Solrisk Mcp

io.github.comil27Published by GitHub account comil27v1.0.1Updated Oct 24, 2026

RETIRED - this server is discontinued and its backend is offline. Do not use.

VerifiedSTDIODesktop onlyFinance

Overview

AI-generated overview

A discontinued Solana token risk MCP server that was meant to return rug, honeypot and dump risk scores for SPL token mint addresses.

What you can do
Score a Solana SPL token by mint address, returning a 0–100 risk score for rug, honeypot and dump risk (per the README). Report mint and freeze authority status, top-10 holder concentration, and liquidity, 24h volume and price signals. The registry description states the server is retired and its backend is offline, so these capabilities are no longer available.
When to use it
Not for new installations: the registry description marks the server as discontinued with an offline backend. Anyone who previously used it for quick Solana token due-diligence checks should look for an active alternative.
Requirements
None can be relied on: the manifest declares no packages, environment variables or headers, and the README's remote endpoint is described by the registry as offline.
Before you install
The server is retired and its backend is offline, so it should not be used. The README also describes a separate paid pay-per-call HTTP API billed in USDC at $0.01 per call; that is a spending consideration and is not the MCP tool itself.

Installation

In SourceWeft

  1. Open Solrisk Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

solrisk-mcp — Solana Token Risk MCP Server

A hosted Model Context Protocol server that gives any AI assistant or agent an instant rug / honeypot / dump risk score (0–100) for any Solana SPL token, straight from on-chain signals — no API key, no install, one URL.

Built for Claude Code, Claude Desktop, Cursor, and any MCP-capable agent framework.

What it does

The solana_token_risk tool takes a token mint address and returns a JSON risk report:

  • riskScore — 0 (safe) … 100 (high rug/honeypot/dump risk)
  • mintAuthority / freezeAuthority — can the supply be inflated or wallets frozen?
  • top10HolderPct — holder concentration (whale/insider dump risk)
  • liquidityUsd / volume24h / priceUsd — market depth signals

Install (remote — nothing to download)

Claude Code

bash
claude mcp add --transport http solrisk https://solrisk.rugscore.workers.dev/mcp

Claude Desktop / Cursor / generic MCP client — add to your MCP config:

json
{  "mcpServers": {    "solrisk": {      "type": "streamable-http",      "url": "https://solrisk.rugscore.workers.dev/mcp"    }  }}

Then ask: "Check the rug risk of token <mint>."

Example

jsonc
// solana_token_risk { "mint": "So11111111111111111111111111111111111111112" }{  "mint": "So111...1112",  "riskScore": 0,  "mintAuthority": null,  "freezeAuthority": null,  "top10HolderPct": 12.4,  "liquidityUsd": 48211934,  "volume24h": 91833021,  "priceUsd": 168.42}

High-volume / autonomous agent use (paid)

The MCP tool above is free. For programmatic pay-per-call at scale, the same engine is exposed as a pay-per-use HTTP API via x402 (USDC on Solana, $0.01/call, no account):

GET https://solrisk.rugscore.workers.dev/check?mint=<MINT>

It returns an HTTP 402 with an x402 payment challenge; pay and retry to get the full report. Discovery: /.well-known/x402 · /openapi.json · /llms.txt

Links

License

MIT

Source: README.md at commit 095cc97

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts