@gaiventures/pilotfish-mcp-managed 0.1.19 → 0.1.21

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.
Files changed (3) hide show
  1. package/README.md +18 -12
  2. package/cli.js +1 -1
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -10,9 +10,10 @@ files.
10
10
  Works with Claude Code, Claude.ai, Claude Desktop, Codex CLI, Cursor, VS Code and any other
11
11
  [MCP](https://modelcontextprotocol.io) client.
12
12
 
13
- > **You need a pilotfish account to use this.** [Sign up](https://pilotfish.gai.ventures/signup), add credits
14
- > (from $10), and create an MCP key under **Connect an agent**. Claude.ai, Claude Desktop and Claude Code can sign
15
- > in with OAuth instead of a key. See [Get started](#get-started).
13
+ > **You need a pilotfish account to use this.** [Sign up](https://pilotfish.gai.ventures/signup) and add credits
14
+ > (from $10) to your organization. Then sign in from your client (OAuth: it acts as you, with your saved logins), or
15
+ > use one of your organization's API keys, which its admins create under **Org settings → API keys**. See
16
+ > [Get started](#get-started).
16
17
 
17
18
  ## Why managed
18
19
 
@@ -36,8 +37,9 @@ Prefer to drive a browser on your own computer, for free? Use the local
36
37
 
37
38
  1. **Sign up** at [pilotfish.gai.ventures/signup](https://pilotfish.gai.ventures/signup) with your Google account.
38
39
  2. **Add credits.** Pay as you go, from $10, under **Usage → Credits**.
39
- 3. **Create an MCP key** under **Connect an agent** in the app (`https://pilotfish.gai.ventures/connect`). Skip
40
- this if your client signs in with OAuth (Claude.ai, Claude Desktop, Claude Code).
40
+ 3. **Sign in, or get an API key.** Clients that sign in with OAuth (Claude.ai, Claude Desktop, Claude Code and most
41
+ others) need no key. Otherwise ask an admin of your organization for one of its API keys: they create them under
42
+ **Org settings → API keys** (`https://pilotfish.gai.ventures/org?view=keys`).
41
43
  4. **Connect your agent** with the steps below.
42
44
 
43
45
  ## Connect
@@ -108,11 +110,15 @@ PILOTFISH_KEY=pf_YOUR_KEY npx -y @gaiventures/pilotfish-mcp-managed --check
108
110
 
109
111
  In Windows PowerShell: `$env:PILOTFISH_KEY = "pf_YOUR_KEY"; npx -y @gaiventures/pilotfish-mcp-managed --check`.
110
112
 
111
- ## MCP keys
113
+ ## API keys
112
114
 
113
- Create keys under **Connect an agent** in the app (`https://pilotfish.gai.ventures/connect`). Make one per agent;
114
- each can be shown again, copied, rotated or revoked there. A key acts as you and stops working if you leave your
115
- organization. Clients that sign in with OAuth (Claude.ai, Claude Desktop, Claude Code) need no key.
115
+ API keys belong to your organization. Its admins create them under **Org settings → API keys** in the app
116
+ (`https://pilotfish.gai.ventures/org?view=keys`), where each can be shown again, copied, rotated or revoked. A key runs
117
+ tasks for the organization, paid from its credits, one task at a time, and with no one's saved logins; anyone given
118
+ one can use it, so rotate a key when someone leaves. Admins can give a key an allowance (a spending limit, with an
119
+ optional auto reload): once it is used, its tasks are refused (`allocation_used`) or pause until it is raised. Each
120
+ key's page in the app shows what it spent, its tasks through the MCP and the API, and its sessions. To use your own saved logins, sign in from your client (OAuth)
121
+ instead: no key needed.
116
122
 
117
123
  ## Tools
118
124
 
@@ -122,7 +128,7 @@ organization. Clients that sign in with OAuth (Claude.ai, Claude Desktop, Claude
122
128
  | `get_job` `{id, wait_seconds?}` | A job's status, open question and its answer link, result, cost so far, live-view link and files. Can wait for the job to finish or need you. A finished job reads `SUCCESS`, `PARTLY DONE` or `NOT DONE`; one that did not pass lists what of the task is done, what is not (with the evidence for each) and why it stopped. |
123
129
  | `get_file` `{id, file_id}` | One of the session's files, attached or downloaded. Up to 5 MB comes back in the result; larger files are linked. |
124
130
  | `list_jobs` `{status?, limit?}` | Your recent jobs with their cost; `[replay]` marks recorded ones. |
125
- | `follow_up` `{id, text, model?, files?, wait?}` | Carry on in the same session: same browser while it is kept, same sign-ins, what earlier turns found. |
131
+ | `follow_up` `{id, text, model?, region?, files?, wait?}` | Carry on in the same session: same browser while it is kept, same sign-ins, what earlier turns found. `region` runs the turn from another country (a site not reachable from the last one): it starts again in a new browser session there. |
126
132
  | `rerun_job` `{id, wait?}` | Run the same task with the same settings again. |
127
133
  | `answer_job` `{id, question_id, answer}` | Answer a job's question: yes, no, done, cancel or text. The id is in the job's `Question …` line, which also says what answer it takes. Codes and passwords go on the answer page, never here. |
128
134
  | `message_job` `{id, text}` | Pass on what the person says while a job runs ("take the cheaper one", a detail it asked for). It reads the message before its next step; the person's newest words win over the task; sent while the job waits on a question, it answers it. |
@@ -137,7 +143,7 @@ organization. Clients that sign in with OAuth (Claude.ai, Claude Desktop, Claude
137
143
  | `delete_session` `{id}` | Delete a session from your history: it no longer shows or opens anywhere; its record and cost are kept for billing. Logins, saved tasks and spending stay. |
138
144
  | `list_logins` | Sites you have saved logins for, with what is stored and each site's settings. Never a password or code. Logins are added in the app. |
139
145
  | `get_settings` / `update_site_settings` `{site, residential?, stealth?, solve?}` | Your sites and their settings: residential IP (auto, always or never), stealth and CAPTCHA solving. |
140
- | `get_usage` `{days?}` | Your credit balance, this month's spending against your limits, and spending by category and model. |
146
+ | `get_usage` `{days?}` | Your organization's credits (your allowance and whether it is fine, low or out, for a member), this month's spending against its monthly limit, and spending by category and model. |
141
147
 
142
148
  ## Tasks that name no site
143
149
 
@@ -183,7 +189,7 @@ Only for this package. Clients that connect to the URL need none.
183
189
 
184
190
  | Variable | Default | Meaning |
185
191
  | --- | --- | --- |
186
- | `PILOTFISH_KEY` | | Your MCP key (`pf_…`). Required. |
192
+ | `PILOTFISH_KEY` | | One of your organization's API keys (`pf_…`). Required. |
187
193
  | `PILOTFISH_URL` | `https://pilotfish-be.gai.ventures` | The pilotfish API, or its `/mcp` URL. |
188
194
 
189
195
  ## License
package/cli.js CHANGED
@@ -10,7 +10,7 @@ import { Client } from "@modelcontextprotocol/sdk/client/index.js";
10
10
  import { isJSONRPCRequest, isJSONRPCResultResponse } from "@modelcontextprotocol/sdk/types.js";
11
11
 
12
12
  // packages/mcp-managed/dist/version.js
13
- var VERSION = true ? "0.1.19" : "0.0.0-dev";
13
+ var VERSION = true ? "0.1.21" : "0.0.0-dev";
14
14
 
15
15
  // packages/mcp-managed/dist/bridge.js
16
16
  var DEFAULT_URL = "https://pilotfish-be.gai.ventures";
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@gaiventures/pilotfish-mcp-managed",
3
- "version": "0.1.19",
3
+ "version": "0.1.21",
4
4
  "description": "Whole browser tasks done in pilotfish's cloud for any MCP agent, signed in with your saved logins. mcprush.com-37c48d491684ec6011385ea5",
5
5
  "license": "MIT",
6
6
  "type": "module",