V.A.P.E. (Virtual Ape Private Eye) — an autonomous on-chain security detective for Base, exposed over the standard Model Context Protocol (MCP).
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"vape-mcp-server","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
<!-- mcp-name: io.github.jUXTAPOSITION1/vape --> # V.A.P.E. MCP Server — standard Model Context Protocol `mcp_servers/vape_mcp.py` V.A.P.E. now speaks the **industry-standard Model Context Protocol** (MCP `2024-11-05`), so any MCP host — Claude, Cursor, VS Code Copilot, or a custom agent — can **discover and call V.A.P.E.'s real capabilities** with no bespoke glue. ## Why this way - **Zero new dependencies.** MCP is JSON-RPC 2.0 over stdio; the server speaks it directly with pure stdlib. Nothing to `pip install` — keeps VAPE compute-free and **Termux/Android-friendly** (stdio is the local transport). - **Real code, real data.** Every tool calls existing VAPE functions (`agents.investigate`, `agents.token_scan`, `agents.data_fetchers`, `agents.defillama`, the Memory retriever + SQLite index) directly in-process. The one exception is `wallet_trace`, which shells out to the real `skillforge/tools/recon/wallet_trace.sh` (Alchemy-backed, live-verified — see PR #145) rather than re-implementing it. No stubs, no fabricated numbers. - **Read-only / keyless-first.** Nothing here signs, spends, or mutates chain state — safe to expose to any host. ## Tools exposed (`tools/list`) | Tool | What it does | |------|--------------| | `investigate_token` | Deep on-chain investigation (GoPlus + DexScreener + Base RPC + hack feed) → 0-100 score + PROCEED/CAUTION/REJECT verdict | | `scan_token_safety` | Fast honeypot/tax/owner-power + liquidity scan → verdict | | `recent_hacks` | Recent DeFi exploits (DeFiLlama): dated, $ lost, chain, technique | | `fear_greed` | Current crypto Fear & Greed index | | `memory_search` | Query Central Memory (SQLite-indexed) by text/category/days | | `memory_stats` | Counts by category, severity, high-confidence | | `research_search` | Web search via the best available provider (Tavily/Brave, keyless fallback) | | `research_scrape` | Scrape a page to clean text/markdown (Firecrawl/BrightData/Apify, keyless fallback) | | `mcp_servers`…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.