"Actual Budget" matching MCP servers:

Drop-in stdio interceptor that gates MCP tools/call requests through a YAML policy (block / require_approval / audit / budget cap) before they reach the real server. The same policy file is reused by @jamjet/claude-code-hook and @jamjet/openai-guardrail, so one rule set covers Claude Desktop, Cursor, OpenAI Agents, and custom clients.

Enables agents to verify postal addresses, email addresses, and phone numbers against Melissa's Global Verification APIs before acting on the data, including batch verification and a per-session call budget to prevent runaway costs.

Analyzes all permission settings files for coding agents, showing which settings take precedence and identifying rules that are accepted but ignored. Helps users understand and debug their agent's actual permission behavior.

Governed AI-ops for managed-endpoint fleets, providing login-storm analysis and patch/config drift detection with built-in audit, budget, and risk-tier governance.

Enables agents to run pre-signature security checks: identifying who can replace a Solana program's code or control an EVM contract's upgrades, surfacing dependency advisories for lockfiles, scanning public repos before release, and setting 30-day signed-webhook alerts on changes. Calls are paid per use in USDC over x402 from a wallet with per-call caps and a session budget.

Enables MCP clients to read campaign and account data freely while routing every write through human-approved plans, with budget caps, drift refusal, undo, and audit logging.

AI payment guardrails for Python & MCP: spend-capped agent identity (KYA), dry-run/budget/approval gates, prompt-injection defense, encrypted secret vault.

Governed SSO/IAM operations for Keycloak and Authentik — login-failure, stale-permission, client-config, and MFA RCA, with unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback.

Enables read-only auditing of repositories by scanning actual files, flagging risky code, secrets, and untrusted platform configs, and generating Chinese-language reports for human decision-making.

Policy sidecar for any MCP server: deny-by-default tool allowlist with argument rules, call and USD budget caps, and a hash-chained audit log with RFC 3161 timestamps.

Enterprise AI governance layer for spend tracking, runtime guardrails, policy enforcement, and budget limits. Connects Claude, ChatGPT, and any MCP client to ThinkNEO's control plane for SOC2/GDPR/HIPAA compliance monitoring and real-time provider health.

Governed OPNsense + pfSense firewall operations — gateway-health, rule-shadow, and blocked-traffic RCA, with guarded rule/alias writes, unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback.

Enables local-first governance preflight for MCP production, including plugin discovery, fail-closed policy evaluation, message validation, budget previews, and payload-free audit receipts without executing or proxying plugins.

MCP server for AI-driven VAPT orchestration, enabling agents to plan and execute authorized security scans through a control plane that enforces scope, sanitization, budget, rate limits, human approval, and audit logging.

Enables agents and apps to verify end-user identity through company API keys, human login links with multi-channel notifications, OIDC client registration, and budget-aware billing.

Enables screening LLM input and output through cost-tiered safety checks with per-tenant budgets, returning allow, block, or review decisions. It exposes a JSON-RPC screen tool that isolates tenant spend and falls back to a configurable policy on provider failure or budget exhaustion.

Enables AI agents to place spot market orders on a paper or ccxt exchange account only when the trade fits a pre-registered mandate, sealing a hash of the agent's rationale into a tamper-evident trace and reconciling the authorized intent against the actual fill. It also exposes the mandate, quotes, balances, and trade trace/journal records as tools, failing closed whenever policy checks are unreachable.

Enables account-isolated, read-only access to a chosen Gmail account for searching mail, retrieving message and thread content, downloading attachments, and listing labels. It verifies the actual Google OAuth grant and account before starting and emits ready-to-use Codex or JSON MCP client configuration.

An MCP server that provides tools to audit AI-agent marketplace integrity by scanning listings for deceptive patterns like fabricated engagement, automated seeding, self-advertisement, unpaid work risk, and high-budget bait.

Control-plane proxy that sits in front of MCP servers, enforcing per-identity policy (YAML/OPA/Cedar), budget limits, and an audit trail on every call. Includes real-time anomaly detection that auto-blocks a compromised agent without a human in the loop.