A command that helps configure API keys for MCP servers, which let an agent connect to external tools. It stores the keys in a project’s .env file and lists optional services that can be skipped.

Use it when setting up Helius, Colosseum Copilot, or Mistral MCP connections, or when preparing a project’s .env file for those services.

It removes the need to manually create or edit the environment file and helps keep secrets out of mcp.json. It also explains which services need keys and which one is keyless but requires a separate command-line program.

setup-mcp — Command for Claude Code by solanabr/solana-ai-kit

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/solanabr/solana-ai-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/setup-mcp/github.svg)](https://agentmods.dev/commands/solanabr/solana-ai-kit/setup-mcp)

Your own site

<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/setup-mcp"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/setup-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/setup-mcp"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/setup-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 700 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00700
Opus 5.5	$0.00006	$0.00280
Sonnet 5.5	$0.00003	$0.00140
Haiku 4.5	$0.00001	$0.00070

Measured 25d ago against content hash 103681048a58, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

setup-mcp scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- Surfpool, local validator and mainnet-fork control: `claude mcp add surfpool -- surfpool mcp`. It needs the `surfpool` CLI on PATH; check with `command -v surfpool`, and if it is missing give the user the install comma

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Surfpool, local validator and mainnet-fork control: `claude mcp add surfpool -- surfpool mcp`. It needs the `surfpool` CLI on PATH; check with `command -v surfpool`, and if it is missing give the user the install comma

.claude/commands/setup-mcp.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Walk the user through filling in .env. Secrets go in .env, never in .mcp.json.

Steps

If .env is missing, copy .env.example to .env (or create an empty one).
For each key below, in order, ask the user to paste a value or say "skip". Write or update that line in .env and leave skipped keys empty. Don't echo values back.

MCP server key (the only one .mcp.json reads):
- HELIUS_API_KEY: Helius RPC and DAS API for the helius MCP server (https://dev.helius.xyz)
Optional skill/CLI keys, read at runtime by skill CLIs in .claude/skills/ext/, not by any MCP server:
- COLOSSEUM_COPILOT_PAT: Colosseum Copilot startup-research skill (PAT at https://arena.colosseum.org/copilot)
- COLOSSEUM_COPILOT_API_BASE: the default https://copilot.colosseum.com/api/v1 works for most
- MISTRAL_API_KEY: QEDGen formal-verification CLI (https://console.mistral.ai)
- THEGRID_API_KEY: TheGrid Colosseum project-graph queries (https://thegrid.id)
- THEGRID_GRAPHQL_ENDPOINT: the default https://beta.node.thegrid.id/graphql works for most
- QUICKNODE_RPC_URL, QUICKNODE_WSS_URL, QUICKNODE_API_KEY: QuickNode RPC, WebSocket/Streams and DAS for the quicknode skill (https://www.quicknode.com)
- X_BEARER_TOKEN: X API bearer token for the ct-alpha CT research skill (https://developer.x.com)
- DFLOW_API_KEY: DFlow order-flow integration skill (credentials from [email protected])
Ask which optional MCP servers to add; the default is none, since each one starts with every session. Run the command for each one the user picks. It adds the server for this user and project only; append --scope project only if the user wants to share it through .mcp.json.
- Playwright, browser automation (needs a browser Playwright can launch): claude mcp add playwright -- npx -y @playwright/mcp@latest --headless
- Surfpool, local validator and mainnet-fork control: claude mcp add surfpool -- surfpool mcp. It needs the surfpool CLI on PATH; check with command -v surfpool, and if it is missing give the user the install command (curl -L https://surfpool.run/install | sh or brew install txtx/taps/surfpool) rather than running it.
- context-mode, keeps large tool output out of context: claude mcp add context-mode -- npx -y context-mode@latest

Read the full file on GitHub · 33 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

25d ago Changed · -36 lines · +6 tokens per session 103681048a58
26d ago Changed · +22 lines aa20ab89ca64
1mo ago First seen · 47 lines · 8 tokens per session scan C c29517546a72

Subscribe to this mod's changes

setup-mcp is a command published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 26d ago), licensed MIT. It adds 14 tokens to every session and 700 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Claude Code claude-agent claude-commands claude-md claude-skills claude-subagents

setup-mcp

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Downloads and executes remote codehighSupply chain

Makes network callslowCapability

How it starts

Steps

What this file has done since we first saw it

Other commands, from other repositories

apex

explain-architecture

prompt

watch

design-audit

fix-pr-comments