An MCP server configuration for Forge, from the Krait project. It starts the server with Node.js so a coding agent can connect to it.

Use it when configuring an MCP environment that needs the Krait Forge server.

It supplies the command needed to launch this server in an MCP setup. The supplied information does not explain what Forge itself does.

krait-forge — MCP server by ZealynxSecurity

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.

agentmods

npx agentmods add mcp/zealynxsecurity/krait/krait-forge

Clone the repo

git clone --depth 1 https://github.com/ZealynxSecurity/krait

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

krait-forge scanned grade A with 0 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 3d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 9 lines

What it actually says

{
  "krait-forge": {
    "type": "stdio",
    "command": "node",
    "args": [
      "mcp-servers/forge/build/index.js"
    ]
  }
}

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.

3d ago First seen · 9 lines scan A c2b70f38a25b

Subscribe to this mod's changes

krait-forge is an MCP server published in the GitHub repository ZealynxSecurity/krait (22 stars, last pushed 22d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai audit claude-code defi ethereum

chaingpt

MCP server "chaingpt" as configured in ChainGPT-org/chaingpt-claude-skill. Runs ${CLAUDE_PLUGIN_ROOT}/mcp-server/launch.mjs with node. Needs 1 environment variable to run.

ChainGPT-org/chaingpt-claude-skill · not measured

suwappu

Cross-chain DEX for AI agents. Swap tokens across 7+ chains. Runs locally from the @suwappu/mcp-server npm package. Needs 1 environment variable to run.

0xSoftBoi/suwappubot · not measured

coingecko-mcp-server

Crypto market data via CoinGecko — prices, markets, history, trending, and deep coin metadata. Runs locally from the @cyanheads/coingecko-mcp-server npm package. Needs 2 environment variables to run.

cyanheads/coingecko-mcp-server · not measured

verdictswarm

Every tool has an answer — your agent needs a decision. MCP server for the VerdictSwarm pre-trade check: a machine-readable avoid/caution/clear before your agent trades, plus intended-size exit feasibility and holder-cluster attribution on Solana. Runs locally from the verdictswarm-mcp Python package. Needs 3…

sentien-labs/verdictswarm-mcp · not measured

verdictswarm-mcp

sentien-labs/verdictswarm-mcp · not measured

ponscli

Unofficial command-line interface for the Pons launchpad on Robinhood Chain. Runs locally from the ponscli npm package.

mesutgulecen/ponscli · not measured