VulnFeed
PYPI · VULNFEED-MCP · SCANNED SEP 20
Dependency vulnerability scanner with EPSS scoring. 9 MCP tools. Free tier + x402.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 29 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability76
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1199 tokens (~119/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "unmonitor_project" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the VulnFeed MCP server?
VulnFeed runs locally as a PyPI package, launched with uvx vulnfeed-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · vulnfeed-mcp
claude mcp add novadyne-hq-vulnfeed -- uvx vulnfeed-mcp
{
"mcpServers": {
"novadyne-hq-vulnfeed": {
"command": "uvx",
"args": [
"vulnfeed-mcp"
]
}
}
} {
"servers": {
"novadyne-hq-vulnfeed": {
"command": "uvx",
"args": [
"vulnfeed-mcp"
]
}
}
} codex mcp add novadyne-hq-vulnfeed -- uvx vulnfeed-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"novadyne-hq-vulnfeed": {
"type": "local",
"command": [
"uvx",
"vulnfeed-mcp"
],
"enabled": true
}
}
} openclaw mcp add novadyne-hq-vulnfeed --command uvx --arg vulnfeed-mcp
mcp_servers:
novadyne-hq-vulnfeed:
command: "uvx"
args: ["vulnfeed-mcp"] {
"McpServers": {
"novadyne-hq-vulnfeed": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"vulnfeed-mcp"
]
}
}
} assistant mcp add novadyne-hq-vulnfeed -t stdio -c uvx -a vulnfeed-mcp
{
"mcpServers": {
"novadyne-hq-vulnfeed": {
"command": "uvx",
"args": [
"vulnfeed-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 19 Sept 26 +13
- Malware scan: pass → unverified ▼ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Tool coverage: 0 functional
- First check of Schema quality: fail functional
- First check of Schema quality: excellent functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: 0 functional
- First check of Tool coverage: 100 functional
- Package version: 0.3.7 → 0.3.9 functional
- Package version: 0.3.7 → 0.3.8 functional
- 18 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 16 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- 14 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 31 Aug 26 −15
- Malware scan: pass → unverified ▼ security
- 30 Aug 26 +15
- Malware scan: unverified → pass ▲ security
- 27 Aug 26 0
- Security disclosure: unverified → fail ▼ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/vulnfeed-mcp@0.3.9
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 29 packages
| Packages resolved | 29 |
|---|---|
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_alerts ~74
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 | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
check_package ~142
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", "Go", "crates.io", "RubyGems", or "Packagist". Defaults to "npm". show_all: Show all vulnerabilities including low-priority ones.
| Name | Type | Req | Description |
|---|---|---|---|
| ecosystem | string | – | – |
| name | string | yes | – |
| show_all | boolean | – | – |
| version | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
list_monitored ~30
List all projects registered for vulnerability monitoring. Shows project names, IDs, package counts, and registration dates.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
lookup_cve ~84
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 | Type | Req | Description |
|---|---|---|---|
| cve_id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
monitor_project ~247
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. With webhook_url set, VulnFeed re-scans the project on a schedule (hourly on the paid tier, daily on the free tier) and POSTs any NEW findings to that URL as JSON, signed with HMAC-SHA256 in the X-VulnFeed-Signature header using the webhook_secret returned here — once. Without it, monitoring is pull-only: nothing happens until check_alerts is called. Args: project_path: Path to the project root. Defaults to current directory. project_name: Human-readable name for the project. Defaults to directory name. webhook_url: Optional https URL to receive new findings (CI hook, Slack/Discord relay, your own endpoint). Must be a public https hostname. Requires VULNFEED_API_KEY (webhooks are a paid feature).
| Name | Type | Req | Description |
|---|---|---|---|
| project_name | string | – | – |
| project_path | string | – | – |
| webhook_url | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
scan_lockfile ~139
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 | Type | Req | Description |
|---|---|---|---|
| lockfile_path | string | yes | – |
| show_all | boolean | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
scan_project ~129
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 | Type | Req | Description |
|---|---|---|---|
| project_path | string | – | – |
| show_all | boolean | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
set_webhook ~109
Set, rotate or remove the webhook for a monitored project. Setting a URL (even the same one) mints a NEW signing secret and returns it once. Passing an empty webhook_url removes the webhook; monitoring continues pull-only via check_alerts. Args: project_id: Project ID from monitor_project / list_monitored. webhook_url: https URL to receive new findings, or "" to remove.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | – |
| webhook_url | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
unmonitor_project ~45
Remove a project from vulnerability monitoring. Deletes the stored dependency snapshot and vulnerability baseline. Args: project_id: The project ID to remove.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
update_deps ~114
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 | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | – |
| project_path | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
What is the VulnFeed MCP server?
VulnFeed is an MCP server listed in the public MCP registry as io.github.novadyne-hq/vulnfeed. Dependency vulnerability scanner with EPSS scoring. 9 MCP tools. Free tier + x402. This page covers its PyPI package (vulnfeed-mcp).
Is the VulnFeed MCP server safe to use?
VulnFeed scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the VulnFeed MCP server expose?
VulnFeed exposes 10 tools: scan_lockfile, check_package, lookup_cve, scan_project, monitor_project, and 5 more. Their descriptions and schemas cost roughly 1,113 tokens of context every time the server is loaded.
Is the VulnFeed MCP server still maintained?
VulnFeed is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the VulnFeed MCP server under?
VulnFeed declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.