MCPAmpel
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCPAMPEL_API_KEY | Yes | Your API key (free at mcpampel.com) | |
| MCPAMPEL_BASE_URL | No | API base URL | https://mcpampel.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_my_serversA | Discover all MCP servers installed in your editor/agent config (Claude Code, Cursor, Windsurf, Gemini CLI) and scan them for security issues with 16 engines. Returns trust scores. |
| scan_urlA | Scan a single URL (GitHub, GitLab, npm, or PyPI) for security issues with 16 engines. |
| check_statusA | Show your daily quota usage and remaining scans. |
| get_scan_resultsB | Get full detailed results for a specific scan by its ID. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: quota checking, local server scanning, URL scanning, and result retrieval. No functional overlap exists between the four tools.
Tools follow a consistent snake_case pattern with leading action verbs (check, get, scan). Minor deviation with 'scan_my_servers' including the possessive pronoun 'my' while others use direct nouns (scan_url, get_scan_results).
Four tools is an appropriate, focused count for a security scanning service covering status checks, two distinct scan targets (local servers vs remote URLs), and result retrieval.
Core scanning workflows are present, but the absence of a list_scans tool creates a notable gap—agents cannot discover historical scan IDs without perfect memory of previous scan operations, limiting the utility of get_scan_results.