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., "@DepHealth MCP audit the dependencies in ./my-project"
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.
Dependency security & health auditing for AI agents — no account, no API key.
DepHealth is an MCP server that lets any AI agent (Claude Code, Claude Desktop, Cursor, …) answer two questions instantly:
"Are this project's dependencies safe?" → audit_project
"Should I add / upgrade to this package?" → check_package
Vulnerability data comes from Google's OSV.dev (738K+ advisories, 40+ ecosystems); package health signals (latest version, license, release recency, deprecation) come from deps.dev. Both are free public APIs — zero signup, zero keys, zero config.
DepHealth | Snyk MCP | Socket MCP | |
Account required | No | Yes | Yes (OAuth) |
API key / auth flow | None | Snyk auth | Sign-in via client |
Ecosystems | npm, PyPI, Go, crates.io | many | many |
Token-lean output | Yes — capped, structured | — | — |
Open source | MIT | partial | partial |
MCP servers are notorious for context bloat (some inject 50K+ tokens of schema). DepHealth exposes 2 tools, 1 resource, 1 prompt with compact structured outputs — advisories are capped at 5 per package, worst-severity first, with the fix version included.
Related MCP server: @4da/mcp-server
Requires Python 3.11+ and uv.
git clone https://github.com/hasarahman/dephealth-mcp
cd dephealth-mcp && uv syncClaude Code:
claude mcp add --scope user dephealth -- uv run --project /path/to/dephealth-mcp dephealth-mcpClaude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"dephealth": {
"command": "uv",
"args": ["run", "--project", "/path/to/dephealth-mcp", "dephealth-mcp"]
}
}
}audit_project(path)Scans every supported manifest directly in path — package.json, requirements.txt, pyproject.toml, go.mod, Cargo.toml — batch-queries OSV, and returns a structured report:
verdict: "1 of 2 checked dependencies have known vulnerabilities (worst severity: HIGH)."
vulnerable_packages:
- lodash 4.17.20 (npm) — 5 advisories
GHSA-35jh-r3h4-6jhm CVE-2021-23337 HIGH Command Injection fixed_in: 4.17.21
...
unpinned_skipped: ["flask"] # hygiene flag: deps with no resolvable versionRange specifiers (^4.17.20, >=2.0) are audited at their floor and marked version_is_range_floor: true.
check_package(ecosystem, name, version?)The "should I add this?" tool. Omit version to check the latest release. Combines OSV advisories with deps.dev health signals and returns a verdict:
avoid — CRITICAL/HIGH vulnerabilities in this version
caution — lower-severity vulns, no release in 2+ years, or deprecated
ok — clean and maintained
check_package("npm", "left-pad")
→ verdict: caution
reasons: ["no release since 2018-04-09 (possibly unmaintained)",
"latest version is marked deprecated"]dephealth://ecosystems — supported ecosystems and their manifest files
security_review(project_path) — a guided prompt: audit, verify upgrade targets are clean, produce a prioritized remediation list
uv run pytest # in-process MCP client tests (hit the live free APIs)
uv run fastmcp dev src/dephealth_mcp/server.py # interactive inspectorBuilt with FastMCP. MIT license.
Scan a project's dependency manifests (package.json, requirements.txt, pyproject.toml, go.mod, Cargo.toml) and report known vulnerabilities from the OSV.dev database. Use before deploying, reviewing, or adopting a codebase.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absolute path to a project directory |
| Name | Required | Description |
|---|---|---|
| path | Yes | |
| verdict | Yes | |
| manifests_found | Yes | |
| unpinned_skipped | Yes | Dependencies without a resolvable version; not queried |
| vulnerable_packages | Yes | |
| dependencies_checked | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that the tool scans manifests and queries the OSV.dev database (implying network usage), but does not state prerequisites (e.g., file access), potential failures, or performance characteristics.
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 with zero waste. It first defines the action and scope, then provides usage context. Every word serves a 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 output schema exists, the agent can infer return format. The description covers input, purpose, and context. Minor gaps: no mention of error handling (e.g., if path is invalid or manifests missing).
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% as the only parameter 'path' has a description. The tool description reemphasizes that the path should point to a project directory containing manifests, but does not add new semantic 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 that the tool scans project dependency manifests and reports vulnerabilities from OSV.dev, specifying which manifest files are checked. However, it does not explicitly differentiate from the sibling tool check_package, which likely focuses on a single 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?
The description provides good usage guidance: 'Use before deploying, reviewing, or adopting a codebase.' However, it does not mention when not to use it or suggest alternative tools like check_package for single-package checks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Assess one package before adding or upgrading it: known vulnerabilities (OSV.dev) plus health signals (deps.dev) — latest version, license, release recency, deprecation. Returns a verdict: ok, caution, or avoid.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name, e.g. 'lodash' or 'github.com/gin-gonic/gin' | |
| version | No | Version to check; omit to check the latest release | |
| ecosystem | Yes |
| Name | Required | Description |
|---|---|---|
| name | Yes | |
| reasons | Yes | |
| verdict | Yes | |
| version | Yes | |
| licenses | Yes | |
| ecosystem | Yes | |
| released_at | Yes | |
| is_deprecated | Yes | |
| latest_version | Yes | |
| vulnerabilities | Yes | |
| latest_release_at | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses data sources (OSV.dev, deps.dev) and the verdict range, but does not explicitly state that the tool is read-only, whether it modifies anything, or potential side effects. The description is adequate but not comprehensive.
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 concise with two sentences, no filler. It front-loads the core action ('Assess one package before adding or upgrading it') and then lists specifics. Every sentence 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 3-parameter schema and the existence of an output schema, the description covers the tool's function and outputs effectively. It lacks details about error handling or behavior when 'version' is omitted, but the schema clarifies options. Overall, it is sufficiently complete for agent understanding.
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 67% (2 of 3 parameters have descriptions). The tool description provides context for the overall task but does not add significant detail beyond what the schema already provides for 'name' and 'version'. The 'ecosystem' parameter lacks a schema description and is not elaborated in the tool description, so value is marginal.
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 ('Assess') and resource ('one package') and clearly lists the assessments performed (vulnerabilities, health signals, version, license, release recency, deprecation) and the verdict output. It distinguishes from the sibling tool 'audit_project' by focusing on a single package rather than a project.
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 states when to use the tool ('before adding or upgrading it'), providing clear context. It does not explicitly mention when not to use it or contrast with the sibling, but the single-package focus implicitly guides selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0audit_projectcheck_packageEach tool has a clearly distinct purpose: audit_project scans entire project manifests for vulnerabilities, while check_package assesses a single package before adding/upgrading. No overlap in functionality.
Both tool names follow the consistent verb_noun pattern using snake_case (audit_project, check_package), making them predictable and easy to understand.
With only 2 tools, the server is minimal but well-scoped for dependency health auditing. While additional tools could be added, the current set covers the core use cases.
The tools cover the primary needs: scanning a project and checking a single package. Missing operations like updating dependencies or listing all vulnerabilities are minor gaps that agents can work around.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.
check-package: block malicious npm/PyPI deps before your AI agent installs them. Free, no key.
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
Trust-check any dependency for agents: OpenSSF Scorecard, licenses, CVEs, deps. 7 ecosystems.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hasarahman/dephealth-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server