VulnFeed scans project dependencies for known CVEs, enriches results with EPSS exploit probability scores, and recommends fix versions.
Scanning
scan_project — Auto-detect and scan all lockfiles in a project directory
scan_lockfile — Scan a specific lockfile (npm, Yarn, pnpm, pip, Pipenv, Go, Rust, Ruby, PHP)
check_package — Check a single package by name, version, and ecosystem (npm, PyPI, Go)
lookup_cve — Get detailed info on a specific CVE or GHSA ID, including severity, EPSS score, affected versions, and fix recommendations
Continuous Monitoring
monitor_project — Register a project for monitoring by taking a baseline snapshot
check_alerts — Diff current vulnerabilities against the baseline to surface only new findings since last scan
update_deps — Refresh a monitored project's dependency snapshot after upgrades
list_monitored — View all projects registered for monitoring
unmonitor_project — Remove a project from monitoring
Key Features
Queries OSV.dev (NVD + GitHub Advisories) for CVE data
Enriches results with EPSS exploit probability scores
Smart filtering suppresses low-priority CVEs (EPSS < 10% AND CVSS < 9.0) by default, reducing noise by ~80%; override with show_all=True
Sorts results by exploitability (most dangerous first) and provides fix version recommendations
Scans composer.lock files to detect known vulnerabilities in PHP dependencies and recommend fix versions.
Scans npm package-lock.json files to detect known vulnerabilities in dependencies and recommend fix versions.
Scans pnpm-lock.yaml files to detect known vulnerabilities in dependencies and recommend fix versions.
Scans pip requirements.txt and Pipfile.lock files to detect known vulnerabilities in Python dependencies and recommend fix versions.
Scans Gemfile.lock files to detect known vulnerabilities in Ruby dependencies and recommend fix versions.
Scans Cargo.lock files to detect known vulnerabilities in Rust dependencies and recommend fix versions.
Scans yarn.lock files to detect known vulnerabilities in dependencies and recommend fix versions.
An MCP server that scans your project dependencies for known vulnerabilities, enriches with EPSS exploit probability scores, and recommends fix versions.
Free tier — 10 scans/day, 1 monitored project, no signup required.
Homepage: vulnfeed.novadyne.ai
uvx vulnfeed-mcpAdd to your MCP client config (~/.claude/settings.json for Claude Code, claude_desktop_config.json for Claude Desktop):
Free tier (no signup, no API key):
{
"mcpServers": {
"vulnfeed": {
"command": "uvx",
"args": ["vulnfeed-mcp"]
}
}
}Paid ($14/mo, unlimited scans + projects):
{
"mcpServers": {
"vulnfeed": {
"command": "uvx",
"args": ["vulnfeed-mcp"],
"env": {
"VULNFEED_API_KEY": "YOUR_LICENSE_KEY_HERE"
}
}
}
}Get a license key at vulnfeed.novadyne.ai.
VulnFeed also accepts x402 micropayments — AI agents can pay per scan with USDC on Base, no API key or signup needed. When the free tier limit is reached, the API returns HTTP 402 with payment requirements that x402-compatible clients handle automatically.
$0.01 per scan
$0.002 per CVE lookup
$0.05 per project monitor setup
Related MCP server: locklens
Tool | Description |
| Auto-detect and scan all lockfiles in a directory |
| Scan a specific lockfile |
| Check a single package for vulnerabilities |
| Detailed CVE info with EPSS + fix versions |
Tool | Description |
| Register for continuous monitoring |
| New vulns since last scan |
| Update snapshot after upgrading packages |
| See all monitored projects |
| Remove from monitoring |
package-lock.json (npm)
yarn.lock (Yarn)
pnpm-lock.yaml (pnpm)
requirements.txt (pip)
Pipfile.lock (Pipenv)
go.sum / go.mod (Go)
Cargo.lock (Rust)
Gemfile.lock (Ruby)
composer.lock (PHP)
Parses your lockfile to extract dependency names + versions
Queries OSV.dev (NVD + GitHub Advisories) for known CVEs
Enriches with EPSS exploit probability scores
Filters noise — suppresses low-EPSS, non-critical CVEs by default
Sorts by exploitability — most likely to be exploited first
Returns fix version recommendations from package registries
By default, VulnFeed suppresses low-priority CVEs (EPSS < 10% AND CVSS < 9.0). This cuts noise by ~80%.
Pass show_all=True to any scan tool to see everything.
monitor_project — takes a baseline snapshot of current deps + known vulns
check_alerts — diffs against baseline, surfaces only new vulns
Run check_alerts periodically to catch newly published CVEs
MIT
Check for new vulnerabilities since the last scan of a monitored project.
Compares current vulnerability data against the stored baseline. Returns new vulnerabilities (not seen before) and resolved ones (previously known, no longer present).
Args: project_id: The project ID returned by monitor_project.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes the comparison against baseline and what it returns (new and resolved vulnerabilities). No annotations, but description provides needed behavioral context.
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?
Very concise, front-loaded, 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?
Given the output schema, one parameter, and no annotations, the description is complete for the tool's purpose and context.
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?
With 0% schema description coverage, the description specifies project_id is 'returned by monitor_project', adding essential meaning.
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 checks for new and resolved vulnerabilities since the last scan, distinguishing it from siblings like check_package and lookup_cve.
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?
Implies usage after a scan and monitoring, but does not explicitly mention when not to use or alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check a single package for known vulnerabilities.
Args: name: Package name (e.g. "express", "django", "golang.org/x/net"). version: Package version (e.g. "4.18.2", "3.2.0"). ecosystem: Package ecosystem — "npm", "PyPI", or "Go". Defaults to "npm". show_all: Show all vulnerabilities including low-priority ones.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| version | Yes | ||
| ecosystem | No | npm | |
| show_all | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
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 does not disclose any behavioral traits such as whether the tool makes external API calls, has rate limits, or side effects. The description focuses solely on parameters and input format.
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 a clear lead sentence and an 'Args:' list format. Every sentence adds value, and the structure allows quick parsing by an AI agent.
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 presence of an output schema and the tool's relative simplicity, the description adequately covers parameter semantics. However, it lacks behavioral context (e.g., response format, error handling) and usage guidance relative to siblings.
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 0%, meaning the input schema only provides types and default values. The description compensates by detailing all four parameters with example values and explanations, fully adding meaning beyond the structured 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 'Check a single package for known vulnerabilities', which is a specific verb+resource combination. It distinguishes from sibling tools like scan_lockfile or check_alerts that handle multiple packages or different actions.
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 individual packages but does not explicitly state when to use this tool versus others like scan_project or lookup_cve. No alternative recommendations or exclusions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all projects registered for vulnerability monitoring.
Shows project names, IDs, package counts, and registration dates.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for disclosing behavioral traits. It only mentions output fields (names, IDs, package counts, dates) but does not state that the operation is read-only, harmless, or requires any authentication. For a list operation, this is a minimal disclosure.
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 extremely concise: two sentences, front-loaded with the core purpose, followed by a brief list of output fields. Every word adds value without 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 tool's low complexity (no parameters, no nested objects) and the presence of an output schema, the description is largely complete. It explains what the tool lists and what fields are returned. It could mention that only currently monitored projects are included, but that is implied by 'registered for vulnerability monitoring'.
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 tool has zero parameters, so schema coverage is 100% and no parameter documentation is needed. The description adds value by specifying the output fields (project names, IDs, package counts, registration dates), though this pertains to output rather than parameters. The baseline for zero-parameter tools is 4.
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: 'List all projects registered for vulnerability monitoring.' It specifies the verb (List) and resource (projects registered for vulnerability monitoring), and distinguishes itself from sibling tools like monitor_project (which adds monitoring) and unmonitor_project (which removes monitoring).
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 does not explicitly state when to use this tool versus alternatives like check_alerts or scan_project. However, the tool's purpose is straightforward and the sibling names imply that this is the listing tool. Some guidance on prerequisites (e.g., needing monitoring set up) is absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up detailed information about a specific vulnerability.
Returns full details including severity, EPSS exploit probability, affected packages, fix versions, and references.
Args: cve_id: Vulnerability ID (e.g. "CVE-2024-29041", "GHSA-rv95-896h-c2vc").
| Name | Required | Description | Default |
|---|---|---|---|
| cve_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes return fields but does not explicitly state read-only behavior, authentication, or error handling. The verb 'look up' implies safety, but explicit disclosure 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?
The description is concise with front-loaded purpose and a clear list of return fields. The 'Args' section is slightly formal but efficient. No redundant sentences.
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 simple 1-parameter tool and presence of an output schema, the description adequately explains what it does and returns. It does not cover error cases, but for a lookup tool, the essentials are covered.
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 0%, but the description fully compensates by documenting the cve_id parameter with an example format (CVE-2024-29041, GHSA-rv95-896h-c2vc). This adds critical meaning beyond the schema type string.
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 'Look up detailed information about a specific vulnerability', using a specific verb and resource. It distinguishes from sibling tools like scan_lockfile or check_alerts by focusing on a single CVE lookup.
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 alternatives (e.g., scanning a lockfile). The purpose is implied but not stated as 'use when you have a CVE ID'. Sibling names provide context, but the description itself lacks usage directives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Register a project for continuous vulnerability monitoring.
Scans the project's lockfiles, records the current vulnerability baseline, and stores a snapshot. Use check_alerts later to see new vulnerabilities that appeared since registration.
Args: project_path: Path to the project root. Defaults to current directory. project_name: Human-readable name for the project. Defaults to directory name.
| Name | Required | Description | Default |
|---|---|---|---|
| project_path | No | . | |
| project_name | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that the tool scans lockfiles, records a baseline, and stores a snapshot. This adequately conveys the stateful nature of registration. However, it does not specify idempotency or behavior if already registered, which is a minor gap.
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 front-loaded with a clear purpose, followed by a concise process explanation, and then parameter documentation. Every sentence adds value, with no unnecessary content.
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 moderate complexity (2 optional params, output schema exists), the description fully covers registration workflow, parameter meanings, and integration with check_alerts. It is complete 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 0%, so description must compensate. It fully documents both parameters: project_path (path, defaults to current directory) and project_name (human-readable name, defaults to directory name). This adds essential meaning beyond the schema's titles and defaults.
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 action ('Register a project for continuous vulnerability monitoring') and details the process (scans lockfiles, records baseline, stores snapshot). It distinguishes itself from siblings like check_alerts and scan_lockfile by implying it is the registration step for continuous monitoring.
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 explicitly tells the agent to use check_alerts later to see new vulnerabilities, indicating a proper workflow. Although it doesn't explicitly mention when not to use it, the description implies it is for setting up ongoing monitoring, which provides adequate guidance.
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 known vulnerabilities.
Reads a package lockfile (package-lock.json, requirements.txt, go.sum), queries NVD + GitHub Advisories, enriches with EPSS exploit probability, and returns a prioritized vulnerability report with fix recommendations.
By default, suppresses low-priority CVEs (EPSS < 10% and CVSS < 9). Set show_all=True to see every vulnerability.
Args: lockfile_path: Absolute path to the lockfile to scan. show_all: Show all vulnerabilities including low-priority ones.
| Name | Required | Description | Default |
|---|---|---|---|
| lockfile_path | Yes | ||
| show_all | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes the scanning process: reads lockfile, queries NVD and GitHub Advisories, enriches with EPSS, returns prioritized report. Mentions default suppression of low-priority CVEs. No contradictions with annotations (none provided).
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?
Concise, well-structured description with a summary paragraph followed by argument details. No 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?
Comprehensive for a scanning tool: covers input, process, default behavior, and output (report). Output schema exists, so return values are documented elsewhere.
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?
Explains both parameters: lockfile_path requires an absolute path, show_all controls visibility of low-priority vulnerabilities. Adds meaning beyond schema (0% coverage in schema descriptions).
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?
Clearly states 'Scan a lockfile for known vulnerabilities' and specifies supported lockfile types. Differentiates from sibling tools like scan_project and lookup_cve.
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?
Provides context on default filtering behavior and how to override (show_all). Lacks explicit comparison to alternatives but is still clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Auto-detect and scan all lockfiles in a project directory.
Walks the project directory looking for lockfiles (package-lock.json, requirements.txt, go.sum, etc.) and scans each one. Skips node_modules, .git, and vendor directories.
By default, suppresses low-priority CVEs (EPSS < 10% and CVSS < 9).
Args: project_path: Path to the project root. Defaults to current directory. show_all: Show all vulnerabilities including low-priority ones.
| Name | Required | Description | Default |
|---|---|---|---|
| project_path | No | . | |
| show_all | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses directory traversal, directory exclusions, and default vulnerability filtering. With no annotations, the description handles transparency well, though additional info on mutation or auth would be beneficial.
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?
Efficient, front-loaded summary followed by concise parameter descriptions. No unnecessary text.
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?
Covers all essential aspects given moderate complexity and presence of output schema. Could mention interaction with remote repos.
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?
Both parameters are fully described with defaults and behavior, compensating for 0% schema coverage. Adds meaning beyond raw 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?
Description clearly states it auto-detects and scans all lockfiles in a project directory, specifying types and distinguishing from siblings like scan_lockfile which scans a single file.
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?
Provides context on when to use (full project scan) and mentions skipped directories, but lacks explicit alternatives or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Remove a project from vulnerability monitoring.
Deletes the stored dependency snapshot and vulnerability baseline.
Args: project_id: The project ID to remove.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool is destructive (deletes snapshot and baseline), which is important. However, it does not mention whether the action is reversible, required permissions, or error conditions (e.g., if project is not monitored). With no annotations, more details would be beneficial.
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 (two sentences plus an Args line) and front-loaded with the main purpose. It is appropriately sized but could be slightly more structured with bullet points.
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 destructive tool, the description covers the basic operation and outcomes. However, it lacks details on prerequisites (e.g., project must be monitored), return values, or side effects. Given the existence of an output schema, return values are not required, but preconditions are 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 coverage is 0%, so the description should add meaning to parameters. It only restates 'project_id: The project ID to remove,' which adds no new information beyond the schema's name and type. It does not clarify format, constraints, or relationship to other tools.
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 removes a project from vulnerability monitoring, and explicitly mentions it deletes the stored dependency snapshot and vulnerability baseline. This distinguishes it from siblings like monitor_project (which adds monitoring) and scan_* (which scan).
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 is provided on when to use this tool versus alternatives, such as when a project should be unmonitored as opposed to other operations. The description only states what it does, without contextual usage cues.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update a monitored project's dependency snapshot after upgrading packages.
Re-reads lockfiles from the project directory and updates the stored dependency list. Preserves vulnerability history: existing known vulns that still apply are kept; new vulns from upgraded deps are flagged; vulns from removed deps are marked resolved.
Args: project_id: The project ID to update. project_path: Path to the project root. Defaults to current directory.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | ||
| project_path | No | . |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It details re-reading lockfiles, updating stored deps, and vulnerability history handling (keep, flag, resolve). Fully transparent within its scope.
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?
Three sentences plus an Args list. No waste. First sentence states purpose, second expands behavior, third lists parameters. Well-structured 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?
Covers purpose, behavior, and parameters. Missing explicit mention of prerequisites (e.g., project must be monitored). Output schema exists, so return values need not be explained. Slight gap, but acceptable.
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 has 0% description coverage; description adds explicit meanings for both parameters: project_id is 'The project ID to update' and project_path is 'Path to the project root. Defaults to current directory.' This adds significant value.
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?
Clear verb ('update') and resource ('dependency snapshot'). Specifies context 'after upgrading packages', distinguishing from siblings like check_alerts or scan_lockfile.
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?
States when to use ('after upgrading packages'), but lacks explicit guidance on alternatives or when not to use. The context is clear enough for an agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool targets a distinct operation: single package check, lockfile scan, project scan, monitoring lifecycle, and CVE lookup. No two tools have overlapping purposes.
All tool names follow a consistent snake_case verb_noun pattern (e.g., check_alerts, monitor_project, scan_lockfile) without deviations.
9 tools is well-scoped for a vulnerability scanning and monitoring server. Each tool serves a clear, justified purpose without bloat or deficiency.
Core workflows (scan, monitor, alert, update, unmonitor) are covered. Missing a tool to list all current vulnerabilities for a monitored project without triggering a new scan, but this is a minor gap.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Supply chain risk scoring for npm, PyPI, Cargo, and Go. 9 tools. Behavioral signals.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/novadyne-hq/vulnfeed-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server