mcpField
N
NightWatch Live Intelligence

NightWatch Live Intelligence

Remote
nightwatch-v1-frontend.onrender.comFinance0Updated 14w ago

About NightWatch Live Intelligence

NightWatch Live Intelligence provides real-time crypto asset data for trading agents, including liquidity grades, transfer routes and spread history. Its 33 MCP tools also expose coverage and bot-tradability indices, alongside agent skill recipes.

Key features

  1. 01Liquidity grades for listed tokens
  2. 02Per-chain deposit and withdrawal routes
  3. 03Cross-exchange spread history
  4. 04Coverage Grade and BTI indices
  5. 0533 live MCP tools
  6. 06Agent skill recipes for trading tasks

Use cases

  1. 01Check token coverage and tradability before trading
  2. 02Verify transfer routes and spreads before moving assets
  3. 03Screen token lists for bot-tradable candidates

MCP support

Provides 33 live tools through a Streamable HTTP MCP endpoint, covering token intelligence, warnings, microbursts and other agent-facing data. The endpoint can be used with Claude Code, Cursor and other MCP clients.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://nightwatch-v1-api.onrender.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

36
ParameterTypeRequiredDescription
symbolstringYesTrading pair symbol
exchangestringYesExchange ID

Details

From the project README

NightWatch Skills — recipes for AI agents

NightWatch Live Intelligence is a real-time, multi-layer crypto asset intelligence system: it watches ~10 exchanges (global + Korean), grades every listed token's liquidity (A–F, 15-step detail), tracks per-venue deposit/withdrawal doors per chain, records cross-exchange spread history, and condenses all of it into two agent-facing gate indices — Coverage Grade ("how well do we actually see this asset") and BTI, the Bot-Tradability Index ("which bot strategy types are viable on it right now"). Everything is served fresh from the live pipeline; missing data is reported as missing, never faked.

One product, four layers

LayerWhat it isWhere
MCPConnection standard — 33 live tools, no auth to browsehttps://nightwatch-v1-api.onrender.com/mcp
APIRaw data under a stable REST contract (free tier + Pro key X-NW-User-Key for deep fields)https://nightwatch-v1-api.onrender.com
SkillsTask recipes (SKILL.md folders) — this reposkills/
TraderOpen-source reference trading bot (paper-first, non-custodial)jamboree777/nightwatch-trader

MCP endpoint

https://nightwatch-v1-api.onrender.com/mcp

Streamable HTTP, 33 tools (token intel, microburst, warnings, mining, oracle bounties, Proof-of-Insight, SBT reputation, Quartermaster decision state, …). Works with Claude Code, Cursor, and any MCP client:

{
  "mcpServers": {
    "nightwatch": {
      "type": "http",
      "url": "https://nightwatch-v1-api.onrender.com/mcp"
    }
  }
}

Listed on the official MCP registry as io.github.jamboree777/nightwatch — metadata in server.json, update procedure in PUBLISH.md.

For LLMs / agents

Skills catalog

Each folder under skills/ is one recipe: a SKILL.md any agent can load and follow. All endpoints referenced are live and were verified returning 200 at publish time.

SkillWhat it does
token-intel-checkRead the three gates (Coverage / Rating / BTI) from one /intel call before touching a token
arb-route-checkCheck transfer doors + spread history before any cross-exchange move
coverage-screenScreen a token list down to bot-tradable candidates
kimchi-premium-readRead the Korea-axis premium correctly (FX vs stablecoin basis)
contribute-factsWORK-Claw: submit sourced facts to the Knowledge Graph and earn Cherry
fund-operating-procedureThe fund's invariant arbitrage pipeline (spread → doors → identity → grade → costs → repeat caps → settle) with a live endpoint per step
capital-allocation-quartermasterQuartermaster: two-book capital segregation, attribution-derived venue floors, rebalance-through-arbitrage, locked collateral pools

Honesty rules baked into every skill: free vs Pro-key fields are labeled; unknown never means no; no capability is claimed that the live API does not actually serve.

License

Documentation and skill recipes in this repository: CC BY-NC-SA 4.0 — see LICENSE.md. The reference trading bot is separately MIT-licensed in its own repo.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.