ctxfw
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| prune_fileA | Extract semantic interfaces, types, pydantic models, sanitized raises, and signatures from a source file while replacing procedural bodies with AST stubs. Use this when you only need to inspect contracts or APIs of an individual dependency without ingesting raw implementation code. Does not modify files on disk (pure in-memory AST operation). |
| resolve_context_bundleA | Calculate topological dependency graph distances (D0 full target, D1 interface stubs, D2 nominal symbols) for an active target file and compile a token-pruned Markdown context bundle. Use this as your primary context builder before editing a file in a multi-module project. For inspecting isolated files, use prune_file instead. Read-only operation. |
| evaluate_spec_axiomsA | Evaluate an architectural brief against formal determinism rules, negative invariant floors, and the Axiom Completeness Index (ACI 1.0000). Use this during intake or planning phases before writing code. Pure analytical evaluation with no side effects. |
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 3 tools
Each tool has a clearly distinct purpose: prune_file handles single-file interface extraction, resolve_context_bundle builds multi-module context, and evaluate_spec_axioms checks architectural specs. Cross-references in descriptions (e.g., 'use prune_file for isolated files') reinforce the boundaries, leaving no ambiguity.
All three tool names follow the same verb_noun snake_case convention: prune_file, resolve_context_bundle, evaluate_spec_axioms. The verbs are specific and match the action, making the pattern predictable and easy to follow.
Three tools is within the ideal 3-15 range and each earns its place. The server covers a focused workflow—file pruning, context resolution, and spec evaluation—without redundancy or bloat.
The tool surface covers the core pipeline (inspect single file, build context bundle, evaluate specs) with no obvious dead ends. Minor gaps exist like a dedicated tool for persisting or comparing context bundles, but agents can complete the core workflow without missing critical operations.