scan_project
Audit a project's dependencies in one shot. Returns a single-sentence verdict (e.g. "DO NOT INSTALL — 1 hallucinated: fastapi-turbo") that an agent can paste into its reply, plus per-package health/vulns/recommendation. Detects hallucinated packages, deprecated, typosquats, critical vulnerabiliti...
This record as markdown: /tools/dev-depscope-mcp/scan-project.md
What scan_project does on Depscope
AI agents call scan_project to retrieve information from Depscope without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
packages | object | Yes | Either ['express','lodash@4.17.0'] (single ecosystem, up to 100) or [{ecosystem, package}, …] (mixed, up to 50). |
ecosystem | string | — | Required when packages is a string array. |
Parameters from the server's own tool schema.
Why scan_project is rated Low
scan_project queries dependency metadata and vulnerability data to generate a health report. It does not create, modify, delete, or execute operations on packages or systems. The tool is fundamentally a data retrieval and analysis function that helps users understand their project's dependency security posture without taking any actions that would change state.
From the tool's definition Tool performs 'audit' and 'detection' operations that retrieve and analyze data: 'Detects hallucinated packages, deprecated, typosquats, critical vulnerabilities' and 'Returns a single-sentence verdict...
Attacks that exploit this kind of access
The rule that runs scan_project safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Depscope, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For scan_project, this is the rule to start with:
scan_project is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Depscope, apply this rule, and every scan_project call is checked against it from then on.
Questions about scan_project
Audit a project's dependencies in one shot. Returns a single-sentence verdict (e.g. "DO NOT INSTALL — 1 hallucinated: fastapi-turbo") that an agent can paste into its reply, plus per-package health/vulns/recommendation. Detects hallucinated packages, deprecated, typosquats, critical vulnerabilities. Accepts EITHER {ecosystem, packages:[name@ver, …]} (up to 100, returns JSON) OR {packages:[{ecosystem, package}, …]} (up to 50, mixed ecosystems, returns text brief). USE WHEN: user pastes package.json/requirements.txt/Cargo.toml; agent generated install command; 'is my stack OK'. RETURNS: JSON with verdict, project_risk, summary.hallucinated_packages, summary.deprecated_packages, per-package health. It is categorised as a Read tool in the Depscope MCP Server, which means it retrieves data without modifying state.
scan_project accepts 2 parameters: packages, ecosystem. Required: packages. The full parameter table on this page comes from the server's own tool schema.
Register the Depscope MCP server in PolicyLayer and add a rule for scan_project: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Depscope. Nothing to install.
scan_project is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the scan_project rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for scan_project. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
scan_project is provided by the Depscope MCP server (cuttalo/depscope-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Depscope, and thousands of servers like it.
This server
Across the catalogue