Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEFAUDIT_URLYesThe base URL of your DefAudit installation, e.g. https://defaudit.example.com
DEFAUDIT_TIMEOUTNoHTTP timeout in seconds.30
DEFAUDIT_APP_TOKENYesPersonal app token from DefAudit (Settings → Profile → Personal app token). Acts as its owner.
DEFAUDIT_VERIFY_TLSNoSet to 'false' only for a trusted development instance using a self-signed certificate.true

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_projectsA

List active DefAudit projects and their most recent scan.

start_scanA

Start a security scan for an existing project. Omit branch to use the project default.

list_scansA

List recent scans for a project. Limit must be between 1 and 100.

get_scanB

Read scan status, progress, timestamps, and severity summary.

get_scan_resultsA

Read completed scan findings, including each finding's false-positive status.

mark_false_positiveB

Mark a finding and matching findings in the project as false positives. A reason is required.

unmark_false_positiveA

Remove the false-positive flag from a finding and matching findings in the project.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 7 tools

Disambiguation5/5

Each tool targets a distinct action and resource: projects vs scans vs findings, with clear separation of listing, starting, reading status/results, and managing false positives. No overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case (e.g., list_projects, start_scan, mark_false_positive). The pattern is uniform and predictable.

Tool Count5/5

Seven tools cover the core scanning and false-positive management workflow without unnecessary bloat. The set is well-scoped for a security audit MCP server.

Completeness4/5

The surface covers project listing, scan initiation/status/results, and false-positive toggling. Minor gaps exist (e.g., no stop_scan or project creation), but the primary workflows are complete and no critical dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues