Schema | scopeguard-mcp

scopeguard-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`SCOPEGUARD_MAX_FILES`	No	Repository scan file ceiling	5000
`SCOPEGUARD_STATE_DIR`	No	SQLite state and audit database	<cwd>/.scopeguard
`SCOPEGUARD_ALLOWED_ROOTS`	No	Path-separated operator allowlist	current directory
`SCOPEGUARD_MAX_FILE_BYTES`	No	Per-file read ceiling	1000000
`SCOPEGUARD_EXECUTION_ENABLED`	No	Enables execute engagements when true	false

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
healthA	Return server safety settings, capabilities, and audit-chain health.
create_dry_run_engagementA	Create a non-executing assessment scope; execute mode is operator-CLI only.
revoke_engagementB	Immediately revoke an engagement and prevent further target operations.
check_scopeA	Normalize a target and report whether it is inside the engagement scope.
plan_assessmentA	Create a bounded web or repository assessment plan without running network tools.
analyze_headersA	Analyze caller-supplied response headers offline; no HTTP request is performed.
scan_repositoryA	Run built-in read-only Python and secret checks under operator-allowed roots.
list_audit_eventsA	Return recent audit events when the engagement includes audit:read.
verify_audit_chainA	Verify every persisted event against the tamper-evident hash chain.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mzatylny/scopeguard-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server