agent-exec MCP server
Accountless pay-per-use sandbox execution, storage, locks, attestation and handoff; pay via x402.
Little public usage data yet
Reviews
Write oneNobody has reviewed agent-exec yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
agent-exec tools (3, 1 write)
write = sends, deletes, buys or postsexecutewrite actionFreePAID: run code in an isolated, network-less sandbox and get stdout, stderr and exit code back. Call it once without payment to receive the price as an x402 PaymentRequired (Base USDC, and Solana USDC where offered); call it again with a signed payment in _meta['x402/payment'] to run. The receipt comes back in _meta['x402/payment-response']. No account, no API key. Complaints, questions, quote requests, or a service you wish we had: POST /feedback on this host -- free, no account. Every report is read and analysed daily; there is no individual reply.
search_listingsFreeFree, unauthenticated search over agent-exec's directory of paid agent-facing services (same data as GET https://agent-exec.45.67.221.128.sslip.io/listings). Returns a page of listings and an opaque cursor for the next page.
service_cardFreeWhat agent-exec sells, what it costs, and exactly where to pay for it. This tool call itself is free and moves no money. Code execution can be bought right here, with the paid execute tool (x402 over MCP), or over plain HTTP at the URLs this returns. Complaints, questions, quote requests, or a service you wish we had: POST /feedback on this host -- free, no account. Every report is read and analysed daily; there is no individual reply.
Public scan report
scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 1956ms20/20
- Tool poisoning3 tool descriptions checked15/15
- Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
- Maintenanceno repository listed3/15
- Maintainer identityverified namespace with website, no repo4/10
Findings (2)
- highWrite-action tools reachable without authentication
auth.open-write - lowNo source repository listed
maint.no-repo
Install directly
claude mcp add --transport http agent-exec https://agent-exec.45.67.221.128.sslip.io/mcp
agent-exec: common questions
- Is agent-exec MCP server safe?
- With care: it is graded C, so read the findings first (60/100). Read the agent-exec safety report
- How do I install agent-exec?
- It runs remotely at agent-exec.45.67.221.128.sslip.io. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does agent-exec need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is agent-exec maintained?
- The latest release is v0.2.0.
- Is agent-exec up?
- 100% of our last 5 checks got an answer. We check remote servers about four times a day.
- What can I use instead of agent-exec?
- Servers from other publishers that do the same job: Maginary MCP server, BridgeNode MCP server and Ausca MCP server. Compare all agent-exec alternatives.
Alternatives to agent-exec
Same job from other publishers: the closest match first, then the best rated.
- MaginaryAI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.not reviewedGrowingB
BridgeNode MCPBridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.not reviewedGrowingA- AuscaPay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.not reviewedEstablishedB
- MCPAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
- MCP ServerAgent-native global eSIM: buy for 193 countries, per-MB in USDT/USDC. Agents earn 20% referral.not reviewedGrowingB