cabal-radar-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BASE_RPC_URL | No | Base mainnet RPC endpoint | https://mainnet.base.org |
| SOLANA_RPC_URL | No | Solana mainnet RPC endpoint | https://api.mainnet-beta.solana.com |
| CABAL_RADAR_LICENSE_PATH | No | Local license file path override | ~/.cabal-radar/license.json |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_token_safetyB | Free Solana or Base token risk heuristics with evidence and limitations. |
| get_pro_upgrade_infoB | Payment options and local activation instructions. No wallet connection. |
| activate_pro_licenseB | Verify a mainnet payment receipt and save a machine-bound local Pro license. |
| detect_block0_bundlerD | Pro: bounded early-acquisition analysis. Launch coverage is explicitly reported. |
| trace_funding_clustersC | Pro: Solana shared-funder heuristics for wallet owners. Base reports unsupported without an indexer. |
| batch_audit_watchlistB | Pro: audit up to 20 tokens with bounded concurrency; return JSON and optional Markdown. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a fairly distinct target: free single-token scan, bundler detection, funding-cluster tracing, batch audit, and two licensing tools. The main ambiguity is between scan_token_safety and the Pro analysis tools, since an agent might not immediately know whether a risk scan already subsumes bundler/funding checks, but descriptions clarify the Pro/free split.
All names use snake_case with a leading verb (scan_, get_, activate_, detect_, trace_, batch_audit_), which is highly predictable. 'batch_audit_watchlist' is a slight deviation since 'batch' modifies the verb rather than being the verb itself, but it remains readable and consistent in style.
Six tools is well-scoped for a token-safety service with a free tier and a Pro tier. Each tool covers a distinct capability (scan, bundler detection, funding trace, batch audit, upgrade info, license activation) and none feels redundant or filler.
The surface covers the core lifecycle: free scanning, multiple Pro analyses, batch auditing, and license info plus activation. Minor gaps exist, such as no explicit license-status or deactivation check, but agents can work around this via get_pro_upgrade_info.