PrufGate MCP
OfficialServer 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 |
|---|---|
| prufgate_fast_scanA | Run engines 1-5 (anti-fabrication, test integrity, diff guard, contract guard, static BOLA) on changed files. |
| prufgate_full_scanA | Run engines 1-5 on the whole workspace plus the diff reviewer; adds the live BOLA probe only when target_url is set. |
| prufgate_anti_fabricationC | Engine 1: canned fallbacks, simulated return values, stub handlers and other fabricated production logic. |
| prufgate_test_auditC | Engine 2: zero-assertion tests, tautologies, self-mocked units and weakened assertions. |
| prufgate_diff_guardC | Engine 3: skipped tests, suppression comments, unsafe casts and weakened lint/CI config added in the diff. |
| prufgate_contract_checkC | Engine 4: undeclared or hallucinated imports, undocumented environment variables and frontend/backend route mismatches. |
| prufgate_bola_checkB | Engine 5: routes and queries without auth or tenant scoping; the live two-token probe runs only when target_url is set. |
| prufgate_reviewC | Engine 6: deterministic review of the diff against base_ref (default: resolved like prufgate check --changed). |
| prufgate_summaryA | Read the last SARIF/Markdown report written by ./prufgate.sh without running a scan. |
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
Each engine (1-6) has a dedicated tool with a specific purpose, and fast_scan vs. full_scan differ clearly by scope (changed files vs. whole workspace). Minor ambiguity remains between running an individual engine tool and the aggregate fast_scan/full_scan, and between prufgate_review and the diff-related engines, but descriptions clarify the boundaries.
All tools share a consistent prufgate_ prefix and snake_case suffixes, which is predictable and readable. However, the suffixes are feature/engine nouns (anti_fabrication, test_audit, summary) rather than a uniform verb_noun pattern, so it falls slightly short of a strict convention.
Nine tools is well-scoped for a scanner with six engines plus summary and aggregate scan modes, and each tool earns its place with a distinct granularity (single engine, fast, full, summary).
The surface covers the full scan lifecycle: individual engines, changed-file and full-workspace scans, diff review, and reading the last report. Gaps include no tools for configuring thresholds/rules, managing baselines, or retrieving individual findings structurally, but core workflows are covered.