mcp-skylos
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyzeD | – |
| security_scanD | – |
| quality_checkD | – |
| secrets_scanD | – |
| remediateD | – |
| verify_dead_codeD | – |
| provenance_scanD | – |
| generate_fixD | – |
| learn_triageD | – |
| get_triage_suggestionsD | – |
| validate_code_changeA | Validate a code diff for security regressions and issues before it lands. Takes a unified diff and checks for:
Returns pass/fail with findings. |
| get_security_contextD | – |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_latest_result | |
| list_results |
TDQS
Scored across 12 tools
Multiple tools appear to overlap in purpose, such as security_scan, secrets_scan, provenance_scan, and quality_check, all of which could be interpreted as scanning or checking code. Without detailed descriptions, an agent could easily misselect among these. Other tools like analyze and get_security_context also have ambiguous boundaries.
All names use snake_case consistently, but the pattern is mixed: some start with a verb (remediate, verify, get, generate, validate, learn), while others start with a noun (security_scan, secrets_scan, provenance_scan, quality_check). This inconsistency could confuse agents expecting a uniform verb_noun structure.
With 12 tools, the server is well within the typical 3-15 range for a security/quality scanning and remediation service. The count feels appropriate for the apparent scope, covering scanning, triage, fixing, and validation without being overwhelming.
The tool set covers a reasonable lifecycle for security scanning and remediation: scanning (security_scan, secrets_scan, provenance_scan, quality_check), analysis (analyze, get_security_context), triage (get_triage_suggestions, learn_triage), fixing (generate_fix, remediate), and validation (validate_code_change). Minor gaps like explicit reporting or configuration are not critical to the core workflow.