Instruction MCP Server

Construct, plan and execute transactions from multiple instructions.

Local serverstdioTypeScript

What is the Instruction MCP server?

Construct, plan and execute transactions from multiple instructions. That is what the instruction mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

This is the JavaScript SDK for building Solana apps for Node, web, and React Native.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

The tools it exposes

The server publishes 3 tools. What each one is for:

  • Sharding — A sharding transport is a kind of distributing transport that sends requests to a particular server based on something about the request itself
  • Retry — A custom transport is a good place to implement global retry logic for every request:
  • Failover — Support for handling network failures can be implemented in the transport itself. Here’s an example of some failover logic integrated into a

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Instruction's toolset — Sharding, Retry, Failover — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
ShardingA sharding transport is a kind of distributing transport that sends requests to a particular server based on something about the request itself. Here’s an example that sends requests to different servers depending on the
RetryA custom transport is a good place to implement global retry logic for every request:
FailoverSupport for handling network failures can be implemented in the transport itself. Here’s an example of some failover logic integrated into a transport:

Example prompts to try

  • Use Instruction to Sharding.
  • Use Instruction to Retry.
  • Use Instruction to Failover.

Frequently asked questions

It connects Instruction to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (Sharding, Retry, Failover) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Instruction directly.