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.
Deterministic Context Firewall & Sovereign Pentad Verification Workflow:
Architectural Intake: Call
evaluate_spec_axiomson architectural briefs to verify determinism and negative invariants (ACI >= 0.9000).Context Assembly: Call
resolve_context_bundlefor multi-module topological dependency bundles (D0/D1/D2/D3) orprune_filefor single-file AST interface extraction.Pre-Merge Verification: Call
evaluate_patchon unified git diffs to enforce cyclomatic complexity budgets, type-ignore bans, import restrictions, and functional test gates.Forensic Audit Retrieval: Call
query_audit_ledgerto inspect persisted SWE-Gate evaluation records (EVL-...) or verify cryptographic SHA-256 hash-chained sessions (SES-...).
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 ( |
| resolve_context_bundleA | Calculate topological dependency graph distances (D0 full |
| evaluate_spec_axiomsA | Evaluate an architectural specification brief ( |
| evaluate_patchA | Verify a unified git diff patch ( |
| query_audit_ledgerA | Retrieve persisted SWE-Gate patch evaluation records and violation findings by |
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 5 tools
Each tool targets a distinct operation: single-file pruning, multi-module bundle compilation, spec evaluation, patch evaluation, and audit retrieval. Descriptions explicitly disambiguate boundaries, e.g. prune_file says 'for multi-module dependency graphs, use resolve_context_bundle instead' and evaluate_spec_axioms points to evaluate_patch for diffs.
All five tools use snake_case with a leading verb (prune_file, resolve_context_bundle, evaluate_spec_axioms, evaluate_patch, query_audit_ledger). The verb_noun pattern is predictable and the two evaluate_* tools share a consistent prefix for their judgment family.
Five tools is well-scoped for a context-bundling and verification framework: two for context generation, two for evaluation gates, one for audit. No tool looks redundant and none of the sub-capabilities appear padded.
The prune/bundle, spec-evaluate, patch-evaluate, and audit-query lifecycle forms a coherent closed loop, but session management is an implicit dependency: session_id (SES-...) is consumed as input with no tool to create or list sessions, and TokenCast budget state is referenced but never exposed.