Scopewalker MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCOPEWALKER_ALLOWED_ROOTS | No | Comma-separated list of absolute paths that tools are allowed to operate on. Defaults to current working directory and system temp. |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_line_countsB | Returns file line counts (code/blank/comment). Use extensions to filter. |
| get_functionsA | Returns function/method info. Use detail=lines for line counts per function. |
| check_thresholdsC | Finds files/functions exceeding size thresholds. Use limit to control output. |
| get_code_inventoryC | Lists classes, functions, methods, and exports. Use extensions to filter. |
| get_code_smellsB | Finds TODO/FIXME/HACK/BUG markers and unsafe casts in code. |
| get_complexity_metricsC | Returns complexity metrics (nesting, params, cognitive, per-function cyclomatic). Use limit/summary_only to control output. |
| get_documentation_coverageC | Finds undocumented functions/classes. Use limit/summary_only to control output. |
| get_prop_drillingB | Detects parameter threading (prop drilling) by finding parameter names passed through chains of functions. Use limit/summary_only to control output. |
| find_dead_codeC | Finds declared symbols that nothing references. dead_code is proven unreachable within the scan; unreferenced_exports may be used outside it. |
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 9 tools
Most tools target a distinct static-analysis concern (line counts, complexity, smells, dead code), and the descriptions clarify their purpose with filters and detail options. There is slight overlap between get_functions and get_code_inventory, and between line-count reporting and threshold checking, but an agent can usually disambiguate with context.
Tool names consistently use lowercase snake_case and mostly follow a get_<noun> pattern such as get_line_counts and get_complexity_metrics. The deviations check_thresholds and find_dead_code still use clear verb_noun naming, so the overall pattern remains predictable.
Nine tools is a well-scoped size for a code-analysis MCP server. Each tool covers a distinct inspection area without unnecessary redundancy or bloat.
The tool set covers the major static-analysis workflows: size, structure, functions, complexity, code smells, documentation coverage, prop drilling, and dead code. A minor possible gap is dependency or import-level analysis, but the surface appears largely complete for its stated scope.