@agentwares/agentguard 0.1.1 → 0.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +17 -17
- package/package.json +2 -2
- package/server.json +2 -2
package/README.md
CHANGED
|
@@ -40,7 +40,7 @@ agentguard is an MCP policy proxy for agents that touch production. It sits betw
|
|
|
40
40
|
|
|
41
41
|
No LLM calls. No phone-home. No account. MIT.
|
|
42
42
|
|
|
43
|
-
Two install paths, one policy engine: the **MCP proxy** (`npx @agentwares/agentguard`, stdio + Streamable HTTP, multiple upstreams) and the **SDK/middleware** ([`@agentwares/agentguard-sdk`](
|
|
43
|
+
Two install paths, one policy engine: the **MCP proxy** (`npx @agentwares/agentguard`, stdio + Streamable HTTP, multiple upstreams) and the **SDK/middleware** ([`@agentwares/agentguard-sdk`](https://github.com/agentwares/agentguard/tree/main/packages/agentguard-sdk#readme)) for OpenAI Agents SDK, LangChain or plain-function tools that never go through MCP.
|
|
44
44
|
|
|
45
45
|
## Install
|
|
46
46
|
|
|
@@ -137,19 +137,19 @@ Run identity: `X-Run-Id` header (HTTP) → `_meta.runId` on the call → session
|
|
|
137
137
|
|
|
138
138
|
## Commands
|
|
139
139
|
|
|
140
|
-
| Command | What it does
|
|
141
|
-
| ------------------------------------------------------------------------------------------------------------------------------- |
|
|
142
|
-
| `agentguard init [--client path] [--all] [--no-probe] [--mode enforce] [--undo]` | generate the policy, rewrite the client config (project-level by default)
|
|
143
|
-
| `agentguard proxy [--http --port 8788] [--agent name] [--run-id id] [--mode m]` | run the proxy (stdio default)
|
|
144
|
-
| `agentguard report [--run id \| --all] [--json]` | what this run did / would have destroyed / spent; where it was halted; chain status
|
|
145
|
-
| `agentguard diff [--run id]` | mutation diff of faked writes
|
|
146
|
-
| `agentguard verify [audit.jsonl]` | recompute the hash chain; exit 1 on the first break
|
|
147
|
-
| `agentguard status [--run id]` | counters vs caps, kill state, pending approvals, running HTTP proxy
|
|
148
|
-
| `agentguard tools [--json]` | every exposed tool with class, verb, upstream and the reason
|
|
149
|
-
| `agentguard kill [reason]` / `agentguard resume` | halt everything now / clear it
|
|
150
|
-
| `agentguard approvals [--all]` / `approve <id>` / `deny <id> [--note …]` | the approval queue
|
|
151
|
-
| `agentguard key create <agent> [--allow p]… [--deny p] [--writes n] [--spend n] [--mode m]` / `key list` / `key revoke <agent>` | scoped credentials
|
|
152
|
-
| `agentguard permission-diff [--base ref] [--head ref] [--fail-on-widen]` | which config changes widen agent permissions (also a [GitHub Action](
|
|
140
|
+
| Command | What it does |
|
|
141
|
+
| ------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
|
|
142
|
+
| `agentguard init [--client path] [--all] [--no-probe] [--mode enforce] [--undo]` | generate the policy, rewrite the client config (project-level by default) |
|
|
143
|
+
| `agentguard proxy [--http --port 8788] [--agent name] [--run-id id] [--mode m]` | run the proxy (stdio default) |
|
|
144
|
+
| `agentguard report [--run id \| --all] [--json]` | what this run did / would have destroyed / spent; where it was halted; chain status |
|
|
145
|
+
| `agentguard diff [--run id]` | mutation diff of faked writes |
|
|
146
|
+
| `agentguard verify [audit.jsonl]` | recompute the hash chain; exit 1 on the first break |
|
|
147
|
+
| `agentguard status [--run id]` | counters vs caps, kill state, pending approvals, running HTTP proxy |
|
|
148
|
+
| `agentguard tools [--json]` | every exposed tool with class, verb, upstream and the reason |
|
|
149
|
+
| `agentguard kill [reason]` / `agentguard resume` | halt everything now / clear it |
|
|
150
|
+
| `agentguard approvals [--all]` / `approve <id>` / `deny <id> [--note …]` | the approval queue |
|
|
151
|
+
| `agentguard key create <agent> [--allow p]… [--deny p] [--writes n] [--spend n] [--mode m]` / `key list` / `key revoke <agent>` | scoped credentials |
|
|
152
|
+
| `agentguard permission-diff [--base ref] [--head ref] [--fail-on-widen]` | which config changes widen agent permissions (also a [GitHub Action](https://github.com/agentwares/agentguard/tree/main/permission-diff)) |
|
|
153
153
|
|
|
154
154
|
HTTP control endpoints (token in `.agentguard/http.json`): `GET /health`, `GET /status?run=`, `POST /kill`, `POST /resume`, `GET|POST /approve/:id`, `/deny/:id`, `GET /approvals`.
|
|
155
155
|
|
|
@@ -183,6 +183,6 @@ node dist/cli.js report && node dist/cli.js diff && node dist/cli.js verify
|
|
|
183
183
|
|
|
184
184
|
## Related
|
|
185
185
|
|
|
186
|
-
- [`@agentwares/agentguard-sdk`](
|
|
187
|
-
- [`@agentwares/agentguard-core`](
|
|
188
|
-
- [permission-diff GitHub Action](
|
|
186
|
+
- [`@agentwares/agentguard-sdk`](https://github.com/agentwares/agentguard/tree/main/packages/agentguard-sdk#readme) — the same engine for OpenAI Agents SDK / LangChain / plain functions, plus the guarded `fetch` for LLM spend.
|
|
187
|
+
- [`@agentwares/agentguard-core`](https://github.com/agentwares/agentguard/tree/main/packages/agentguard-core#readme) — the Web-standard policy engine (bring your own stores).
|
|
188
|
+
- [permission-diff GitHub Action](https://github.com/agentwares/agentguard/tree/main/permission-diff) — comments on PRs that widen `agentguard.yaml`, `.claude/settings.json` or `mcp.json`.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@agentwares/agentguard",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.2",
|
|
4
4
|
"description": "MCP policy proxy for AI agents: hard spend limits, destructive-action gating with approvals, a kill switch, scoped credentials, dry-run writes with mutation diffs, loop breaker, blast-radius caps and a hash-chained audit log. No LLM calls, no phone-home, no account.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"type": "module",
|
|
@@ -52,7 +52,7 @@
|
|
|
52
52
|
"@modelcontextprotocol/sdk": "^1.30.0",
|
|
53
53
|
"yaml": "^2.9.0",
|
|
54
54
|
"zod": "^4.5.4",
|
|
55
|
-
"@agentwares/agentguard-core": "^0.1.
|
|
55
|
+
"@agentwares/agentguard-core": "^0.1.2"
|
|
56
56
|
},
|
|
57
57
|
"devDependencies": {
|
|
58
58
|
"tsx": "^4.23.13",
|
package/server.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
|
|
3
3
|
"name": "io.github.agentwares/agentguard",
|
|
4
4
|
"description": "MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.",
|
|
5
|
-
"version": "0.1.
|
|
5
|
+
"version": "0.1.2",
|
|
6
6
|
"repository": {
|
|
7
7
|
"url": "https://github.com/agentwares/agentguard",
|
|
8
8
|
"source": "github",
|
|
@@ -15,7 +15,7 @@
|
|
|
15
15
|
"registryType": "npm",
|
|
16
16
|
"registryBaseUrl": "https://registry.npmjs.org",
|
|
17
17
|
"identifier": "@agentwares/agentguard",
|
|
18
|
-
"version": "0.1.
|
|
18
|
+
"version": "0.1.2",
|
|
19
19
|
"runtimeHint": "npx",
|
|
20
20
|
"transport": {
|
|
21
21
|
"type": "stdio"
|