"Actual Budget" matching MCP servers:

Keyword Metrics for Google Ads search volume, CPC, advertising competition and monthly history. Optional AI Search Volume provides modeled question-demand signals, not actual ChatGPT or Perplexity query counts. Free discovery and quotes; paid calls require an approved budget and use USDC on Base via x402. Also includes SERP, domain and local-market research.

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.

MCP server for programmatic read-only access to RiseUp cashflow data, allowing AI assistants to retrieve budget information via natural language.

Lets an AI agent hire and pay a verified human: post real-world tasks (voice, observation, judgment) and pay in USDC via a non-custodial x402 auth-capture escrow on Base, budget frozen at deploy. Humans verify their X identity before submitting.

Screen-reader navigation cost analyzer. Measures how hard it is for assistive-technology users to discover, reach, and operate interactive targets on the web.

MCP server that lets AI agents discover and pay for .agent services using USDC over x402, with daily budget controls and payment link creation.

Enables MCP-capable agents to inspect a local Synthesizer installation, query local grids and APIs, find examples, plot grid spectra, and validate scripts, so answers are grounded in the user's actual environment.

A budget-bound x402 payment wallet for AI agents: it autonomously pays HTTP 402 payment-gated URLs across every major chain (EVM, Solana, and many non-EVM families). Self-custodial and backendless, your key, your RPC, with spend caps enforced before any on-chain send.

Enables AI agents to call paid APIs and settle HTTP 402 payment challenges with USDC on Base, without private keys ever being involved.

MCP server to ask research questions about real-world datasets and get actual database records back, with auto-registration and trial credit.

Let your AI assistant pay for web content in USDC (x402 on Base) within a budget you set. Inside the budget it pays on its own; above it you are asked to confirm. The wallet key stays on your computer. For claude.ai and ChatGPT there is a remote server (https://agent.p2flux.com/mcp) where you approve each payment in your own browser wallet.

Provides read-only, governance-audited operations for OLVM and oVirt 4.5 engines, enabling inventory, health, capacity, and diagnosis queries over MCP and CLI with audit logging and budget guards.

VibOps MCP is the control plane between your AI agents and your GPU infrastructure. 74 tools covering: GPU fleet management (deploy, scale, monitor across NVIDIA, AMD, Intel, AWS, Google, Groq), Agent Infrastructure Control Plane (per-agent GPU cost, budget enforcement, model policies, dependency graph), governance (AI Act, SOC 2, immutable HMAC audit chain), and GPU FinOps (chargeback, waste..)..

Enables AI assistants to interact with Bayesian marketing mix models through natural language, including data upload, model building, result inspection, budget optimization, and scenario planning.

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.

NexaLayer MCP Server — a Model Context Protocol server that lets AI agents create and manage dynamic and static proxy sessions with budget guardrails.

Enables agents to autonomously pay x402 API requests in USDG on Robinhood Chain while enforcing budget caps and scoped sessions.

Enables AI agents to take real professional decision cases, search reference libraries and rulebooks, submit a decision, and receive an exact score against the professional's actual outcome.

Enables coding agents to query a repository's code graph and project memory through cited excerpts, navigate symbols and dependencies, and optionally inspect pull requests, all within a configurable token budget.

A unified MCP server that lets AI agents (Claude Code, Codex, Cursor) deploy web apps and VPS instances, provision Supabase-compatible Postgres/Auth/Storage databases, register DNS domains, and send transactional email using a shared MONA Pass identity and VND wallet. It also embeds MONA Pay tooling for VietQR top-ups, checkout, webhooks and reconciliation, so agents can handle payment requests, budget approvals and resource lifecycles end to end.