Hound MCP is a zero-config dependency security tool for AI coding agents that scans packages and lockfiles for vulnerabilities, license issues, and typosquatting across 7 ecosystems — no API keys or accounts required.
Core tools:
hound_audit — Scan an entire lockfile (package-lock.json, yarn.lock, requirements.txt, Cargo.lock, etc.) for vulnerabilities across all dependencies
hound_vulns — List all known vulnerabilities for a specific package version, grouped by severity with fix versions and advisory links
hound_inspect — Full package profile including license, vulnerabilities, OpenSSF Scorecard, GitHub stats, and dependency count
hound_tree — Full resolved dependency tree including transitive dependencies (configurable depth up to 10)
hound_score — 0–100 Hound Score (letter grade A–F) combining vulnerability severity, OpenSSF Scorecard, release recency, and license risk
hound_compare — Side-by-side package comparison with a recommendation based on vulns, scorecard, stars, recency, and license
hound_preinstall — GO / CAUTION / NO-GO verdict before installing a package, checking vulns, typosquatting, abandonment, and license concerns
hound_upgrade — Find the minimum safe version upgrade that resolves all known vulnerabilities
hound_license_check — Scan a lockfile for license compliance against a configurable policy (permissive, copyleft, or none)
hound_typosquat — Detect whether a package name looks like a typosquat of a popular package
hound_advisories — Look up full details for a security advisory by GHSA, CVE, or OSV ID
hound_popular — Scan popular or user-specified packages for known vulnerabilities in a given ecosystem
Supported ecosystems: npm, PyPI, Go, Maven, Cargo, NuGet, RubyGems
Retrieves GitHub-sourced security advisories (GHSA), repository stars, and OpenSSF Scorecard metrics for package safety evaluation.
Integrates with Google Open Source Insights (deps.dev) and Google Open Source Vulnerabilities (OSV) to provide comprehensive package metadata and security alerts.
Audits dependencies within the .NET ecosystem to identify security vulnerabilities and recommend safe upgrade paths.
Scans npm packages for vulnerabilities, license compliance, and dependency trees using deps.dev and OSV data.
Checks .NET packages in the NuGet ecosystem for vulnerabilities, license risks, and OpenSSF health scores.
Parses pnpm-lock.yaml files to conduct batch security audits and license compliance checks across all project dependencies.
Audits Python packages (PyPI) for security risks, metadata, and vulnerability history.
Inspects Ruby packages for security advisories, dependency resolution, and license verification.
Analyzes yarn.lock files to detect vulnerable packages and resolve transitive dependency security risks.
The dependency bloodhound for AI coding agents.
AI coding agents recommend and install packages without knowing if they're safe — and most security tools require accounts, API keys, or paid plans to tell you. Hound fixes that: it scans for vulnerabilities, checks licenses, audits dependency trees, and detects typosquatting across 7 ecosystems — zero config, zero API keys, zero cost.
Hound is the only security tool built specifically for AI coding agents — works across npm, PyPI, Go, Cargo, Maven, NuGet, and RubyGems, and plugs into Claude Code, Cursor, VS Code, and any MCP client out of the box.
It uses two fully free, unauthenticated public APIs: deps.dev (Google Open Source Insights) and OSV (Google Open Source Vulnerabilities).
Related MCP server: DepScope
claude mcp add hound -- npx -y hound-mcpAdd to your MCP config file:
{
"mcpServers": {
"hound": {
"command": "npx",
"args": ["-y", "hound-mcp"]
}
}
}{
"mcp": {
"servers": {
"hound": {
"type": "stdio",
"command": "npx",
"args": ["-y", "hound-mcp"]
}
}
}
}Client | Config path |
Claude Desktop (macOS) |
|
Cursor |
|
Windsurf |
|
12 tools → Full reference with example outputs
Tool | What it does |
| Scan an entire lockfile for vulnerabilities across all dependencies |
| 0–100 Hound Score (vulns + scorecard + recency + license) with letter grade |
| Side-by-side comparison of two packages with a recommendation |
| GO / CAUTION / NO-GO verdict before installing a package |
| Find the minimum safe version upgrade that resolves all known vulns |
| Scan a lockfile for license compliance against a policy |
| All known vulnerabilities for a package version, grouped by severity |
| Full package profile — license, vulns, scorecard, stars, dep count |
| Full resolved dependency tree with transitive deps |
| Detect typosquatting variants of a package name |
| Full advisory details by GHSA, CVE, or OSV ID |
| Scan popular packages for known vulnerabilities |
Supported ecosystems: npm · pypi · go · maven · cargo · nuget · rubygems
3 prompts you can invoke directly from your AI client. → Full prompt reference
Prompt | What it does |
| Full project security audit — vulns, licenses, typosquats |
| Go/no-go recommendation before adding a new dependency |
| Pre-ship dependency scan that flags release blockers |
→ See full examples with real lockfiles and expected output
Before merging a PR — scan the lockfile diff to catch newly introduced vulnerabilities before they land in main
Auditing an inherited codebase — run hound_audit on an existing lockfile to get a full report in seconds
Checking a package before adding it — use hound_preinstall to get a GO / CAUTION / NO-GO verdict
License compliance — run hound_license_check to ensure no GPL or AGPL packages sneak into a commercial project
CI security gate — ask your AI agent to run a security audit as part of every release check
git clone https://github.com/tiluckdave/hound-mcp.git
cd hound-mcp
pnpm install
pnpm build
pnpm test # run tests
pnpm check # typecheck + lint + testDocker support — run Hound as a container for CI/CD pipelines
bun.lockb parser — Bun lockfile support
gradle.lockfile parser — Gradle (Java/Android) ecosystem support
hound_diff tool — compare two lockfile snapshots to surface newly introduced risks
GitHub Action — run hound_audit as a PR check without an AI agent
Contributions are welcome. Read CONTRIBUTING.md to get started.
The one rule: Hound must stay zero-config and free forever. Don't add features that require API keys or accounts.
Good first issues are labeled and ready.
💬 Questions or ideas? Open a Discussion
MIT © 2026 Tilak Dave
Get full details for a security advisory by ID (GHSA, CVE, or OSV ID). Returns title, severity, affected versions, fix versions, and references.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Advisory ID — e.g. GHSA-rv95-896h-c2vc, CVE-2024-29041, or any OSV ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as read-only nature, authentication requirements, or rate limits. For a simple lookup tool, this is a gap but not critical.
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 concise sentences front-load the purpose and output. No wasted words.
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?
The description lists the return fields but does not specify format, pagination, or error handling. Without an output schema, this is adequate for a simple lookup but lacks completeness for complex agent usage.
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 description coverage is 100% for the single parameter 'id', with a descriptive example. The tool description does not add additional parameter information beyond what the schema already provides, so the baseline score of 3 applies.
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 tool retrieves full details for a security advisory by ID, listing specific ID types (GHSA, CVE, OSV) and the returned information (title, severity, affected versions, etc.). This distinguishes it from sibling tools like hound_audit or hound_vulns.
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?
The description implies the tool is used for getting advisory details by ID, but does not explicitly state when to use it over alternatives or provide exclusion criteria. The context is clear given sibling tools have different purposes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan a project's lockfile for dependency risks. Parses package-lock.json, yarn.lock, pnpm-lock.yaml, requirements.txt, poetry.lock, Cargo.lock, go.sum, Gemfile.lock, pubspec.lock, or Pipfile.lock and batch-queries OSV for vulnerabilities across all dependencies.
| Name | Required | Description | Default |
|---|---|---|---|
| lockfile_name | Yes | Filename to determine format: package-lock.json, yarn.lock, pnpm-lock.yaml, requirements.txt, poetry.lock, Cargo.lock, go.sum, Gemfile.lock, pubspec.lock, Pipfile.lock | |
| lockfile_content | Yes | Full text content of the lockfile |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses that the tool parses lockfiles and batch-queries OSV, implying a read-only operation. However, it does not mention authentication, rate limits, or potential side effects, leaving some gaps.
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 sentences with clear front-loading: first sentence states the core function, second details supported formats and action. No wasted words.
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?
The tool has no output schema, so the description should explain return values. It mentions 'batch-queries OSV for vulnerabilities' but does not describe the structure or format of the output, leaving some incompleteness.
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% with descriptions for both parameters. The description reinforces the parameter purpose by listing supported lockfile names, but does not add significant new meaning 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 tool scans a project's lockfile for dependency risks, lists supported lockfile formats, and indicates it queries OSV for vulnerabilities. This is specific and distinguishes it from siblings like hound_vulns or hound_advisories.
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?
The description implies the tool is used when you need to scan a lockfile for vulnerabilities, but it does not provide explicit guidance on when to use it versus alternatives, nor does it mention prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Side-by-side comparison of two packages: vulnerabilities, OpenSSF Scorecard, GitHub stars, release recency, and license. Returns a recommendation.
| Name | Required | Description | Default |
|---|---|---|---|
| ecosystem | No | Package ecosystem (default: npm) | npm |
| package_a | Yes | First package name | |
| package_b | Yes | Second package name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool returns a recommendation and lists the comparison fields, which is helpful. It does not mention any side effects, auth requirements, or rate limits, but for a read-only comparison tool, the behavioral disclosure is adequate.
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 concise sentences front-loaded with the tool's purpose. Every phrase earns its place with no redundancy or extraneous information.
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 tool's low complexity (3 parameters, no output schema), the description sufficiently covers the tool's functionality and output. It tells the agent what to expect (comparison attributes and a recommendation), making it complete for its scope.
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 description coverage is 100% with all parameters described. The description adds context about comparison but does not enrich the meaning of individual parameters beyond what the schema provides. Baseline score of 3 is appropriate.
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 'Side-by-side comparison of two packages' and lists the specific attributes compared. This distinguishes it from sibling tools that likely focus on single-package analysis (e.g., hound_vulns, hound_inspect). The verb 'compare' and resource 'packages' are precise.
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?
The description implies usage for comparing two packages across multiple dimensions, guiding when to use this tool. It does not explicitly mention when not to use it or alternatives among siblings, but the context of comparison is clear enough for appropriate selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a comprehensive profile of a package version: licenses, vulnerabilities, OpenSSF scorecard, GitHub stats, and dependency count — all in one call.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name | |
| version | Yes | Package version | |
| ecosystem | No | Package ecosystem (default: npm) | npm |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the return fields but does not explicitly mention read-only nature, rate limits, or data freshness. While typical for a profile tool, it lacks explicit safety or behavioral notes.
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?
A single, well-structured sentence (19 words) that front-loads the purpose and lists key outputs with no redundancy.
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 3 parameters, no output schema, and no annotations, the description provides adequate context for a profile tool. It names all key return items. However, it could mention data sources or limitations.
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% with each parameter described. The description adds no further parameter details beyond listing output fields, so it does not significantly augment schema semantics.
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 'Get' and the resource 'comprehensive profile of a package version', listing specific components (licenses, vulnerabilities, etc.). It effectively distinguishes from siblings that focus on individual aspects (e.g., hound_vulns, hound_score).
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?
The description implies use when a broad overview is needed ('all in one call'), contrasting with more specific siblings. However, it does not explicitly state when not to use or list alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan a lockfile for license compliance. Resolves licenses for every dependency and flags packages that violate the chosen policy (permissive, copyleft, or none).
| Name | Required | Description | Default |
|---|---|---|---|
| policy | No | License policy to enforce: 'permissive' (MIT/Apache/BSD only), 'copyleft' (allows GPL but not AGPL), 'none' (report only, no violations) | permissive |
| lockfile_name | Yes | Filename: package-lock.json, yarn.lock, pnpm-lock.yaml, requirements.txt, poetry.lock, Cargo.lock, go.sum, Gemfile.lock, Pipfile.lock | |
| lockfile_content | Yes | Full text content of the lockfile |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool resolves licenses and flags violations based on policy, but it does not mention side effects, permissions, or the output format. The behavior is adequately described for a read-only scan.
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 long, each serving a distinct purpose: defining the action and elaborating the policy behavior. It is front-loaded and free of unnecessary words.
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?
The description lacks information about the return value, which is critical since no output schema exists. Without knowing what the tool returns (e.g., violations list, pass/fail), an agent cannot effectively use the results. This is a significant gap for a tool with 3 parameters.
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%, with all parameters described in the schema. The description adds context by explaining the policy enum values but does not provide new semantic information beyond the schema. It restates the workflow without adding depth.
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 tool 'scan[s] a lockfile for license compliance' with specific verbs and resources. It distinguishes itself from sibling tools like hound_vulns (security vulnerabilities) by focusing solely on licenses.
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?
The description explains the purpose and policy options but does not provide explicit guidance on when to use this tool versus alternatives (e.g., hound_audit). Usage context is implied by the tool's function, but no exclusions or comparisons are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan a list of popular (or user-specified) packages for known vulnerabilities. Quickly surface which widely-used packages in an ecosystem have open security issues.
| Name | Required | Description | Default |
|---|---|---|---|
| packages | No | Specific package names to check. If omitted, uses a curated list of popular packages for the ecosystem. | |
| ecosystem | No | Package ecosystem (default: npm) | npm |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must convey behavioral traits. It only states the core function (scanning for vulnerabilities) without mentioning safety (e.g., read-only), performance implications, or limitations. The lack of detail on what the tool does beyond the basic purpose makes it minimally transparent.
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 sentences that are front-loaded with purpose, no redundant words, and every sentence adds value. The structure is efficient and clear.
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 tool's simplicity (2 optional parameters, no output schema), the description provides sufficient context for an AI agent: it scans packages for vulnerabilities and can use a curated list. While return format isn't detailed, the purpose is clear enough for correct 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%, providing baseline of 3. The description adds extra context for the 'packages' parameter by explaining the default behavior (using curated list if omitted). This goes beyond the schema's description, warranting a higher score.
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 tool 'scans a list of popular (or user-specified) packages for known vulnerabilities.' It specifies the action (scan), resource (list of packages), and goal (find vulnerabilities), distinguishing it from siblings like hound_vulns by emphasizing focus on popular packages.
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?
The description implies usage for quickly surfacing vulnerabilities in widely-used packages, but does not explicitly state when to use versus alternatives like hound_vulns or hound_audit. No exclusion criteria or when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Safety check before installing a package. Checks known vulnerabilities, typosquatting risk, abandonment, and license concerns. Returns a go/no-go verdict.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name | |
| version | No | Package version (defaults to latest) | |
| ecosystem | No | Package ecosystem (default: npm) | npm |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It describes the tool as a safety check that analyzes multiple aspects and returns a go/no-go verdict, implying a read-only, non-destructive operation. However, it lacks details on authorization requirements or how the verdict is calculated.
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 concise sentences. The first sentence states the purpose, and the second details the checks and output. No extraneous information.
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?
The description explains the output (go/no-go verdict) but does not specify the format or structure of the verdict. Given the absence of an output schema, this leaves some ambiguity for an agent invoking the tool.
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 has 100% description coverage, so the baseline is 3. The description does not add additional semantics beyond what the schema already provides for the parameters; it only gives context for the overall tool purpose.
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 tool performs a safety check for installing a package, covering vulnerabilities, typosquatting, abandonment, and license concerns. It distinguishes itself from sibling tools like hound_vulns or hound_typosquat by being a comprehensive pre-install check that returns a single verdict.
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?
The description explicitly says 'before installing a package', which clearly indicates when to use this tool. It does not explicitly state when not to use it or mention alternatives among siblings, but the context is strong enough for an agent to infer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compute a 0-100 Hound Score for a package version combining vulnerability severity, OpenSSF Scorecard, release recency, and license risk. Returns a letter grade (A-F) with a breakdown.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name | |
| version | Yes | Package version | |
| ecosystem | No | Package ecosystem (default: npm) | npm |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It mentions the scoring factors and output, but does not state side effects (likely none), required permissions, or failure conditions (e.g., if package not found). The read-only nature is assumed but not confirmed.
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 sentences, front-loaded with the core action. Every word adds value: specifies numeric range, factors, and output format. No redundancy or fluff.
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 absence of an output schema, the description adequately summarizes the return format (letter grade with breakdown). However, it lacks details on the breakdown structure (e.g., numeric sub-scores) and does not address edge cases like missing data or unsupported packages. With siblings, more usage context 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?
Schema coverage is 100%, so parameters are already documented. The description reinforces that 'name' and 'version' identify the package and 'ecosystem' (with default) is optional. However, it does not explain how ecosystem influences the score, leaving some nuance unaddressed.
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 it computes a 0-100 Hound Score for a package version, listing the factors involved (vulnerability severity, OpenSSF Scorecard, etc.) and the output (letter grade A-F with breakdown). It distinguishes itself from sibling tools like hound_advisories or hound_vulns by focusing on a composite score.
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?
No explicit guidance on when to use this tool versus its siblings. The description implies assessing package health, but does not contrast with alternatives (e.g., hound_audit for detailed audit, hound_vulns for vulnerabilities). An agent would need to infer usage from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Show the full resolved dependency tree for a package version, including all transitive dependencies with their depth and relation type.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name | |
| version | Yes | Package version | |
| maxDepth | No | Maximum depth to display (default: 3, max: 10) | |
| ecosystem | No | Package ecosystem (default: npm) | npm |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only says what the tool shows, but does not mention whether it performs network fetches, has rate limits, or if it is read-only. Basic transparency is missing.
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?
Single sentence, front-loaded with action and resource. No redundant information, every word contributes to understanding.
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 no output schema, the description adequately explains what the tool returns. It could be improved by mentioning the output format (e.g., tree structure, JSON), but is otherwise sufficient for agent decision-making.
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% with descriptions for all parameters. The tool description adds context about the output (full tree, transitive dependencies) but does not add new meaning to parameter definitions beyond what the schema provides.
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 tool shows the full resolved dependency tree for a package version, including transitive dependencies with depth and relation type. This distinguishes it from sibling tools like hound_advisories or hound_audit.
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?
No guidance on when to use this tool versus alternatives like hound_inspect or hound_audit. The description does not mention prerequisites, exclusions, or conditions for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check if a package name looks like a typosquat of a popular package. Generates likely typo variants and checks which ones exist in the registry.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name to check | |
| ecosystem | No | Package ecosystem (default: npm) | npm |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool generates typo variants and checks registry existence, but lacks details on return format, side effects, or authentication needs. Adequate but not rich.
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 contains no superfluous information. Every word earns its place.
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 tool's low complexity (2 parameters, no output schema, no nested objects), the description is largely sufficient for an agent to understand its function. Could benefit from mentioning return value type (e.g., list of found typosquats), but overall 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?
Schema description coverage is 100%, with both parameters well-described. The description adds context about generating typo variants for the name parameter, but doesn't significantly enhance meaning beyond the schema. Baseline 3 applies.
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 tool's purpose: checking if a package name is a typosquat of a popular package. It uses a specific verb ('Check') and resource ('package name'), and distinguishes from sibling tools like hound_inspect or hound_popular.
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?
The description implies usage when suspecting typosquatting, but does not provide explicit when-to-use or when-not-to-use guidance, nor does it reference alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find the minimum version upgrade that resolves all known vulnerabilities for a package. Checks every published version and returns the nearest safe one.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name (e.g. express, lodash) | |
| version | Yes | Current vulnerable version (e.g. 4.17.20) | |
| ecosystem | No | Package ecosystem (default: npm) | npm |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry full behavioral disclosure. It mentions checking every published version but does not disclose potential network dependencies, rate limits, performance implications, or error behavior (e.g., if no safe version exists). This is a significant gap for a tool that requires external calls.
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 sentences, zero wasted words. First sentence states core purpose, second adds method detail. Efficient and front-loaded.
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 query tool, the description explains what it returns (nearest safe version) and the method (checks each published version). It does not cover error handling or edge cases, but given the absence of output schema, it is reasonably complete. Sibling tools imply similar interface patterns.
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?
Input schema covers all parameters with descriptions (100% coverage). The description adds no additional meaning beyond the schema; it only repeats the version concept. Baseline 3 is appropriate since schema does the heavy lifting.
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 tool finds the minimum version upgrade that resolves all known vulnerabilities for a package. It uses a specific verb 'Find' and resource 'minimum version upgrade', and the purpose is distinct from sibling tools like hound_advisories (list advisories) or hound_vulns (list vulnerabilities).
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?
The description implies usage when a user has a vulnerable package and wants the minimal safe upgrade. It explicitly mentions checking every published version and returning the nearest safe one, providing clear context. However, it does not explicitly state when not to use or name alternative tools for excluded scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all known vulnerabilities for a specific package version, grouped by severity with fix versions and advisory links.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name (e.g. express, lodash) | |
| version | Yes | Package version (e.g. 4.18.2) | |
| ecosystem | No | Package ecosystem (default: npm) | npm |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavior. It mentions grouping by severity and included fields (fix versions, advisory links), but omits whether the operation is read-only, requires permissions, or has any side effects.
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 action and includes key details without unnecessary words.
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?
No output schema is provided, but the description gives a reasonable overview of the response structure (grouped by severity with fix versions and advisory links). For a moderately complex tool, this is fairly complete, though it could explicitly state the output format (e.g., JSON).
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%, so parameters are well-documented in the schema. The description reinforces the parameter roles but adds no new meaning 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 tool lists vulnerabilities for a specific package version, with details on grouping and included information. It uses a specific verb-resource combination and distinguishes from sibling tools like hound_advisories which likely cover general advisories.
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?
The description implies use for retrieving vulnerability info for a specific version, but lacks explicit when-not-to-use or comparisons to siblings. No exclusions or alternative suggestions are provided.
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 clearly distinct purpose: e.g., advisories for details, audit for lockfile scanning, compare for side-by-side, inspect for profile, license_check for compliance, popular for scanning popular packages, preinstall for safety check, score for computation, tree for dependencies, typosquat for name similarity, upgrade for safe version, vulns for listing. No overlap.
All tools follow the 'hound_' prefix with a descriptive noun or verb-noun compound (e.g., audit, compare, license_check, preinstall, score, tree, typosquat, upgrade, vulns). The pattern is consistent and predictable, aiding agent selection.
12 tools cover the domain of package security and dependency analysis comprehensively without being excessive. Each tool serves a necessary function, and the count is appropriate for the scope.
The tool set covers the full lifecycle: advisory retrieval, vulnerability scanning (lockfiles), profiling, comparison, license checking, popular package scanning, pre-install checks, scoring, dependency trees, typosquat detection, upgrade recommendations, and vulnerability listing. No obvious gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Protects AI coding agents from installing malicious open source packages. Every npm and PyPI package is checked against SafeDep’s real-time threat intelligence before installation.
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tiluckdave/hound-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
