A
licenseNot graded
qualityA
maintenanceDeterministic, auditable payment policy enforcement for AI agents. It provides pre-action authorization with scopes, budgets, allowlists, and signed mandates via an MCP server.
MIT
spendshield
Related Servers
Alternatives to spendshield
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceGoverns AI agents' spending by enforcing budgets, approvals, and kill switches before any payment, providing an MCP interface for tool calls with policy checks.1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceMCP Guard Server - Budget control, approval workflows and audit logging for AI agents (Claude Code, Cursor, ChatGPT)MIT
- FlicenseNot gradedqualityBmaintenanceAn MCP server that enables AI agents to safely interact with a double-entry payments ledger, enforcing idempotency, policy-based access control, and human-in-the-loop approval for high-value actions.-
- AlicenseNot gradedqualityCmaintenanceBudget & cost control for AI agents: hard per-agent spend caps, rate limits, idempotency, and human-in-the-loop approval — enforced before each LLM call, not after the invoice. One hosted MCP endpoint (no proxy or self-hosting), settled via x402 (USDC on Base).MIT
- FlicenseNot gradedqualityDmaintenanceRuntime agent firewall for PII redaction, rate limits, and policy enforcement, enabling autonomous agent security via MCP integration.-
TDQS
A3.8/5.0
Scored across 5 tools
Disambiguation5/5
Each tool targets a clearly distinct operation: status is a live snapshot, audit is historical records, reset is session state management, protect gates a spend, and secret_get retrieves a credential. No two tools plausibly serve the same purpose, and the descriptions make the boundaries obvious.
Naming Consistency4/5
The tools are all lowercase snake_case and mostly follow a domain-prefix pattern, with four sharing spend_ and one using secret_. The slight inconsistency is that the second segment mixes nouns and verbs, and secret_get breaks away from the spend_ namespace, so it is not as uniform as a strict verb_noun convention.
Tool Count5/5
Five tools is well-scoped for a spending-defense utility: status, audit, reset, protect, and secret retrieval each cover a necessary function without redundancy. There are no filler tools or obvious bloat.
Completeness4/5
The set covers the core lifecycle well: protect a spend, inspect status, review audit trails, reset session amounts, and safely retrieve secrets. The main gap is configuration management such as setting budgets, whitelists, or blacklists, but agents can still work within the existing guardrails.
Maintenance
ActivityMaintained
ResponsivenessResponsive