MCP Shamash
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SHAMASH_AUDIT_LOG_PATH | No | Audit log location | ./audit.log |
| SHAMASH_MAX_TOKENS_PER_HOUR | No | Hourly token limit | 50000 |
| SHAMASH_MAX_TOKENS_PER_SCAN | No | Token limit per scan | 1000 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_projectC | Performs comprehensive security scan on project directory |
| scan_networkC | Performs network scanning within project boundaries |
| pentest_applicationC | Performs penetration testing on deployed applications |
| check_complianceC | Validates project against compliance frameworks |
| generate_remediationC | Generate actionable remediation advice for findings |
| manage_false_positivesC | Manage false positive suppressions |
| manage_custom_rulesC | Manage custom security rules |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| security_review | Comprehensive security review prompt |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Scan Results | Access detailed scan results |
| Compliance Reports | Access compliance validation reports |
TDQS
Scored across 7 tools
Most tools have distinct purposes targeting different security activities (compliance, remediation, rule management, false positives, pentesting, network scanning, project scanning), though 'scan_network' and 'scan_project' could potentially overlap in scope if network scanning is part of project scanning. The descriptions help clarify their boundaries, with only minor ambiguity.
Tools follow a consistent verb_noun pattern throughout (e.g., check_compliance, generate_remediation, manage_custom_rules), with all using snake_case. The only deviation is 'pentest_application' which uses 'pentest' as a verb instead of a more standard verb like 'perform_pentest', but this is minor and still readable.
With 7 tools, the count is well-scoped for a security-focused server, covering key areas like scanning, testing, compliance, and management. Each tool appears to earn its place without feeling too thin or bloated, fitting typical server tool ranges (3-15 tools).
The toolset provides good coverage for security operations, including scanning (network and project), testing (pentest), compliance validation, remediation generation, and rule/false positive management. Minor gaps might include tools for reporting results or integrating with external systems, but core workflows are well-covered and agents can likely work around these omissions.