MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
mcp_spending-controlgithub.com/AxeGlzA/mcp_spending-controlupdated this year
A simple MCP-based project designed to help you track and control your expenses.
-
@proceedgate/mcp-serverupdated this year
MCP Server for ProceedGate cost governance - control agent spending via Model Context Protocol
npm MIT -
@policylayer/mcpgithub.com/policylayer/policylayerupdated this year
MCP server for PolicyLayer spending controls. Add policy-governed payments to any AI agent.
npm MIT -
Agent spending controls as an MCP server: Veyline by Payload returns signed, policy-checked preflight decisions on proposed agent payments, plus entitlement and usage reads. Free sandbox key to evaluate.
mcpb MIT -
gvnrgithub.com/mightbesaad/gvnrupdated this year
Budget & 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 -
imprestgithub.com/Theoddalex/imprestupdated this year
Spend control & audit for AI agents — give your agent an allowance, not your keys. MCP server, non-custodial, x402.
pypi MIT -
Model Context Protocol server for Silvanexum — the spend-control plane for AI agents. Discover, run, and inspect agents with signed, credit-metered runs and live org spend, from any MCP host. Run with `npx -y @silvanexum/mcp`.
npm Apache-2.0 -
Steward MCP — 25 tools for x402 agent commerce: trust verification, spend controls, merchant directory
npm MIT -
A payment-control demo for AI assistants: spending limits, verified records, and human approval. Built for the PayPal AI Hackathon.
MIT -
agentcache-mcpactive
Agent-facing MCP for the AgentCache control plane — cache, pre-spend governance gate, verifiable savings, and cross-run reasoning memory.
npm MIT -
A policy gateway for agentic commerce - lets merchants safely expose their catalog to AI buyers with bounded, explainable spending controls, built on Razorpay MCP
-
Dossier — Google Gemini Deep Research as an MCP server. Durable background runs, spend control, context-safe report reading, and citation verification.
-
AI Agent Cost Control & Usage Analytics Dashboard 2026: Monitor Claude, Cursor & Codex Spend
-
Economic control plane for AI agent fleets: enforced, delegated authority over what agents can spend. Fleet budgets, scoped MCP keys, append-only audit logs, and human approval queues.
MIT -
Give your AI agent a spending limit. Authoryze is a remote MCP server that issues single-use virtual cards with per-merchant and per-amount controls you approve before the agent can spend. Works with Claude, ChatGPT, Cursor, and Claude Code. OAuth 2.1 with DCR or API key. Built on Visa Intelligent Commerce and Mastercard Agent Pay.
-
SCRIPTMASTERLABS x402 Gateway: read-only discovery of x402 paid APIs and fresh payment requirements on Base. Caller controls authorization and spending.
npm MIT -
Neutral, cross-vendor control plane for AI agents that spend money — one policy, one sub-second freeze, one tamper-evident audit ledger across every agent-wallet backend. Open-core: SDK + MCP + x402/AP2.
npm NOASSERTION ★ 1 -
Local daemon + hooks + MCP server that tell Claude Code sessions how close the account is to its rate limits, with local token spend, live session control and iPhone, Apple Watch and Android dashboards. Not affiliated with Anthropic.
MIT ★ 2 -
NexaLayerno update data
Managed proxy sessions with hard budget caps, for direct API use and browser automation. Discover current products and prices, create and rotate sessions, monitor health and usage, and enforce owner-controlled spend limits. Early-access launch pricing (subject to change): dynamic proxies $0.23/GB; shared static from $1.05/month; dedicated static $1.43–$5.86/month.
smithery -
Open-source MCP server that lets your AI agent shop for you while you keep control of the money. The agent fills the cart and reaches payment, then hands you a UPI QR to approve on your phone. Your PIN never touches the AI. Local-only, with a signed spending policy.
pypi Apache-2.0 -
Supervise an AI coding agent (Claude Code / Codex / ACP) overnight and keep control: block forbidden tool calls before they run, gate 'done' on real tests, checkpoint work to git, cap spend, and get a morning report where every line is sourced. Local-first, no telemetry. Rust daemon + Tauri app + Claude Code plugin.
MIT ★ 1 -
reins-spend-mcpactive
Reins — let an LLM pay APIs only inside an on-chain spend policy (budget, payee allowlist, expiry, revoke) on Solana. MCP server + CLI.
npm MIT -
TWZRD buyer-side x402 trust packages: x402 trust gate, elizaOS trust plugin, and the agent-intel client. Vet a counterparty before you pay.
pypi MIT -
Shotoku MCP server - gate any MCP tool call against a local spend and action policy.
npm MIT -
MCP server for AgentVeins: governed payments as a tool any agent can call.
npm MIT -
Valta-MCPgithub.com/Valta-hq/Valta-MCPupdated this year
Financial guardrails for AI agents — pre-call spend gates and a cryptographically hash-chained audit trail. Stops an agent before it overspends, not after.
MIT ★ 1 -
x402-agent-paygithub.com/Omnivalent/x402-agent-payupdated this year
Seamless USDC payments for AI agents using the x402 protocol
npm MIT ★ 2 -
agent-budgetgithub.com/nyx-builds/agent-budgetupdated this year
Budget enforcement and spend tracking for autonomous agents — per-agent limits, threshold alerts, cost analysis. MCP server.
MIT -
Rein Guard MCP server — give any MCP-capable agent harness a spend-governed fetch: every x402 paywall is policy-checked, receipted and observable before a cent moves.
npm MIT -
Wallie MCP server — give your MCP client a spending allowance. Pay any x402 API (Base or Solana, exact or upto) inside hard policy rails, over five stdio tools.
npm MIT -
AgentGuard MCP server: local spend caps, kill-switch style blocking, and Ed25519-signed provenance receipts for AI agent actions. Zero data plane: prompts never pass through this server.
npm SEE LICENSE IN LICENSE -
@agentpay-run/mcp-servergithub.com/sdeanesh-png/agentpayupdated this year
Official MCP server for AgentPay. Lets agents charge vendors, check budgets, and inspect quota through any MCP-compatible client (Claude Desktop, Cursor, etc.).
npm MIT -
buzz-axirugithub.com/axiruai/buzz-axiruupdated this year
Bounded spend authority for Buzz agents. A gating MCP proxy in front of your payment MCP server: policy evaluation before money moves, human approvals in the Buzz channel, and a hash-chained decision log keyed to the agent's Nostr pubkey.
npm Apache-2.0 -
See what each AI agent, client and job costs, in dollars at list price, and give any job a spend ceiling: preflight answers approved: false past it, and your code decides. An SDK and an HTTP API, not a proxy.
pypi MIT ★ 7 -
Approvals, spend limits and a kill switch for AI agents, set up in one command: npx immiscible init. See it first, offline and with no account: npx immiscible try. Installs a fail-closed Claude Code hook, prints MCP setup for Claude Code, Cursor and VS Co
npm MIT -
prompt-squeezegithub.com/joshua-burnell-1/prompt-squeezeupdated this year
Builds prompt-cost discipline into Claude Code: measure every prompt, surface avoidable spend, report org-wide. Skill + UserPromptSubmit hook + MCP rollup with cited dollar/Wh/CO2e receipts.
Apache-2.0 ★ 1 -
GVNR: stops AI agents overspending and running dangerous commands, before the action runs. Per-minute spend caps, allow/deny/escalate on every action, hash-chained receipts, MCP server. Free, self-hosted. Formerly Enforcer Governor.
npm FSL-1.1-ALv2