agent-exec
Pay-per-use sandboxed code execution for agents, paid with HTTP 402 and no account
- Pricing
- Paid
- Platforms
- API
- Runs
- Remotely
- Version
- 0.4.0
- Listing updated
- 1 day ago
About agent-exec
agent-exec is a paid MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
agent-exec lets software agents submit source code and receive stdout, stderr and the exit code from an isolated sandbox with no network access. There are no accounts or API keys; possession of a valid payment under the HTTP 402 flow is what authorises a call.
The registry entry describes a wider catalogue than the homepage text does: sandbox execution, storage, locks, attestation, an email inbox and DNS names, all paid through x402. The site provides a machine-readable x402 manifest, an OpenAPI file and llms.txt. It also takes feedback by plain POST to a /feedback endpoint; reports are read and analysed daily, but nobody replies individually.
Per-call prices and supported languages are not given on the page available here.
Install
Run in a terminal
claude mcp add --transport http agent-exec https://agent-exec.448c.org/mcpAdd to Settings → Connectors → Add custom connector
https://agent-exec.448c.org/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"agent-exec": {
"url": "https://agent-exec.448c.org/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"agent-exec": {
"type": "http",
"url": "https://agent-exec.448c.org/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"agent-exec": {
"serverUrl": "https://agent-exec.448c.org/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"agent-exec": {
"type": "http",
"url": "https://agent-exec.448c.org/mcp"
}
}
}What it does
- Isolated sandbox
- Runs submitted code without network access.
- Standard outputs
- Returns stdout, stderr and exit code.
- No account
- Payment itself is the credential.
- Machine-readable docs
- x402 manifest, OpenAPI and llms.txt.
- Feedback endpoint
- Free POST for questions and requests.
Good for
- Run untrusted snippets from an agent safely
- Execute a quick script without provisioning a server
- Pay per run from an autonomous agent wallet
- Report a missing service by POST
Pricing
Paid
Pay per use via x402; prices not published on the page.
Prices change. Check agent-exec.448c.org before you buy.
agent-exec FAQ
Do I need an API key?
No. Payment is sufficient.
Can the sandbox reach the network?
No, it is network-less.
What comes back?
stdout, stderr and the exit code.
Do feedback reports get a reply?
No individual reply; they are read daily.
Is agent-exec free?
No. agent-exec is a paid product.
How do I add agent-exec to Claude Code?
Run this command in your terminal: claude mcp add --transport http agent-exec https://agent-exec.448c.org/mcp
What are the best alternatives to agent-exec?
The closest alternatives to agent-exec are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to agent-exec

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools