# cabal-hunter

> cabal-hunter, an MCP server by api.cabal-hunter.com, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Solana pre-trade safety for AI agents: cabal, bundle, dump, deployer & honeypot in one verdict.

- Canonical: https://www.anchorterminal.com/tools/cabal-hunter
- Markdown: https://www.anchorterminal.com/tools/cabal-hunter.md (~700 tokens)
- Slim: https://www.anchorterminal.com/tools/cabal-hunter.min.md (~630 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/cabal-hunter.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

# cabal-hunter

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by api.cabal-hunter.com (https://api.cabal-hunter.com)
- Category: Cloud & infrastructure (https://www.anchorterminal.com/categories/infrastructure.md)
- Listed because: It's published in the registry under api.cabal-hunter.com, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Solana pre-trade safety for AI agents: cabal, bundle, dump, deployer & honeypot in one verdict.

## Facts

- MCP registry: `com.cabal-hunter.api/cabal-hunter` 1.2.0
- Endpoint: https://api.cabal-hunter.com/mcp (streamable HTTP)
- Source: https://github.com/paulf280-ui/solana-safe-sniper-mcp-template
- Website: https://api.cabal-hunter.com
- GitHub stars: 1
- Registry entry updated: 2026-07-07

## Tools

- Tools it lists (2, about 1,765 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-10-04 22:22 UTC), descriptions withheld: they contain text aimed at the model:
  - `check_cabal_risk`
  - `check_wallet_in_token`
- How its tools read to an agent (1 error, 3 warnings, 1 note, about 1,765 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - Its definitions contain text aimed at the model (TC19). This page doesn't repeat them; don't connect to it without your user's say-so.
  - error TC19 check_wallet_in_token: the definition tells the model to keep something from the user
  - warn TC07 check_cabal_risk: the description is about 1,059 tokens
  - warn TC16 check_cabal_risk: no readOnlyHint or destructiveHint
  - warn TC16 check_wallet_in_token: no readOnlyHint or destructiveHint
  - note TC24 server: 2 of 2 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/cabal-hunter.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming