Skip to main content
Glama
Sign In

SCRIPTMASTERLABS — Cascade Graph

by com.scriptmasterlabs
OverviewDiscussionsAdmin

Server Details

Cascade Graph MCP: macro decision capsules + Jev jury review over a hash-chained calibration log.

Ownership verified

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
0.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

B3.4/5.0

Scored across 4 tools

Disambiguation4/5

The four tools have mostly distinct purposes: analysis, capsule creation, juror review, and status inspection. However, cascade_analyze and cascade_review_jev both involve evidence-based evaluation, so an agent could briefly hesitate between them despite the descriptions clarifying the distinction.

Naming Consistency4/5

All tools use the cascade_ prefix, which creates a predictable namespace. The suffixes vary between verbs and nouns (analyze, capsule, review_jev, status), but the convention remains readable and mostly consistent.

Tool Count5/5

Four tools is well-scoped for a focused deterministic analysis and review server. Each tool earns its place by covering a distinct stage: analysis, capsule generation, juror review, and status inspection.

Completeness3/5

The surface covers core workflow stages, but notable gaps remain: there is no explicit capsule retrieval or verification tool, and no evidence ingestion or review-result lifecycle management. Agents may be able to work around these through external state, but the lifecycle is not fully represented.

Available Tools

4 tools
cascade_analyzeAnalyze Cross-Market EvidenceC
Read-onlyIdempotent
Inspect

Run deterministic evidence-bounded market analysis. Does not execute trades.

Inputs: evidence (required), instrument (required).

cascade_capsuleBuild Decision CapsuleC
Read-onlyIdempotent
Inspect

Build a deterministic SHA256 Decision Capsule from admitted Cascade state. No model spend.

Inputs: evidence (required), instrument (required), observed_at (required).

cascade_review_jevRun BYOK Jev Jury ReviewAInspect

Run up to five Jev by TypeSafe AI jurors on supplied Cascade evidence using the caller key in X-JEV-API-KEY. Requires model_spend_authorized=true. Deterministic vetoes skip provider calls. Returns shadow research review; never submits trades, signs payments, or uses an operator key.

Inputs: evidence (required), instrument (required), observed_at (required), model_spend_authorized (required).

cascade_statusCascade Graph StatusA
Read-onlyIdempotent
Inspect

Inspect Cascade Graph build/runtime truth without model spend or trade execution.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • sealedrun

      sealedrunofficial

      sealedrun
      A
      license
      Not graded
      quality
      B
      maintenance
      Tamper-evident recorder for AI agent tool calls. Every MCP call is written to a hash-chained, signed log the agent cannot edit, delete or hide; anyone can verify the chain offline.
      Apache 2.0
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources