Package Scout
Searches the live npm registry for real packages matching an AI agent's task, returns a recommended package with version and install command, and provides package details such as license, weekly downloads, dependencies, advisories, release date, README, npm URL, and repository.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Package Scout
Your AI agent loves writing code. Scout would rather not.
Before your agent hand-rolls a CSV parser, Package Scout checks whether npm, or the platform itself, already has one. It answers with a one-line verdict, an install command and the facts behind both. It makes no model calls and needs no API keys.
Looks like ten lines. It's ten years of bug reports.
We ran ten small, legal CSV files through three hand-rolled parsers and the package Scout picks.
What you could do | Lines you own | Files parsed correctly |
The quick way: | 5 | 6 of 10 |
The clever way: a regex | 7 | 9 of 10 |
The careful way: a state machine | 35 | 10 of 10 |
Scout's way: | 2 | 10 of 10 |
Neither failing parser throws an error. The quick one files Jane Smith's email under a column named undefined. The clever one turns two customers into three.
The files, the method and the raw results are in the CSV challenge, with a passing public GitHub Actions run. Think your agent's parser does better? npm run challenge -- ./its-parser.mjs.
Related MCP server: pkgguard
Meet Scout
Every team has one: the developer who answers "how should we build this?" with "we shouldn't, there's a package for that." Scout is that developer, working for your AI agent. Scout has never written a CSV parser and is not about to start.
Scout is lazy, with standards:
A package is for a rabbit hole, never for a few lines. Ask for left-pad and Scout tells you to install nothing.
Every pick is real and checked. It exists on npm today, has a license, is not deprecated and has no known advisories of its own.
No AI inside. Scout is a lookup. Your agent brings the intelligence; Scout brings the facts.
Try it in a minute
Claude Code: install the plugin
With Node 24.3+ on your PATH, run these two commands inside Claude Code:
/plugin marketplace add Memrov/package-scout
/plugin install package-scout@package-scoutRun /reload-plugins or start a new session, then ask:
/package-scout:scout parse a CSV upload in the browserThe server is bundled and starts automatically. No API key, hosted login,
npm install, or separate server is needed. Claude Code itself uses your normal
Claude account. See the plugin guide for updates,
troubleshooting and development.
Other MCP clients: npm
With Node 24.3+, configure a stdio MCP server with:
{
"command": "npx",
"args": ["--yes", "@memrov2/package-scout@1.0.1"]
}The npm package has no runtime dependencies. See the client setup and signed release.
ChatGPT, Codex, or another MCP client
The maintained hosted copy uses Sites sign-in for API access. In ChatGPT or Codex, use the existing Package Scout plugin. To run your own HTTP server, follow the setup below.
Run it. You need Node 24.3 or newer.
git clone https://github.com/Memrov/package-scout
cd package-scout
npm ci --ignore-scripts
npm run devOpen http://127.0.0.1:8787 and ask Scout something. Then give it to your agent:
claude mcp add --transport http package-scout http://127.0.0.1:8787/mcpThat is Claude Code. Any other MCP client can point at the same /mcp address, and a project can share it in .mcp.json:
{
"mcpServers": {
"package-scout": { "type": "http", "url": "http://127.0.0.1:8787/mcp" }
}
}For your own hosted copy, put its address in place of http://127.0.0.1:8787 and configure your client's authentication for that host.
Now ask your agent for something it would normally build from scratch:
"Let customers upload a CSV of contacts."
"Render this Markdown as HTML."
"Retry failed API calls with backoff."
"Add a date picker to the signup form."
"Left-pad these invoice numbers to six digits."
No agent handy? The same search is one request:
curl -s http://127.0.0.1:8787/v1/search -H 'content-type: application/json' \
-d '{"keywords":["csv parser"],"runtime":"browser"}'What comes back
A short answer: about 2 KB, where the full evidence is about 17 KB. This is a live answer from 2026-11-17, trimmed to the verdict and the first of its three picks:
{
"verdict": "Scout's pick: papaparse@5.7.1. 25.5M downloads a week, MIT, no known direct advisories. That's the whole job.",
"platform": null,
"packages": [
{
"name": "papaparse",
"version": "5.7.1",
"install": "npm install papaparse@5.7.1",
"description": "Fast and powerful CSV parser for the browser that supports web workers and streaming large files. Converts CSV to JSON and JSON to CSV.",
"weekly_downloads": 25501733,
"licenses": ["MIT"],
"dependencies": null,
"runtime": "declared",
"match": "complete",
"published_at": "2026-11-11T16:33:28Z",
"openssf_scorecard": 4.2,
"npm_url": "https://www.npmjs.com/package/papaparse",
"repository": "https://github.com/mholt/papaparse"
}
],
"returned": 3
}When the platform already does the job, the verdict changes. Trimmed again:
{
"verdict": "Don't install anything: String.prototype.padStart() is built in. If that is not enough, Scout's pick is pad-left@2.1.0.",
"platform": {
"builtin": "String.prototype.padStart()",
"example": "String(7).padStart(3, '0') // '007'",
"limits": "It counts UTF-16 code units, so emoji and combining characters throw the width off.",
"note": "The internet broke over an 11-line version of this in 2016. It has been built in since 2017."
}
}And when Scout is not sure, it says so. A pick with a small crowd opens with "Closest fit", a partial match opens with "Partial match", and both end with "Read its README before you trust it." Ask for detail: "full" to get every signal the answer was built from.
Find it. Check it. Prove it.
Step | Tool | What you get |
Find it |
| A verdict, the built-in answer if there is one, and up to three real packages. |
Check it |
| License, weekly downloads, dependencies, known advisories, release date and the README, each with its source. |
Prove it | Your agent writes a test. A throwaway container runs it against the exact version. You keep the logs, pass or fail. |
Scout's bar
Nothing makes the shortlist unless it clears all five.
It exists. Scout reads the live registry, so there are no invented package names.
It has a license it can name.
It is not deprecated, and not a prerelease. Unless you ask for those.
It has no known advisories of its own.
It gets at least 1,000 downloads a week. Ask for niche packages and this one goes away. The other four stay.
Advisories in a package's dependencies are not checked, and a metadata match is not a test. Scout says both in every answer.
Things Scout will tell you not to install
You were about to install | Scout says | The catch |
a left-pad package |
| It counts UTF-16 code units, so emoji throw the width off. |
a deep-clone helper |
| It throws on functions, and class instances come back plain. |
a UUID generator |
| Version 4 only. |
an HTTP client |
| No retries or interceptors, and you check |
a date picker |
| It looks different in every browser and cannot do ranges. |
a modal library |
| Styling and animation are yours. |
a currency formatter |
| Display only. |
an argument parser |
| No subcommands or generated help. |
dotenv |
| Plain |
a test runner |
| Built for Node code. |
is-odd |
| None. Scout isn't angry. Scout is disappointed. |
There are 27 built-ins so far, in catalog/platform.json, and the test suite runs every Node one to make sure it works. Each entry states its limits, because that is the point where a package becomes the right answer after all. Adding one is a single JSON entry.
The rabbit-hole list
Jobs that look like ten lines and are not. This is Scout's first pick for each, checked live on 2026-11-17. Run npm run holes to check again.
The job | Scout is asked for | Scout's first pick | Downloads a week |
Parse a CSV upload |
| 25.5M | |
Render Markdown |
| 130M | |
Read YAML |
| 395M | |
Drag and drop |
| 43.2M | |
Generate a PDF |
| 17.8M | |
Fuzzy search |
| 21.2M | |
Retry with backoff |
| 56.6M | |
Highlight code |
| 53.3M | |
Verify a JWT |
| 232M | |
Handle time zones |
| 44M | |
Diff two texts |
| 189M | |
Read and write zip files |
| 72.4M | |
Read an Excel file |
| 28.1M | |
Resize an image |
| 166M | |
Show a toast |
| 59.2M | |
Draw a chart |
| 66.9M | |
Run a WebSocket server |
| 409M | |
Cache with eviction |
| 800M | |
Rate-limit an API |
| 97.4M | |
Compare versions |
| 1.2B |
What Scout won't do
Use AI. No model calls, no API keys, no inference bill.
Install anything. It returns an install command. Running it is your call.
Run package code, unless you ask it to prove a pick.
Call a metadata match a test. It tells you what it checked and what it did not.
Look beyond npm. Not yet.
FAQ
Does Scout use AI? No. It looks things up.
How is that different from asking the model? A model remembers packages. Scout checks them: today's version, license, downloads and advisories.
Will it bloat my node_modules? It installs nothing. It returns up to three options, says how many dependencies each one brings, and tells you when the platform already does the job.
Why only three results? You weren't going to read ten.
Where's the score out of 100? We had one. It was made up, so we deleted it. Now you get the facts it was made from.
Can I trust the pick? Trust the facts, then check. When Scout is unsure, the verdict says so. For anything that matters, have your agent prove it.
What if no package exists? Then you get to write code. Scout is sorry for your loss.
Which agents does it work with? Claude Code can install the bundled plugin, which uses MCP over stdio. Other clients can connect over HTTP. Both transports are checked against the official MCP SDK client. ChatGPT uses it through the plugin skill in plugin/skills.
Works well with ponytail
Package Scout was inspired by ponytail, which teaches an agent to write less code. Ponytail's ladder asks whether the code needs to exist, then whether the codebase, the platform or an installed dependency already has it, and only then writes the minimum.
Scout adds one question before that last rung: is this a rabbit hole someone has already mapped? The two share a rule, in ponytail's words: "Never add a dependency for a few lines."
Go deeper
Reference: every parameter, how candidates are filtered and ordered, limits, cache and costs.
Agent-written evaluations: the Prove it step.
The CSV challenge: the ten files, the entrants and how to bring your own parser.
The agent skill: how an agent is told to use Scout.
Security controls and evidence: OpenSSF results, signed releases and the requirements still unmet.
npm releases: publication, provenance verification and future trusted publishing.
Development
Use Node 24.3+:
npm ci --ignore-scripts
npm run check # types
npm test # unit tests, including every built-in answer
npm run dev # http://127.0.0.1:8787
npm run test:live # real lookups against npm and deps.dev
npm run challenge # the CSV challenge
npm run holes # regenerate the rabbit-hole table
npm run build && npm run validateHosting and plugin publishing notes are in the reference.
License and data
Application code is Apache-2.0. Evidence comes from npm and deps.dev; deps.dev-generated data is CC BY 4.0, and every response carries attribution.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Verify npm packages before your AI agent installs them: hallucinations, advisories, API drift.
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
Live npm and UNPKG data for AI agents: resolution, audits, import maps, malware/CVE checks.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI coding agents to search the npm registry and retrieve package metadata, READMEs, download stats, GitHub details, and usage snippets via the Model Context Protocol.915 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to automatically verify npm packages against the live registry before installation, flagging hallucinated, slopsquatted, or otherwise suspicious packages with risk verdicts.4 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to verify, compare, and safely upgrade npm packages by scoring packages from public signals and sandboxed co-installation, detecting breaking API surface changes, and rewriting code that upgrades break.55 npm8MIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code and other compatible clients to retrieve real-time, context-aware documentation, TypeScript types, examples, migration guides, error diagnoses, package comparisons, and dependency scans for any npm package.MIT