ghost-audit-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GHOST_DATASET | No | Path to the dataset directory to audit. Can also be set with the option --dataset DIR. When omitted, the bundled synthetic demo dataset ("Lumen Lane Books") is used. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ghost_describeA | Call first. Capabilities, glossary of statuses/phases/operations, field meanings and known limits. |
| ghost_summaryA | Portfolio view: verified/claimed status counts, claimed->verified transitions (false COMPLETE), top risk categories, violations by system, manual-review counts. Good for dashboards and executive briefs. |
| ghost_list_casesA | Filter cases; returns compact rows (status, risks, steps, confidence, needs_manual_review). Use before ghost_get_case. |
| ghost_get_caseA | Full context of one case: request, subject and identifier history, resources with rule/proof/link/activity ids, planned steps, review signals and why claimed differs from verified. |
| ghost_explain_caseA | Deterministic 8-15 line markdown narrative of one decision with [evidence/activity] citations. Quote it, do not paraphrase facts. |
| ghost_get_evidenceA | Metadata of an evidence file (path, origin, captured_at, resources seen) and a text snippet from the file or OCR cache; binaries are never returned. |
| ghost_review_queueA | Prioritised human review queue (withheld/ambiguous links, inferred states, false COMPLETE with active risk) with reasons, a score and confidence_v2 (a review-priority signal, not a probability). |
| ghost_whatifA | In-memory re-run with another MIN_PICK_CONFIDENCE (default 0.30): which cases would change or become manual (~1 s), and/or which cases a confidence_v2 review threshold would route to a human. Never writes output.csv. |
| ghost_ingest_reportA | Ingestion diagnostics: evidence files that could not be parsed, ignored rows/log lines, CSV issues and cases degraded to INCOMPLETE + needs_manual_review. Empty on the shipped dataset. |
| ghost_verify_outputB | Structural validation of output.csv (contract, vocabulary, ids, phase order) plus sha256 and status counts. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| review_deletion_case | Review one deletion case and build a case card. |
| executive_brief | One-page DPO brief from the portfolio summary. |
| triage_queue | Interactive triage of the review queue. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| summary | portfolio summary |
| queue | review queue (top 25) |
| describe | capabilities and glossary |
TDQS
Scored across 10 tools
Each tool targets a distinct task: describe (glossary), summary (portfolio), list_cases (filter rows), get_case (full case context), explain_case (narrative with citations), get_evidence (file metadata/snippet), review_queue (human queue), whatif (re-run simulation), ingest_report (ingestion diagnostics), verify_output (contract validation). The read-side case tools (list/get/explain) operate at clearly different granularity and the descriptions even guide sequencing ('Use before ghost_get_case').
All names share the consistent 'ghost_' prefix and snake_case convention, which is good. Most are verb_noun (get_case, list_cases, explain_case, verify_output, ingest_report), but a few are noun/other-style (summary, review_queue, whatif), a minor deviation from a strict pattern.
Ten tools is well within the ideal range and each earns its place: reporting, per-case inspection, evidence access, review, simulation, ingestion, and validation are all non-redundant functions. No filler tools present.
The audit/verification lifecycle is well covered: ingestion diagnostics, portfolio summary, case listing/inspection/explanations, evidence, review queue, what-if simulation, and output validation. Minor gaps exist—no tool to retrieve full evidence content (binaries intentionally withheld) and no write/resolve action for review items, but these reflect deliberate read-only design.