Skip to main content
Glama

MUJ428 Trust Layer — Bind Approved Intent to Verified Effect

Server Details

Payment-rail-independent intent-to-effect integrity for consequential agent actions.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.6/5.0

Scored across 2 tools

Disambiguation5/5

The two tools serve clearly distinct roles: one provides requirements/information, the other performs the decision/verification action. No overlap exists, so an agent should never confuse which tool to call for a given step.

Naming Consistency4/5

Both tool names use a verb-led snake_case pattern ('get_evidence_signal_requirements', 'trust_action'), but 'trust_action' is less standard as a verb phrase. The two names are generally consistent and predictable.

Tool Count3/5

With only two tools, the surface feels thin even for a specialized trust layer. The count is acceptable for a narrowly scoped server, but it hovers at the borderline where more operational tools would likely be needed.

Completeness2/5

The server promises to bind intent to verified effect, yet there is no obvious tool for submitting evidence, recording completed actions, or retrieving past trust receipts. The current surface covers upfront requirements and one-shot decisions, but leaves the verification loop incomplete.

Available Tools

2 tools
get_evidence_signal_requirementsEvidence Signal RequirementsA
Read-onlyIdempotent
Inspect

Returns MUJ428 evidence-check payment, network, endpoint, and assurance-pricing requirements before an autonomous payment.

Inputs: no named parameters.

trust_actionMUJ428 Trust ReflexA
Read-onlyIdempotent
Inspect

VERIFY BEFORE ACT across payments, purchases, delegation, approvals, writes, releases, commits, and other consequential actions. Returns ALLOW, VERIFY, REQUIRE_VERIFICATION, or DENY plus Trust Receipt v1.3; FREE_PREFLIGHT execution_authority=false and no funds are moved.

Inputs: action (required), evidence, external, milestone, +12 more.

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

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to use payment APIs safely by gating every tool call through deterministic mandates, value checks, and an exactly-once ledger, so they cannot pay twice or exceed authorisation.
      36 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enforces verifiable authorization, budgets, approvals, and audit trails between an agent and merchant/payment MCP servers, so that the legality of an entire transaction — not just a single call — is checked before money moves. Adds default-deny policy, two-phase budget reserve/commit, action-bound approvals, transaction guards against double-charging or unpaid fulfillment, result sanitization, and tamper-evident hash-chain evidence.
      2
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources