This server lets MCP-compatible clients (like Claude) access packagerating.com package health and risk scores live from a coding session.
list_packages — List npm/PyPI packages that have been scored, sorted by composite score, and optionally filtered by language and limited to 1–200 results.
get_package — Fetch the full health/risk score and dimension breakdown for a single package, optionally for a specific version; triggers and waits for a first crawl if needed.
request_crawl — Enqueue one or more packages for crawling without waiting, useful for pre-warming scores before comparison.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@packagerating MCP Server Is express safe to use?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Give Claude (or any MCP-compatible client) live, on-demand access to packagerating.com package health/risk scores — right inside your coding session, not just in CI.
Three tools, each a thin mirror of the public REST API:
Tool | What it does |
| List scored packages, sorted by composite score by default |
| Full score + dimension breakdown for one package by name. Transparently waits for a first-ever crawl to finish. |
| Pre-warm one or more packages for crawling without waiting on the result |
A never-before-scored package can take up to ~60 seconds to return on first lookup via
get_package(the server waits for the crawl to finish); every subsequent lookup is fast.
Get a free API key at packagerating.com.
Add the server. In Claude Code:
claude mcp add packagerating -e PACKAGERATING_API_KEY=your-api-key-here -- npx -y @packagerating/mcp-serverThat adds it in Claude Code's local scope (personal, this project only). To share it with a
team via a committed .mcp.json, add --scope project.
For any other MCP-compatible client, add this to its config:
{
"mcpServers": {
"packagerating": {
"command": "npx",
"args": ["-y", "@packagerating/mcp-server"],
"env": {
"PACKAGERATING_API_KEY": "your-api-key-here"
}
}
}
}No local install, no build step either way — npx fetches the latest published version each time.
Related MCP server: Depfender MCP Server
"Is
left-padsafe to add as a dependency? What aboutlodash?"
Claude calls get_package for each name and can compare the results directly in conversation —
liveness, community, security, dependency posture, versioning, and dependency-tree risk, plus the
three composite scores (General, Automation, Risk).
npm install
npm test # unit tests, mocked HTTP — no live API calls
npm run typecheck
npm run build # bundles to dist/index.js via @vercel/ncc
npm run smoke-test # exercises the real production API — requires a real PACKAGERATING_API_KEYpackagerating/skills — Claude Code plugin built on this server
packagerating/audit-dependencies — GitHub Action, npm dependencies
packagerating/audit-dependencies-python — GitHub Action, Python dependencies
packagerating.com — sign up for an API key and learn about the product
Get the full health/risk score for a single package by name. If the package has never been scored, this triggers a crawl and waits (bounded) for it to finish before returning.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name in its registry, e.g. "axios" or "requests". | |
| version | No | Specific version to look up. Defaults to the most recently crawled version. | |
| language | No | Language ecosystem. Defaults to javascript. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does disclose the non-obvious side effect: triggering a crawl and waiting bounded if never scored. It doesn't cover timeout behavior, output shape, or idempotence, but the key behavioral trait is clearly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two focused sentences: the first states the purpose, the second a necessary caveat about triggering a crawl. No redundant words or repetition of schema details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, it covers the main purpose, side-effect, and bounded wait. Missing details are mostly output structure and explicit relationships to siblings, but the description is sufficient for correct selection and basic invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and all parameters have descriptive metadata (name, version, language). The description adds 'by name' and 'full score' but does not provide meaning beyond the schema, matching the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') with a clear resource ('full health/risk score for a single package by name'). It distinguishes from sibling tools by emphasizing 'single package' and the score result, versus list_packages (listing) and request_crawl (triggering crawls).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It implies when to use: when you need a score for one package, and warns that it may trigger a crawl if unscored. However, it does not explicitly name alternatives like request_crawl for cases where you don't want to wait, so it stops short of full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List npm/PyPI packages that have at least one score, sorted by composite score by default.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Field to sort by. Defaults to general_score. | |
| limit | No | Max results, 1-200. Defaults to 50. | |
| order | No | Sort direction. Defaults to desc. | |
| language | No | Filter by language ecosystem. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the transparency burden. It discloses key filtering behavior (only packages with at least one score) and default sorting, but it does not mention the response format, pagination, or explicitly state that this is a read-only operation beyond the verb 'List'. There is no contradiction with any structured metadata.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the core action and adds relevant qualifiers without any filler. Every word contributes to understanding the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complete parameter schema and simple list operation, the description adequately covers the key behavior: what is listed, the score filter, and default ordering. The lack of an output schema is somewhat mitigated by the straightforward nature of a list tool, though explicit return structure or pagination details would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides 100% coverage with full descriptions and enums for all four parameters, so the baseline is 3. The description adds minor context about 'composite score' and default sort, but it does not meaningfully expand on parameter usage beyond what the schema already declares.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('List') and resource ('npm/PyPI packages') with a clear scope ('that have at least one score') and default ordering ('sorted by composite score by default'). This distinguishes it from siblings like get_package (single package lookup) and request_crawl (initiating crawls).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides clear context for when to use the tool: when you need a list of scored npm/PyPI packages. It does not explicitly name alternatives or exclusions, but the context is sufficient for an agent to distinguish this list operation from package details or crawling requests.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Enqueue one or more packages for crawling without waiting for the result. Useful for pre-warming several packages at once, e.g. before comparing alternatives.
| Name | Required | Description | Default |
|---|---|---|---|
| language | Yes | Language ecosystem of the packages to crawl. | |
| packages | Yes | Package names to enqueue for crawling. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the burden. It discloses that the operation is non-blocking ('without waiting for the result') and that it enqueues, but it does not clarify return behavior, authentication needs, or queue side effects, leaving some ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core action, and every clause contributes value. No wasted words or repetition of schema fields.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with 2 parameters and no output schema, the description covers the main behavior and a use case. It lacks explicit mention of what the caller receives after enqueueing, but given the tool's low complexity, it is reasonably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides 100% coverage of both parameters with descriptions, so the description adds little beyond reinforcing that multiple packages can be submitted ('one or more'). It does not introduce new constraints or format details beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Enqueue' and the resource 'packages for crawling,' and distinguishes itself from siblings by emphasizing 'without waiting for the result,' which contrasts with synchronous retrieval tools like get_package.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides a clear use case: 'pre-warming several packages at once, e.g. before comparing alternatives,' which implies when this tool is appropriate. However, it does not explicitly name alternatives or state when not to use it, so it falls short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a distinct purpose: listing scored packages, fetching a single package's score, and enqueueing crawls without waiting. Although get_package can trigger a crawl, the key difference is that request_crawl is for background pre-warming, so there is no ambiguity.
All tool names follow the same verb_noun pattern: list_packages, get_package, request_crawl. The naming is predictable and consistently formatted.
With only 3 tools, the server is tightly scoped to its purpose of providing package ratings. Each tool is necessary and there is no bloat, making the count feel intentional rather than thin.
The tool surface covers the core workflows: listing available packages, retrieving detailed scores, and requesting background crawls for pre-warming. There are no obvious operational gaps for the stated domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Provide AI-powered real-time analysis and intelligence on NPM packages, including security, depend…
Live trust signals for domains & packages: age, registrar, typosquat resemblance.
Supply chain risk scoring for npm, PyPI, Cargo, and Go. 9 tools. Behavioral signals.
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/packagerating/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server