Koskamo

AgentFuel MCP

AgentFuel provides safety checks for Solana and Robinhood Chain trading bots and AI agents. It offers rug-check risk scores for tokens, a live feed of new pump.fun launches with risk assessments, and pre-sign, prompt-injection, and x402 endpoint checks. The server enables agents to verify token safety before executing trades, using a pay-per-call model via x402 (USDC on Solana) without requiring accounts or API keys.

Visit Fizzl

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

AgentFuel MCP logo, by FizzlCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by Fizzl
MCP endpoint (Streamable HTTP)
https://api.agentfuel.eu/mcp
Vendor documentation

What its tools do

9 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (9)

9 of 9 have a description · 9 of 9 declare behavior hints · 6 of 8 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Check rug-check risk scores for Solana tokens
  • Monitor live feed of new pump.fun launches with risk scores
  • Verify transactions before signing to prevent prompt injection
  • Check x402 endpoint safety before payment

Source and maintenance

Community listingRegistry 0.2.0
mcp-registry: io.github.Fizzl13/agentfuel@0.2.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
agentfuel 0.1.0
MCP protocol negotiated in check
2025-11-25
Tools
9 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

AgentFuel: rug-check scores and a pump.fun launch feed for Solana trading agents. Use rugcheck before buying a token, presign_check before signing the buy. More agent tools from the same maker at https://fizzl.eu: Presign Guard (https://presign-guard.fizzl.eu) checks a transaction before signing and texts for prompt injection; x402 Doctor (https://x402-doctor.fizzl.eu) checks x402 endpoints before paying.

Tools

9 advertised

afuel_token — Official AFUEL token address
Advertised by the server during the last successful anonymous check.
Advertised read-only

The official mint address of AgentFuel ($AFUEL) on Solana, with the launch wallet and links. Other tokens can copy the name or ticker; only this mint is AFUEL. Free, does not count toward the daily limit.

afuel_token input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
afuel_token annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
rugcheck — Rug-check a Solana token
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Risk score (0-100) for a Solana token mint: mint/freeze authority and holder concentration. Automated on-chain checks, not financial advice.

rugcheck input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "mint"
  ],
  "properties": {
    "mint": {
      "type": "string",
      "pattern": "^[1-9A-HJ-NP-Za-km-z]{32,44}$",
      "description": "Token mint address (base58)"
    },
    "exclude": {
      "type": "array",
      "items": {
        "type": "string",
        "pattern": "^[1-9A-HJ-NP-Za-km-z]{32,44}$"
      },
      "description": "Token accounts to leave out of the holder check, such as a pool or bonding curve"
    }
  }
}
rugcheck annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
rugcheck_robinhood — Rug-check a Robinhood Chain token
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Risk score (0-100) for an ERC-20 token on Robinhood Chain (chain id 4663): verified source, upgradeable proxy, owner, mint/blacklist/fee functions, holder concentration (contracts such as pools are left out) and, when known, the Uniswap v4 pool hook. Automated on-chain checks, not financial advice.

rugcheck_robinhood input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "token"
  ],
  "properties": {
    "token": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{40}$",
      "description": "Token contract address (0x...)"
    }
  }
}
rugcheck_robinhood annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
latest_launches — Latest pump.fun launches
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Newest pump.fun token launches with creator, dev-buy share and risk score, newest first.

latest_launches input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Maximum number of launches, default 20"
    },
    "maxRisk": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Only launches with risk score at or below this"
    },
    "sinceMs": {
      "type": "number",
      "description": "Only launches after this unix time in milliseconds"
    }
  }
}
latest_launches annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
latest_launches_robinhood — Latest Robinhood Chain launches
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Newest tokens on Robinhood Chain (new Uniswap v4 pools: Pools.trade launches and graduated launchpad tokens) with a rug-check risk score, newest first.

latest_launches_robinhood input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Maximum number of launches, default 20"
    },
    "maxRisk": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Only launches with risk score at or below this"
    },
    "sinceMs": {
      "type": "number",
      "description": "Only launches after this unix time in milliseconds"
    }
  }
}
latest_launches_robinhood annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
safe_buy — Check a token and its buy transaction in one call
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Before a bot buys a Solana token: rug-checks the token and has Presign Guard check the buy transaction the bot is about to sign. Returns one verdict: green (no red flags), orange (ask the user first) or red (do not sign), with the reasons. Nothing is signed or sent. Automated checks, not financial advice.

safe_buy input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "mint",
    "transaction"
  ],
  "properties": {
    "mint": {
      "type": "string",
      "pattern": "^[1-9A-HJ-NP-Za-km-z]{32,44}$",
      "description": "Token mint address the bot wants to buy (base58)"
    },
    "intent": {
      "type": "string",
      "maxLength": 500,
      "description": "What the buy should do, e.g. \"buy 0.1 SOL of <mint> on pump.fun\""
    },
    "exclude": {
      "type": "array",
      "items": {
        "type": "string",
        "pattern": "^[1-9A-HJ-NP-Za-km-z]{32,44}$"
      },
      "description": "Token accounts to leave out of the holder check, such as a pool or bonding curve"
    },
    "transaction": {
      "type": "string",
      "maxLength": 12000,
      "minLength": 1,
      "description": "The base64 wire transaction of the buy, unsigned or about to be signed"
    }
  }
}
safe_buy annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
presign_check — Check a Solana transaction before signing (Presign Guard)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Green, orange or red verdict for a Solana transaction your bot is about to sign, such as the buy after a rug-check. Red: do not sign. Orange: ask the user first. Nothing is signed or sent. Powered by Presign Guard (presign-guard.fizzl.eu, by Fizzl: fizzl.eu), which has the full report with reasons.

presign_check input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "transaction"
  ],
  "properties": {
    "intent": {
      "type": "string",
      "maxLength": 500,
      "description": "What the transaction should do, e.g. \"buy 0.1 SOL of <mint> on pump.fun\""
    },
    "transaction": {
      "type": "string",
      "maxLength": 12000,
      "minLength": 1,
      "description": "The base64 wire transaction about to be signed"
    }
  }
}
presign_check annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
injection_check — Check a text for prompt injection (Presign Guard)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Green, orange or red verdict for a text your agent received (a token description, web page, tool result or another agent's message): does it try to make the agent ignore its instructions, pay or hand over keys? Powered by Presign Guard.

injection_check input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "text"
  ],
  "properties": {
    "task": {
      "type": "string",
      "maxLength": 500,
      "description": "One sentence: what the agent is doing for its user"
    },
    "text": {
      "type": "string",
      "maxLength": 8000,
      "minLength": 1,
      "description": "The text the agent received and is about to act on"
    },
    "source": {
      "enum": [
        "web",
        "email",
        "tool",
        "api",
        "agent",
        "chat",
        "document",
        "other"
      ],
      "type": "string"
    }
  }
}
injection_check annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
x402_check — Check an x402 endpoint before paying (x402 Doctor)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Does this paid x402 endpoint work for a paying agent? Pass, warn or fail with the main problems. Never pays the endpoint. Powered by x402 Doctor (x402-doctor.fizzl.eu, by Fizzl: fizzl.eu), which has the full report.

x402_check input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "The x402 endpoint, e.g. https://api.example.com/paid"
    },
    "method": {
      "enum": [
        "GET",
        "POST"
      ],
      "type": "string"
    }
  }
}
x402_check annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (3 of 3 answered).

  1. 2026-11-07: 2 of 2 checks answered
  2. 2026-11-09: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1288 ms
95th percentile latency
1288 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1288 ms · metadata changed · 9 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http agentfuel-mcp https://api.agentfuel.eu/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add agentfuel-mcp --url https://api.agentfuel.eu/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agentfuel-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agentfuel-mcp": {
      "url": "https://api.agentfuel.eu/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agentfuel-mcp": {
      "type": "streamableHttp",
      "url": "https://api.agentfuel.eu/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agentfuel-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agentfuel-mcp": {
      "type": "http",
      "url": "https://api.agentfuel.eu/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http agentfuel-mcp https://api.agentfuel.eu/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://api.agentfuel.eu/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "agentfuel-mcp": {
      "serverUrl": "https://api.agentfuel.eu/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AgentFuel MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,689