run-Id your agent sent with the calls; one run is one agent session |
| proxyId * | string | the proxy id returned by okgate_create_proxy |
{
"name": "okgate_export_audit",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"proxyId",
"runId"
],
"properties": {
"runId": {
"type": "string",
"minLength": 1,
"description": "the X-Run-Id your agent sent with the calls; one run is one agent session"
},
"proxyId": {
"type": "string",
"minLength": 6,
"description": "the proxy id returned by okgate_create_proxy"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Least-privilege recommendation from the proxy's recorded calls: the minimal tool allowlist, argument keys used per tool, and the upstream tools never used (remove them first). No LLM call here; apply it in the dashboard. Requires an account key.
| Parameter | Type | Description |
|---|---|---|
| proxyId * | string | the proxy id returned by okgate_create_proxy |
{
"name": "okgate_recommend_allowlist",
"description": "Least-privilege recommendation from the proxy's recorded calls: the minimal tool allowlist, argument keys used per tool, and the upstream tools never used (remove them first). No LLM call here; apply it in the dashboard. Requires an account key.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"proxyId"
],
"properties": {
"proxyId": {
"type": "string",
"minLength": 6,
"description": "the proxy id returned by okgate_create_proxy"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}okgate hosted: a policy proxy between agents and their MCP servers (loop breaker, caps, dry-run, kill switch, hash-chained audit). okgate_spend_report and okgate_get_pricing need no key: post an agent log to the first and it names the band whose cap would have stopped each overspend, which is the cheapest way to find out whether this is worth paying for. The other tools need an account key (Authorization: Bearer ak_...); POST https://agentwares-agentguard.vercel.app/api/v1/signup with {"accept_terms": true} to get one and start the free trial, with no human and no card. A browser dashboard exists at https://agentwares-agentguard.vercel.app/dashboard but is not required. Create a proxy, point the agent at the returned mcpUrl with its key, then read runs with okgate_get_run. okgate was agentguard until 8 October 2026: the agentguard_* tool names still run their okgate_* twins until 2027-01-15.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.