@automatebrowser/mcp 0.3.0

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.
@@ -0,0 +1,17 @@
1
+ {
2
+ "name": "automatebrowser",
3
+ "owner": {
4
+ "name": "AutomateBrowser",
5
+ "url": "https://farazpawle.github.io/automatebrowser/"
6
+ },
7
+ "description": "AutomateBrowser — drive your real, logged-in browser from your editor.",
8
+ "plugins": [
9
+ {
10
+ "name": "automate-browser",
11
+ "source": "./",
12
+ "description": "The MCP server's 46 browser tools plus the automate-browser skill: tab ownership, page interaction, extraction, sessions, capture and troubleshooting.",
13
+ "homepage": "https://farazpawle.github.io/automatebrowser/",
14
+ "license": "MIT"
15
+ }
16
+ ]
17
+ }
@@ -0,0 +1,10 @@
1
+ {
2
+ "name": "automate-browser",
3
+ "displayName": "AutomateBrowser",
4
+ "version": "0.3.0",
5
+ "description": "Drive your real, logged-in browser from your editor — 46 tools, plus the automate-browser skill covering tab ownership, page interaction, extraction, sessions, capture and troubleshooting.",
6
+ "author": {
7
+ "name": "AutomateBrowser"
8
+ },
9
+ "keywords": ["browser", "automation", "mcp", "chrome", "scraping"]
10
+ }
package/CHANGELOG.md ADDED
@@ -0,0 +1,167 @@
1
+ # Changelog
2
+
3
+ Notable changes to `@automatebrowser/mcp`. Format follows
4
+ [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); versions follow
5
+ [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
6
+
7
+ **Nothing has been published to npm under this name yet.** `0.3.0` is cut and verified and is the
8
+ version the first publish will carry; `0.2.0` was cut the same way on 2026-08-26 and held. Every
9
+ version before those belongs to `@browsermcp/mcp`, the project this one was extracted from. That
10
+ lineage is kept below rather than hidden, because an installed copy that predates the rebrand is
11
+ still out there and its users need somewhere to see what changed. Until that publish happens,
12
+ `[0.3.0]` is what you get by building from source.
13
+
14
+ Dates are the date of the work, not of a release.
15
+
16
+ ## [Unreleased]
17
+
18
+ Nothing yet. `0.3.0` was cut on 2026-09-17, and work after it lands here.
19
+
20
+ ## [0.3.0] — 2026-09-17
21
+
22
+ Cut and verified, **not yet published** — the version the first publish will carry. This is the bulk
23
+ of the current product, substantially more than `[0.2.0]` contains, so it is this section and not
24
+ that one that describes what a user actually receives. `[0.2.0]` stays rather than being absorbed,
25
+ because it names a real cut that the link block below points at.
26
+
27
+ ### Added
28
+
29
+ - **A terminal client.** `automate-browser` drives the same browser from a shell, joining the same
30
+ relay mesh as any connected editor.
31
+ - **Performance answers, not just numbers.** Core Web Vitals (LCP, FCP, CLS, INP) rated against
32
+ Google's thresholds, the long tasks that blocked the main thread, a breakdown of where the LCP time
33
+ actually went, and re-analysis of a saved trace with no browser attached. Field data from real
34
+ visitors where an API key is supplied.
35
+ - **A JS heap sampler** that reports the trend over a window, with no debugger and no banner.
36
+ - **Cross-origin iframes** can be driven without the debugger.
37
+ - **`browser_eval` takes a function plus element refs**, so a script can act on elements already
38
+ found rather than re-querying the DOM.
39
+ - **`browser_emulate`** — location, user agent, extra headers, colour scheme and a responsive set.
40
+ - **`browser_downloads`**, **`browser_issues`**, element and WebP screenshots, coordinate clicking
41
+ for targets no ref can address, and a strip of stills for showing a person what happened.
42
+ - **`include`** attaches the fresh console or network state to the same reply as the action, removing
43
+ a round-trip after every navigation.
44
+ - **A structured error taxonomy** — codes, recovery hints and a retryable flag, delivered both as
45
+ prose and as `structuredContent`.
46
+ - **An action audit log**, with secrets redacted before they are written.
47
+ - **Origin allow/deny lists**, a sensitive-value tier, and a read-only mode.
48
+ - **A remote browser** on another machine, and whole-browser proxy control.
49
+ - **A shipped agent skill** with seven references, installable as a plugin, plus the manifests that
50
+ make it discoverable.
51
+ - **A landing page** and an out-of-date-install check.
52
+ - **A file-path sandbox** over the client's MCP roots, a pre-flight on write targets so a bad path
53
+ fails before the work rather than after it, and `AUTOMATE_BROWSER_WORKSPACE` for the many clients
54
+ that send no roots at all.
55
+ - **An opt-in switch to forbid agent-written JavaScript** entirely.
56
+ - **A ceiling on inline screenshot size**, so a high-density display does not silently cost three
57
+ times the context for the same picture.
58
+ - **The first unit suite** — no browser, no relay, no model — and a real-Chrome integration suite.
59
+ - **A memory profile of the relay** in CI. It is the one process meant to outlive its clients, and
60
+ nothing watched it before.
61
+ - **Recovery is visible rather than inferred.** When the connection to the browser drops and comes
62
+ back, the existing diagnostics say so, instead of leaving an agent to work it out from a failure.
63
+ - **A real-browser regression suite that runs on two browsers**, covering two profiles driven at
64
+ once, actions two frames deep, and partial form fills — with every failure reporting the scenario,
65
+ the page, the browser and the two commands that reproduce it.
66
+ - **The extension's command definitions are generated from the server's schemas**, so the two halves
67
+ of the wire protocol can no longer drift apart without a gate noticing.
68
+
69
+ ### Changed
70
+
71
+ - **The tool list costs 9,435 tokens per request instead of 10,469 — 9.9% less, with nothing
72
+ removed.** Every MCP client re-sends every tool schema on every message, so this is the one cost a
73
+ user pays for doing nothing. Measured across 348 real Claude Code sessions and 89,258 model turns it
74
+ came to **934 million tokens, 80% of everything this server has ever cost a context** — 92 million of
75
+ it in 36 sessions that never called a browser tool at all. Two cuts, neither touching a tool, a
76
+ parameter or a validation rule: the `$schema` dialect key that `zod-to-json-schema` stamps on all 46
77
+ input and 9 output schemas and the protocol never reads (770 tokens, stripped at the wire by
78
+ `wireSchema`), and three parameter descriptions that were being restated on up to six tools each —
79
+ `includeSnapshot` cost 29 tokens six times over. Those explanations moved to the shipped skill's
80
+ `page-interaction` reference, read once per **task** rather than once per **turn**. Profile ceilings
81
+ in `scripts/count-tokens.mjs` were lowered to match, the first time they have ever moved down:
82
+ full 9,580, core 4,210, slim 1,855.
83
+ - **`browser_screenshot` now says what a picture costs**, because the same scan found screenshots to be
84
+ **half** this server's footprint on a heavy browser day: 249 inline captures averaging ~1,531 tokens
85
+ each, and an MCP result is re-read on every later turn until the session ends. Only 20 of 445
86
+ captures scoped themselves to one element. The tool's description and the skill's
87
+ `capture-and-diagnostics` reference now point at `ref` for a single element, and at `browser_eval` /
88
+ `browser_find` for a value that needs no picture at all. Deliberately spent 30 of the tokens saved
89
+ above to say it.
90
+ - **The agent drives only a tab it owns**, and works in the background. It no longer takes over
91
+ whatever tab the user happens to be looking at.
92
+ - **Element refs survive a re-render**, via stable signatures rather than positional indexes.
93
+ - **Interactions wait for the element to be ready** and for the DOM to settle afterwards.
94
+ - **Transient failures retry automatically**, gated on whether the tool is idempotent.
95
+ - **Five outcomes are told apart, instead of being squeezed through one error flag.** A form fill
96
+ that lands two fields of three now reports itself as partial rather than as a clean success, and a
97
+ reply lost on the way back is no longer advertised as safe to retry — for a click, that advice was
98
+ "click twice". The audit log records which of the five actually happened.
99
+ - **Cookie, storage and header values are redacted by default**; ask for them explicitly.
100
+ - **The console and network lists are paged**, newest first.
101
+ - Snapshots can be lean, full, or written to a file.
102
+
103
+ ### Fixed
104
+
105
+ - A reconnecting extension no longer orphans the agent's tabs.
106
+ - Background screenshot captures no longer hang; a stall is bounded and named.
107
+ - Advanced mode no longer reshapes a click, and a trusted Enter submits forms.
108
+ - Uncaught page errors keep their stacks.
109
+ - The network log survives a service-worker eviction.
110
+ - Two long-lived logs moved out of the swept temp directory.
111
+ - Dependency advisories pinned so `npm audit --omit=dev` passes.
112
+ - Retrying an action can no longer land on a different browser or a different tab than the one it
113
+ started against.
114
+ - Passing an address to a tool no longer sidesteps the page restrictions that were meant to judge it.
115
+ - A failed address check no longer skips read-only protection entirely.
116
+ - Invalid response options are rejected **before** the action runs, not after it has already happened.
117
+ - Network restrictions reach every connected browser, not only the first one to connect.
118
+ - One failed reconnection attempt no longer ends automatic recovery for the rest of the session.
119
+ - Element references from different embedded pages no longer resolve against the wrong page, and a
120
+ form fill or clear aimed at an embedded page reaches it rather than the page around it.
121
+ - A doubly-nested frame is no longer listed twice under a reference that does not work.
122
+ - Reloading a page now waits for the new document rather than reporting the one it replaced.
123
+ - Setting a radio button to "false" no longer switches it on.
124
+ - The schema size budget is enforced for **every** tool profile. It had been measuring only the
125
+ default one, so two of the three had been quietly over their ceiling for two weeks.
126
+
127
+ ### Removed
128
+
129
+ - **`acceptInsecureCerts`.** It never worked on any build — Chrome does not expose the certificate
130
+ domain to extensions — so it could only ever return an error, charged against every request in
131
+ every editor. Passing it now fails by name rather than being quietly ignored, and says what to do
132
+ instead: start the browser with `--ignore-certificate-errors`, or click through the warning page
133
+ once, which is remembered for that host for the session. Everything else works against such a site
134
+ normally either way.
135
+
136
+ ## [0.2.0] — 2026-08-26
137
+
138
+ Cut and verified, **not published**. The first version under the AutomateBrowser name.
139
+
140
+ ### Added
141
+
142
+ - **A singleton relay.** One process owns the port; every editor connects to it as a controller, so
143
+ several editors share one browser instead of fighting over a port.
144
+ - **Per-tab ownership** — two editors can drive two tabs of the same browser at once, with soft-claim
145
+ leases, lease-loss notifications and a roster in the extension popup.
146
+ - **A debugger-free extension**, rewritten with an always-on connection, so the yellow automation
147
+ banner is gone for everything but the opt-in CDP features.
148
+ - **Tool profiles** (`full`, `core`, `slim`) behind a registry, a per-call timeout, a per-controller
149
+ send queue, and a console-error footer on mutating calls.
150
+ - **A tool-schema token budget** and a release verification gate, both enforced in CI.
151
+ - **A generated tool reference** in the README, written from the live schemas.
152
+ - **Auto-recovery** when the extension's service worker is asleep.
153
+ - A warning when the relay is a different build from the server talking to it.
154
+
155
+ ### Changed
156
+
157
+ - Renamed from `@browsermcp/mcp` to `@automatebrowser/mcp`; de-branded throughout.
158
+
159
+ ## [0.1.3] — 2025-04-25
160
+
161
+ The last release of `@browsermcp/mcp`, the upstream project this was extracted from, published to npm
162
+ under that name. `0.1.0` through `0.1.2` precede it; this repository begins at the point the server
163
+ was extracted from that monorepo on 2025-03-27, and no history before that is reproduced here.
164
+
165
+ [Unreleased]: https://github.com/farazpawle/automatebrowser/compare/v0.3.0...HEAD
166
+ [0.3.0]: https://github.com/farazpawle/automatebrowser/compare/cf28a4b...v0.3.0
167
+ [0.2.0]: https://github.com/farazpawle/automatebrowser/commit/cf28a4b
package/LICENSE ADDED
@@ -0,0 +1,202 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Portions Copyright (c) Microsoft Corporation.
190
+ Portions Copyright 2017 Google Inc.
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.