@gaiventures/pilotfish-mcp-managed 0.1.36 → 0.1.38

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 +31 -33
  2. package/cli.js +1 -1
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -2,23 +2,29 @@
2
2
 
3
3
  [![npm](https://img.shields.io/npm/v/@gaiventures/pilotfish-mcp-managed)](https://www.npmjs.com/package/@gaiventures/pilotfish-mcp-managed)
4
4
 
5
- [![pilotfish (managed) MCP server](https://mcprush.com/badge/pilotfish-managed-mcp/card.svg)](https://mcprush.com/to/pilotfish-managed-mcp?ref=badge)
5
+ An MCP server that does whole browser tasks for your AI agent. Your agent says what it wants done ("download last
6
+ month's invoices from our AWS billing console", "pull the risk factors from Apple's latest 10-K on SEC EDGAR").
7
+ [pilotfish](https://pilotfish.gai.ventures) does it in its cloud browser, signed in with your saved logins, and
8
+ returns the answer and any files.
6
9
 
7
- Hand whole browser tasks to [pilotfish](https://pilotfish.gai.ventures) from any AI agent. Your agent says what it
8
- wants done ("download last month's invoices from our AWS billing console", "pull the risk factors from Apple's latest
9
- 10-K on SEC EDGAR"). pilotfish does it in a cloud browser and returns the answer and any files.
10
+ For people and teams using Claude Code, Claude.ai, Claude Desktop, Codex CLI, Cursor, VS Code or another
11
+ [MCP](https://modelcontextprotocol.io) client, and for products that run browser tasks for their own users. It is a
12
+ paid service: you need a pilotfish account ([sign up with Google](https://pilotfish.gai.ventures/signup)), and tasks
13
+ are paid from your organization's credits.
10
14
 
11
- It works with Claude Code, Claude.ai, Claude Desktop, Codex CLI, Cursor, VS Code and any other
12
- [MCP](https://modelcontextprotocol.io) client. Clients that take a URL connect to `https://pilotfish-be.gai.ventures/mcp`
13
- directly. This package is a small relay for clients that can only start a local (stdio) server.
15
+ ```sh
16
+ claude mcp add --transport http pilotfish https://pilotfish-be.gai.ventures/mcp
17
+ ```
14
18
 
15
- > **You need a pilotfish account.** [Sign up with Google](https://pilotfish.gai.ventures/signup): you name your
16
- > organization and become its admin. Or accept an invitation to join someone else's. Tasks are paid from the
17
- > organization's credits.
19
+ Then run `/mcp` in Claude Code and sign in. Any client that takes a URL connects to
20
+ `https://pilotfish-be.gai.ventures/mcp`, by signing in or with an API key. This npm package is a small relay for clients that can only
21
+ start a local (stdio) server: `npx -y @gaiventures/pilotfish-mcp-managed` (setup under "Connect" below).
18
22
 
19
23
  Want a browser on your own computer for free, driven by your agent's own model, with no account? Use the open
20
24
  [`@gaiventures/pilotfish-mcp`](https://www.npmjs.com/package/@gaiventures/pilotfish-mcp) instead.
21
25
 
26
+ [![pilotfish (managed) MCP server](https://mcprush.com/badge/pilotfish-managed-mcp/card.svg)](https://mcprush.com/to/pilotfish-managed-mcp?ref=badge)
27
+
22
28
  ## Why managed
23
29
 
24
30
  - **One call per task.** pilotfish plans and runs the task on its own models and checks the answer. Your agent spends
@@ -182,7 +188,10 @@ make one in the app's **Org settings → API keys** and pick the project **Perso
182
188
  Personal project, with your own saved logins, and only you can see or manage it. Admins (the primary admin included)
183
189
  can always do this; a member can once an admin turns on **Allow personal API keys** on the member's page (turning it
184
190
  off revokes their keys at once), and then finds their keys on their Org settings page. Admins see each person's key
185
- usage, never the keys. Most people need no key at all: Claude Code, the Claude app, Cursor and VS Code sign in, and
191
+ usage, never the keys. Every key, personal ones included, can have a spending limit of its own: admins set it on the
192
+ key's page (a member sees the limit and how much of it is used, and asks an admin to change it). At the limit, new
193
+ tasks with that key are refused and running ones pause until it is raised; `get_usage` with a personal key says what
194
+ is left of it. Most people need no key at all: Claude Code, the Claude app, Cursor and VS Code sign in, and
186
195
  a client that starts this package signs in once with `login` (see **Sign in a terminal**).
187
196
 
188
197
  ## Projects
@@ -397,30 +406,19 @@ machine running it stopped or was replaced says `PAUSED` (`machine_lost`, `machi
397
406
  does: `follow_up` with the text "Continue" picks it up from where it left off, in a new browser. A job whose machine
398
407
  stopped before it did anything on a site starts again by itself, once.
399
408
 
400
- ## Whole tasks or steps?
409
+ ## Writing tasks
401
410
 
402
411
  Send the whole web task in one `browser_task`, however many sites and steps it has: "find the cheapest return flight
403
- on MakeMyTrip, then book a hotel near the beach for those dates on Booking.com", "read my last Swiggy order and add it
404
- to my Splitwise group". pilotfish splits it into parts, asks for every sign-in it needs at the start, carries what
405
- each site gives to the next and checks the end result. Split it yourself only where a step is not browser work (your
406
- own code, files, an API) or needs your own decision between steps; then send each browser step with the values it
407
- needs written in, or use `follow_up` to stay in the same browser and sign-ins. Say in the task what may be completed
408
- without asking ("pay with my saved card", "go ahead and submit"); anything else that is final waits for a yes.
409
-
410
- ## Tasks that name no site
411
-
412
- Send them as they are: "the best free resource to learn linear algebra", "research Postgres vs MySQL for a startup".
413
- pilotfish searches the web first and answers from what it read, every fact linked to its page, in seconds and with no
414
- browser. When the answer needs a site (a fare for a date, a table to book, your own account), the browser starts on
415
- the site the search found; a price or availability for particular dates is always read on the site itself.
416
-
417
- ## When the person says more mid-task
418
-
419
- Your agent reads what the person types only between tool calls, so `browser_task`, `follow_up` and `get_job` return
420
- within two minutes by default (50 s for a client that takes no progress updates, since most give up on a call after
421
- 60 s) while the task carries on. Anything the person says meanwhile (a correction, a detail,
422
- the answer to the task's question) goes to the task with `message_job`, in their words, and the agent keeps waiting
423
- with `get_job`.
412
+ on MakeMyTrip, then book a hotel near the beach for those dates on Booking.com". pilotfish splits it into parts, asks
413
+ for every sign-in it needs at the start, carries what each site gives to the next and checks the end result. Say in
414
+ the task what may be completed without asking ("pay with my saved card", "go ahead and submit"); anything else that
415
+ is final waits for a yes.
416
+
417
+ A task that names no site ("research Postgres vs MySQL for a startup") may be answered from a web search, every fact
418
+ linked to its page, with no browser. A price or availability for particular dates is always read on the site itself.
419
+
420
+ Your agent gets the rest from the tools' own descriptions: when to split a task itself, and how to pass on what the
421
+ person says while a task runs (`message_job`).
424
422
 
425
423
  ## When a job needs a person
426
424
 
package/cli.js CHANGED
@@ -15,7 +15,7 @@ import { Client } from "@modelcontextprotocol/sdk/client/index.js";
15
15
  import { isJSONRPCRequest, isJSONRPCResultResponse } from "@modelcontextprotocol/sdk/types.js";
16
16
 
17
17
  // packages/mcp-managed/dist/version.js
18
- var VERSION = true ? "0.1.36" : "0.0.0-dev";
18
+ var VERSION = true ? "0.1.38" : "0.0.0-dev";
19
19
 
20
20
  // packages/mcp-managed/dist/bridge.js
21
21
  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": "0.1.36",
3
+ "version": "0.1.38",
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",