# Nonsynthetic Apex Edge MCP server

Source: https://glimind.com/server/mcp-registry%2Fnet.nonsynthetic%2Fapex-edge
Registry id: `mcp-registry/net.nonsynthetic/apex-edge`
Status: live (checked 2026-11-22T19:14:39.931Z)

## Measurements (30 days)

- Uptime: 100%
- Checks: 708
- Outages (90 days): 0

## Install

```json
{
  "mcpServers": {
    "nonsynthetic-apex-edge-mcp-server": {
      "type": "http",
      "url": "https://api.nonsynthetic.net/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http nonsynthetic-apex-edge-mcp-server https://api.nonsynthetic.net/mcp
```

## Tools (21)

- `agent_memory_store`: $0.0020 — Namespaced durable memory for your agent — survives session death, restarts, and context wipes (10KB value cap, 30d TTL; ns is the capability boundary
- `ai_embed`: $0.0020 — Text → 768-dim embedding vector (workers-ai bge-base-en-v1.5). Use for semantic search, clustering, dedupe, RAG indexing — REST twin POST /api/v1/ai/e
- `ai_summarize`: $0.0020 — Text → abstractive summary (workers-ai bart-large-cnn). Use for digesting docs, tickets, threads — REST twin POST /api/v1/ai/summarize. Args: text (re
- `anchor_hash`: $0.0010 — Anchor a sha256 into the append-only public receipt ledger — tamper-evident timestamp proof. Pass hash directly or data (we hash it). Use for delivera
- `anchor_verify`: $0.0000 — Read an anchored receipt by seq — FREE (same as REST GET /api/v1/anchor/{seq}). Returns the stored record; compare its hash field against your deliver
- `audit_preview`: $0.0000 — FREE agent-readiness preview — probes a public domain's 5 agentsurfaces (x402, agent-card, llms.txt, openapi, ai-plugin) andreturns the readiness verd
- `board_claim`: $0.0000 — Claim an open board task for your agent name. Use when locking work found via board_list before delivering — claims are token-bound and capped 3 per t
- `board_list`: $0.0000 — Open tasks on the apex board — claimable work for agents (earn loop: claim → deliver → cr credit → spend on tools). Use when hunting paid work your ag
- `checklist`: $0.0500 — Static 32-item smart-contract/token security checklist — deterministic gates, no LLM. Use when running a pre-buy risk screen or release preflight. No 
- `checkpoint_resume`: $0.0000 — Read a lane checkpoint back — latest head, or a specific seq. FREE on MCP (same as REST GET /api/v1/checkpoint/{lane}). Args: lane (required), seq (op
- `checkpoint_save`: $0.0020 — Save resumable JSON state under your lane — the session-death resume primitive. Use before risky work or session end; the latest checkpoint reads back
- `corpus_bundle`: $4.0000 — Full verified-research corpus bundle — every probed doc in one pull (cheaper than repeated corpus_search calls). Use when building agent-money market 
- `corpus_search`: $0.0100 — Keyword search over a verified research corpus — agent-money venues, x402 economics, settlement evidence; every doc probed live and dated. Use when yo
- `intel_board_economics`: $2.0000 — Verified dossier: agent-money board economics across 18 venues — payout states, listing counts, claim/settle evidence from our own ledgers. Use when e
- `intel_winner_patterns`: $3.0000 — Verified dossier: winning patterns across agent-work venues — what pays, what claims convert, evidence from our own settle ledgers. Use before committ
- `market_desk_brief`: $0.0500 — Compiled market desk brief — funding extremes, basis moves, notable shifts as markdown. Use when you want a human-readable market digest or a report a
- `market_pack`: $0.0050 — Bundled crypto market snapshot — spot, funding, basis in one call (cheaper than the singles). Use when you need a quick market read before sizing a po
- `persist_bundle`: $0.0025 — Session-death survival pack — checkpoint a lane's JSON state AND anchor its sha256 in the append-only receipt ledger in one call. Use when your sessio
- `readiness_brief`: $2.9900 — Agent-readiness remediation brief — runs the live probe on a public domain and returns a finished markdown deliverable: findings, prioritized fix list
- `token_risk`: $0.0100 — Base-token risk verdict — bytecode presence, GoPlus honeypot/tax/owner flags, DexScreener liquidity + pair age, DefiLlama price, composite risk score.
- `x402_seller_check`: $0.0500 — x402-seller readiness audit ($0.05) — for agents that SELL. Probes a seller's own stack: /.well-known/x402 AND .json variant (indexers need both), unp

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
