ctxray
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CTXRAY_DEFAULT_BUDGET | No | Default token budget used by the ctxray MCP server tools. This environment variable is optional; the npx example runs without it. | 32000 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ctxray_repo_mapC | Compute the Dependency PageRank architectural map and token distribution of a repository within a target token budget. |
| ctxray_blast_radiusB | Analyze the upstream and downstream dependency blast radius of modifying a specific file or module. |
| ctxray_skeletonizeA | Compress a source file into an AST signature skeleton (preserving types, interfaces, signatures, and docstrings while folding function bodies). |
| ctxray_forensicsB | Run Tarjan SCC circular dependency detection, architectural layer violation checks, Git churn hotspot analysis, and Mermaid graph compilation on a repository. |
| ctxray_init_rulesB | Auto-generate repository-specific CLAUDE.md, AGENTS.md, and .cursor/rules/architecture.mdc based on live Dependency PageRank hotspots and circular dependency diagnostics. |
| ctxray_traceB | Analyze AI coding agent session JSONL logs (Claude Code, Codex, Cursor) to pinpoint context bloat offenders, prompt-cache breaks, and token/USD savings. |
| ctxray_packB | Compile a repository into a cache-pinned, secret-redacted LLM context bundle (xml or md). |
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 7 tools
Each tool targets a distinct operation: mapping, blast-radius analysis, file compression, diagnostics, rule generation, session tracing, and context bundling. Some conceptual overlap exists between repo_map, forensics, and pack around repository analysis, but the descriptions make the boundaries usable.
All names share the ctxray_ prefix and snake_case, but the verb/noun pattern is inconsistent (e.g., skeletonize vs repo_map, forensics vs init_rules). Mixing verbs, nouns, and compound nouns reduces predictability.
7 tools is well within the 3–15 range for a repository-analysis server. Each tool has a distinct function, so there is no obvious bloat or thinness.
The surface covers mapping, change-impact analysis, file compression, diagnostics, rule generation, session tracing, and context packing—core workflows for an AI coding context tool. Minor gaps exist, such as no tool for validating or updating generated rules, but nothing that blocks core usage.