Show HN: Reachpad MCP – Share fullstack applications using MCP/CLI in minutes

Reachpad launched Reachpad MCP, an MCP server that lets coding agents like Claude, ChatGPT, Cursor, and OpenCode create, fork, and persist cloud development environments via a REST API, CLI, or SDK. The tool supports persistent snapshots, forking, and brokered credentials, and is available via npx with configuration through environment variables.

Development infrastructure for coding agents. A reachpad environment is a cloud development computer an agent operates itself: a repo, a filesystem, installed dependencies and build state that all survive between calls — not an ephemeral sandbox that forgets. Processes are the exception; see below. This is the MCP server. It lets Claude, ChatGPT, Cursor, OpenCode or your own agent create an environment, run commands in it, fork it, and come back to it later, without a developer keeping a laptop open for them. It persists. Pause it and the disk is sealed; the next call boots from that seal with the files, installs and git state intact, rather than rebuilding. Processes are the exception: a start is always a cold boot. It forks. Twenty attempts from one prepared state cost a delta each, not twenty rebuilds — because the environment is a snapshot chain, not a machine. It can keep secrets out of the box. A brokered credential is called at the boundary on your behalf and its value never enters the environment, the log or the store. A credential written into the environment instead is readable there, by design. It is agent-agnostic. The REST API is canonical; this server, the SDK and the CLI are translations of it. Bring your own agent. The API is the product boundary, not a web UI: reachpad.dev https://reachpad.dev . npx -y @reachpad/mcp stdio, for a local client In Claude Code: claude mcp add reachpad -e REACHPAD IDENTITY CREDENTIAL=… -- npx -y @reachpad/mcp npx @reachpad/mcp stdio REACHPAD MCP HTTP PORT=8722 npx @reachpad/mcp streamable http stdio is what a local client talks to; Streamable HTTP is what a remote connector talks to. Same tools, same behaviour — added rather than forked, because two implementations of one surface is how they drift. The HTTP side answers 405 to GET : every tool here is request/response, and the spec permits declining the server-initiated stream rather than holding a connection open for traffic that never comes. There are no sessions — nothing is held across calls that a restart could not rebuild. And it carries no credential of its own : whatever authorizes the HTTP request is what authorizes reachpad. | variable | meaning | |---|---| REACHPAD ENDPOINT | your reachpad host. Plaintext http:// to anything but loopback is refused before a socket opens. | REACHPAD IDENTITY CREDENTIAL | your per-user credential. It names one account and can act for no other — the server takes the identity from the credential's own record, never from the request. | REACHPAD API KEY | optional, per-environment scoped and revocable. When set, run command uses it and needs no identity exchange. | REACHPAD MCP HTTP PORT | serve HTTP instead of stdio. | REACHPAD MCP HTTP HOST | default 127.0.0.1 . This process bridges to a control plane with your credentials, so binding it to the world is a decision made on purpose, behind a proxy that terminates TLS. | REACHPAD MCP HTTP TOKEN | bearer token, compared in constant time. Absent, every caller that can reach the port is authorized, and the server says so on stderr. | REACHPAD MCP ALLOWED ORIGINS | comma-separated. A request carrying an unlisted Origin is refused — a browser cannot forge it, which closes DNS rebinding. No Origin at all is a non-browser client and is allowed. | If several credentials are set, the narrowest wins, and a refused credential is never retried under a broader one — falling back would be privilege escalation nobody chose to perform. | tool | what it does | |---|---| get credit balance | remaining compute credits. One credit runs one standard environment for one minute. | create environment repo?, ref?, name? | a new environment, optionally with a repository cloned into /work . Reachpad generates its display name when omitted. | list environments | your environments and how many forks each has | get environment environment | what it boots from: its head snapshot, its log position and its fork tree | run command environment, argv, cwd?, env?, timeout ms? | one command, its exit code and its output. A paused environment resumes to serve it. | checkpoint environment environment, name? | fork from the last sealed snapshot; the original is untouched | delete environment environment | archive it and free the plan slot. Nothing is deleted — snapshots and history survive. | Not here, deliberately: exposing a port and starting an agent inside the environment. Both are in reachpad's roadmap and neither is in the fleet yet — a tool that always fails costs a model a turn and teaches it to distrust the rest, so this server advertises nothing it cannot serve. These are the ways a naive client of a streaming exec API misleads a model, and what this one does instead. An unterminated stream is UNKNOWN, never success. If the response ends without a terminal event, the tool says so in those words. It is not a zero exit, and an agent must not retry a non-idempotent command on the strength of it. Its deadline is looser than the server's , so a server-side answer always wins the race. A client that gives up first turns "your build finished" into "unknown", and the numbers are mirrored from the server rather than guessed. Refusals carry remedies, not codes. At your plan limit you get the limit, your current count, and what to do — the numbers come from the server, because a limit hardcoded in a client is a lie the moment your plan changes. Results are handles, not payloads. Output is tailed with the dropped byte count named. Build logs can be megabytes, and an MCP result that size destroys the caller's context window. A refusal is a result, not a transport error , so the model can read it and act. Only an unknown tool is a protocol error. node --test 'test/ .test.mjs' No network and no credentials. The protocol suite spawns the shipped server as a child process and speaks real JSON-RPC over its stdio against a stub control plane on a real socket, so nothing under test is an internal import. One test runs the same arc against a real reachpad and skips when no endpoint is configured. This repository is the source. It is deliberately separate from the reachpad backend : this code is public, it is published to npm, and its release workflow holds publishing rights — none of which belong in the same repository as the control plane. Nothing here can read the backend's source, and no job in the backend copies files out to here. Two server constants are mirrored in src/client.js — the exec grace period and the default exec timeout. A mirrored constant normally rots; this one does not, because the backend's own CI fetches this published package and fails if they disagree. The check lives where the number would change.