# AgentFuel (remote · api.agentfuel.eu)

Rug-check risk scores for Solana tokens and a live feed of new pump.fun launches.

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `api.agentfuel.eu`: 71/100 (this document), [markdown](https://verifymcp.io/servers/fizzl13-agentfuel/api.md), [page](https://verifymcp.io/servers/fizzl13-agentfuel/api)

## Channel facts

- Endpoint: `https://api.agentfuel.eu/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 463 tokens (~92/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 83% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the AgentFuel MCP server?

AgentFuel is a hosted endpoint at https://api.agentfuel.eu/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http fizzl13-agentfuel 'https://api.agentfuel.eu/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "fizzl13-agentfuel": {
      "url": "https://api.agentfuel.eu/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fizzl13-agentfuel": {
      "type": "http",
      "url": "https://api.agentfuel.eu/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.fizzl13-agentfuel]
url = "https://api.agentfuel.eu/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fizzl13-agentfuel": {
      "type": "remote",
      "url": "https://api.agentfuel.eu/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fizzl13-agentfuel --url 'https://api.agentfuel.eu/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fizzl13-agentfuel:
    url: "https://api.agentfuel.eu/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "fizzl13-agentfuel": {
      "Transport": "http",
      "Url": "https://api.agentfuel.eu/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add fizzl13-agentfuel -t streamable-http -u 'https://api.agentfuel.eu/mcp'
```

### Other

```json
{
  "mcpServers": {
    "fizzl13-agentfuel": {
      "type": "http",
      "url": "https://api.agentfuel.eu/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 71, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-04 (score 70)

First indexed and scored.

## MCP tools (5)

### `rugcheck` (~76 tokens)

Rug-check a Solana token

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

Input parameters:

- `exclude` (array): Token accounts to leave out of the holder check, such as a pool or bonding curve
- `mint` (string, required): Token mint address (base58)

### `latest_launches` (~76 tokens)

Latest pump.fun launches

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

Input parameters:

- `limit` (integer): Maximum number of launches, default 20
- `maxRisk` (number): Only launches with risk score at or below this
- `sinceMs` (number): Only launches after this unix time in milliseconds

### `presign_check` (~123 tokens)

Check a Solana transaction before signing (Presign Guard)

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.onrender.com), which has the full report with reasons.

Input parameters:

- `intent` (string): What the transaction should do, e.g. "buy 0.1 SOL of <mint> on pump.fun"
- `transaction` (string, required): The base64 wire transaction about to be signed

### `injection_check` (~102 tokens)

Check a text for prompt injection (Presign Guard)

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.

Input parameters:

- `source` (string)
- `task` (string): One sentence: what the agent is doing for its user
- `text` (string, required): The text the agent received and is about to act on

### `x402_check` (~86 tokens)

Check an x402 endpoint before paying (x402 Doctor)

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), which has the full report.

Input parameters:

- `method` (string)
- `url` (string, required): The x402 endpoint, e.g. https://api.example.com/paid

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fizzl13-agentfuel/api#diagnostics

## Score history

- 2026-11-05: 71
- 2026-11-04: 70

## Common questions

### What is the AgentFuel MCP server?

AgentFuel is an MCP server listed in the public MCP registry as io.github.Fizzl13/agentfuel. Rug-check risk scores for Solana tokens and a live feed of new pump.fun launches. This page covers its hosted endpoint (https://api.agentfuel.eu/mcp).

### Is the AgentFuel MCP server safe to use?

AgentFuel scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AgentFuel MCP server expose?

AgentFuel exposes 5 tools: rugcheck, latest_launches, presign_check, injection_check, x402_check. Their descriptions and schemas cost roughly 463 tokens of context every time the server is loaded.

### Does the AgentFuel MCP server require authentication?

No. We connected to AgentFuel without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgentFuel MCP server still maintained?

AgentFuel is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.agentfuel.eu/mcp
- Repository: https://github.com/Fizzl13/agent-coin-api
- Website: https://www.agentfuel.eu/
- Changelog RSS feed: https://verifymcp.io/servers/fizzl13-agentfuel/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/fizzl13-agentfuel/api.json
- HTML version of this page: https://verifymcp.io/servers/fizzl13-agentfuel/api