EdgeDepth Research MCP Server
A read-only MCP server for EdgeDepth's market microstructure search engine, enabling users to query recorded crypto and TradFi perpetuals for market conditions, outcomes, and reproducibility-keyed evidence directly from MCP clients.
README
EdgeDepth Research MCP Server
@edgedepth/research-mcp is the official, read-only Model Context Protocol server for EdgeDepth, a market microstructure search engine over recorded Binance USDT-M crypto and TradFi perpetuals. Use it from Claude, Cursor, Codex, or any MCP client to find every verified occurrence of a market condition, inspect forward outcomes across the complete matched set, compare against an eligible baseline, and open replay-linked evidence.
Every result includes counts with denominators and a reproducibility key. Same key, same bytes.
Website · Search the market · REST API documentation · MCP setup guide · Learning hub
Why use EdgeDepth Research?
- Search recorded market microstructure: query a closed, versioned feature registry covering order flow, price action, volatility, funding, open interest, positioning, candle formations, and liquidations.
- Keep the denominator: every count reports the eligible population and exclusions behind it. Missing data is absent, never silently changed to zero.
- Measure outcomes without lookahead selection: forward returns, MFE, and MAE are computed over all occurrences. Outcome fields cannot be used as filters.
- Compare matched and baseline populations: deterministic cohort results put the matched distribution beside every other eligible predicate-false bucket.
- Audit and replay the evidence: results carry a reproducibility key, and representative occurrences include authenticated web handoffs to the exact recorded market moment.
- Stay read-only: the MCP tools search and retrieve research. They do not trade, modify alerts, publish reports, or write account data.
Choose a connection
The package exposes one tool core through two transports:
- Hosted MCP (recommended): connect to
https://mcp.edgedepth.com/mcpover Streamable HTTP and authorize once in your browser. No API key to copy. - Local stdio: run
npx -y @edgedepth/research-mcpwith an EdgeDepth API key.
Connect
Claude Desktop
In Settings > Connectors > Add custom connector, enter:
https://mcp.edgedepth.com/mcp
Complete the EdgeDepth browser authorization prompt.
Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"edgedepth-research": {
"url": "https://mcp.edgedepth.com/mcp"
}
}
}
Codex (~/.codex/config.toml)
[mcp_servers.edgedepth]
url = "https://mcp.edgedepth.com/mcp"
Then run:
codex mcp login edgedepth
Remove any old bearer_token_env_var line before using browser OAuth.
Local stdio with npx
Create a key on the EdgeDepth Developer page, then add:
{
"mcpServers": {
"edgedepth-research": {
"command": "npx",
"args": ["-y", "@edgedepth/research-mcp"],
"env": {
"EDGEDEPTH_API_KEY": "edk_live_YOUR_KEY"
}
}
}
}
Local stdio requires Node.js 20 or newer. Use the research:read key scope for the read-only tools and add research:interpret only when you need interpret_prose.
Recommended agent workflow
- Call
list_featuresfirst. It is the live, closed grammar and prevents invented fields. - Call
list_instrumentsto check the manifest-derived universe, coverage, and provenance. - If starting from natural language, call
interpret_prose. It returns a proposed document and never executes it. - Inspect or show that proposal, then pass the exact document to
run_scan. - Read rates from
outcomes_summary, which covers all occurrences. Page rows are examples, never the denominator. - Return the full reproducibility key with the answer. Use
next_pageonly with a cursor returned by the API.
Example instruction for an MCP client:
Call list_features first, then list_instruments for btcusdt and ethusdt.
Propose an exact query for elevated VPIN and one-sided taker flow over the last
seven complete UTC days. Show me the proposed document before running it.
Report counts with denominators, summarize outcomes over all occurrences, and
include the full reproducibility key.
Tools
| Tool | What it does |
|---|---|
list_features |
Returns the closed grammar registry: feature ids, types, ranges, operators, windows, sequence rules, limits, and error codes. |
list_instruments |
Returns the research universe and coverage. The default is a compact summary; use symbols: [...] for selected full records or full: true for the verbatim canonical universe. |
interpret_prose |
Turns prose into a proposed query document. It does not execute the query. Optional time_zone accepts an IANA time zone for calendar planning. |
run_scan |
Executes a research_query.v2 document and returns canonical result bytes with counts, denominators, outcomes, and the reproducibility key. |
next_page |
Continues a prior scan with its opaque cursor. Never construct cursors manually. |
snapshot_at |
Reads registry feature values, window aggregates, and fired rules as of a recorded moment. |
base_rate |
Counts matches and eligible buckets for one clause over a window. |
commonality |
Finds the deterministic intersection across multiple moments with selection-bias caveats included. |
get_report |
Retrieves a published report by its 8-character canonical hash. |
run_cohort |
Compares what followed every match with what followed every other eligible predicate-false bucket. |
All tools are read-only.
Research contract
- Validation failures pass through as
422 {"errors":[{"code":"...","message":"..."}]}. - Transport failures use the
{"error","code"}envelope. - Contract codes are machine-actionable. For errors such as
UNSUPPORTED_FEATUREorOUTCOME_IN_PREDICATE, calllist_features, repair the document, and retry. - Deterministic tools are exact-document, UTC-only tools.
interpret_prosemay use a time zone to plan dates, butrun_scan,run_cohort, andbase_ratenever reinterpret calendar language. - Reruns and ETag
304 Not Modifiedrevalidations are free.list_instrumentsETags are scoped to the requested summary, symbol projection, or full representation.
REST API and documentation
The MCP server is a thin, deterministic interface to the public EdgeDepth Research API:
- REST API quickstart
- Authentication and API keys
- Credits, caching, and limits
- Versioned query grammar
- Reproducibility contract
- Worked API examples
- MCP connection guide
- How EdgeDepth Research works
- What you can ask
The default REST base used by the stdio package is https://app.edgedepth.com/api/v1/research.
Environment
Local stdio
| Variable | Default | Purpose |
|---|---|---|
EDGEDEPTH_API_KEY |
None | Required for stdio tool calls. |
EDGEDEPTH_API_BASE |
https://app.edgedepth.com/api/v1/research |
Optional REST API base override. |
Hosted server operators
| Variable | Default | Purpose |
|---|---|---|
EDGEDEPTH_OAUTH_EXCHANGE_URL |
http://127.0.0.1:3002/api/mcp/oauth/exchange |
OAuth access-token exchange endpoint. |
MCP_INTERNAL_SECRET |
None | Required internal assertion secret; must match the web app. |
PORT |
3003 |
HTTP listen port. |
HOST |
127.0.0.1 |
HTTP listen host. |
Authentication and security
The hosted server uses browser OAuth. It validates opaque access tokens, exchanges them for separate short-lived internal assertions, and never passes the OAuth access token to the REST API. The MCP server is stateless and stores no user credentials.
Compatible clients rotate refresh tokens silently while the connection remains active. Review or revoke access at EdgeDepth Connected Apps.
API keys remain available for scripts, local stdio, and MCP clients without browser OAuth. Treat an edk_live_... key as a secret and never commit it to source control.
Develop
npm install
npm run build
npm test
npm run typecheck
TypeScript builds to dist/. Example nginx locations, systemd hardening, and operator environment values live under deploy/. Production deployment and npm publishing remain operator actions.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。