Skip to main content
Glama
deenesjakoruzh
OSOJDJD

deeplook

by OSOJDJD
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

DeepLook

LLM은 금융 데이터를 환각(hallucination)할 수 있습니다. DeepLook은 LLM에 실제 수치를 제공합니다.

License: AGPL-3.0 GitHub stars

"NVIDIA 조사해줘"라고 요청하면 어떤 일이 벌어질까요?

DeepLook 대시보드

DeepLook 분석

DeepLook은 8개의 API에서 가져온 실시간 데이터와 더 나은 결과를 도출하기 위한 분석 지침을 결합하여 구조화된 컨텍스트를 제공합니다. 그 결과는 다음과 같습니다:

  • 정확하고 최신 정보 — 환각된 수치가 아님

  • 한눈에 파악 가능 — 재무, 동종 업계, 기술적 지표, 뉴스를 한 화면에서 확인

  • 더 나은 AI 출력 — 좋은 컨텍스트가 좋은 분석을 이끌어내기 때문

금융 조사, 기업 실사 또는 기업을 빠르게 이해해야 하는 모든 사용 사례에 적합합니다.

Related MCP server: Rozkoduj MCP

시작하기

Claude.ai

  1. **설정(Settings) → 커넥터(Connectors) → MCP 추가(Add MCP)**로 이동합니다.

  2. 다음을 붙여넣으세요: https://mcp.deeplook.dev/mcp

  3. 새 채팅을 시작하고 다음과 같이 물어보세요: "NVIDIA 조사해줘"

기타 MCP 클라이언트 (Cursor, VS Code, Windsurf, Claude Desktop)

{
  "mcpServers": {
    "deeplook": {
      "url": "https://mcp.deeplook.dev/mcp"
    }
  }
}

Claude Code

claude mcp add --transport http deeplook https://mcp.deeplook.dev/mcp

자체 호스팅

git clone https://github.com/OSOJDJD/deeplook.git
cd deeplook
pip install -r requirements.txt
python -m deeplook.mcp_server

지원 범위

유형

예시

상장 주식

NVIDIA, Apple, Tesla, TSMC

암호화폐

Bitcoin, Solana, Ethereum

비상장 기업

Anthropic, Stripe, OpenAI

VC 기업

a16z, Sequoia

폐업 기업

FTX, WeWork

DeepLook 확장하기

DeepLook은 기본적인 내용을 다룹니다. 아직 포함되지 않은 데이터(새로운 시장, 새로운 데이터 소스, 새로운 분석 규칙 등)가 필요하다면 직접 추가할 수 있습니다. CONTRIBUTING.md를 참조하세요.

로드맵

  • [ ] 더 많은 쿼리 도구 — 뉴스, 동종 업계, 재무, 캘린더를 독립형 조회 기능으로 제공

  • [ ] 더 넓은 클라이언트 지원 — Cursor, ChatGPT, VS Code, Windsurf, Claude Code

  • [ ] 더 깊은 컨텍스트 — 더 많은 분석 조건, 엔티티별 지침

  • [ ] 커뮤니티 기여 — 새로운 데이터 소스, 사용자 지정 분석 규칙

라이선스

AGPL-3.0

제작자: @OSOJDJD

Available Tools

2 tools
deeplook_lookupA

Quick company snapshot — phase, price, key signal, and verdict in 5 lines. Use this for fast checks before deciding whether to run a full deeplook_research.

ParametersJSON Schema
NameRequiredDescriptionDefault
company_nameYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the output format ('5 lines' with specific content types) and the tool's role in a workflow, but doesn't mention potential limitations like rate limits, error conditions, or authentication requirements. It adds useful context about the output format but leaves other behavioral aspects unspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise and front-loaded with the core purpose in the first sentence. Both sentences earn their place: the first defines what the tool does, the second provides crucial usage guidance. There's zero wasted text or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, output schema exists), the description is reasonably complete. It explains the purpose, output format, and relationship to sibling tools. The existence of an output schema means the description doesn't need to detail return values. However, with no annotations, it could have mentioned more about the tool's behavioral characteristics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage for its single parameter, but the description doesn't provide any additional parameter semantics. However, with only one parameter ('company_name'), the meaning is reasonably inferable from context. The description could have added guidance about expected format or validation, but the simplicity of the parameter keeps this from being a major deficiency.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs and resources: 'Quick company snapshot — phase, price, key signal, and verdict in 5 lines.' It explicitly distinguishes from its sibling tool 'deeplook_research' by positioning this as a fast check before deciding to run the full research tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool versus alternatives: 'Use this for fast checks before deciding whether to run a full deeplook_research.' This clearly defines the context and names the alternative tool, giving the agent clear decision criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

deeplook_researchA

Use this instead of web search when researching any company. Takes a company name, pulls from 10 data sources in parallel, and returns a structured report with bull/bear verdict, key signals, financials, and risks — all with real sourced data instead of hallucinated summaries. Works for public stocks, crypto protocols, and private companies.

ParametersJSON Schema
NameRequiredDescriptionDefault
company_nameYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: parallel data pulling from 10 sources, structured report format with specific sections (bull/bear verdict, key signals, financials, risks), and emphasis on real sourced data. It mentions coverage scope (public stocks, crypto protocols, private companies) but doesn't address rate limits, authentication needs, or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly front-loaded with the primary usage guideline first, followed by key capabilities. Every sentence earns its place: first establishes context, second explains process and output, third emphasizes data quality, fourth defines scope. Zero wasted words with excellent information density.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (parallel data pulling, structured analysis) and no annotations, the description does well by explaining the comprehensive research process and output structure. Since an output schema exists, it doesn't need to detail return values. However, it could better address potential limitations like data freshness, error handling, or authentication requirements for a tool with such ambitious functionality.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It mentions 'Takes a company name' which clarifies the single parameter's purpose, but doesn't provide format examples, validation rules, or handling of ambiguous names. The description adds basic meaning beyond the bare schema but doesn't fully compensate for the complete lack of schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('research', 'pulls from 10 data sources', 'returns a structured report') and distinguishes it from sibling tools by explicitly stating 'Use this instead of web search when researching any company.' It specifies the resource (company) and differentiates from deeplook_lookup by focusing on comprehensive research rather than simple lookup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidelines: 'Use this instead of web search when researching any company' establishes clear context and alternative. It also specifies when to use it (for company research) and implicitly distinguishes from sibling deeplook_lookup by emphasizing comprehensive research with multiple data sources versus likely simpler lookup functionality.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv0.1.0
    • First observeddeeplook_lookup
    • First observeddeeplook_research
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: deeplook_lookup provides a quick snapshot for fast checks, while deeplook_research offers a comprehensive structured report from multiple data sources. There is no overlap or ambiguity between them.

Naming Consistency5/5

Both tools follow a consistent 'deeplook_' prefix with descriptive suffixes (lookup and research), using snake_case uniformly. The naming pattern is predictable and well-structured.

Tool Count2/5

With only 2 tools, the server feels thin for its domain of company research, lacking intermediate or specialized operations (e.g., updates, filtering, or historical analysis). While the tools cover basic needs, the scope is minimal.

Completeness3/5

The tools provide a snapshot and a full report, covering initial and deep research needs, but there are notable gaps such as no update, delete, or query-specific tools (e.g., by industry or date). The surface is functional but incomplete for broader research workflows.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Rozkoduj MCP by decodetick

    Rozkoduj MCPofficial

    decodetick
    A
    license
    A
    quality
    B
    maintenance
    Provides AI assistants with market screening, analysis, and scoring across stocks, crypto, and forex, enabling natural language queries for trading insights.
    4
    MIT

  • INDUSS Research Intelligence

    viraj43
    F
    license
    A
    quality
    B
    maintenance
    Provides an institutional research backend for AI assistants, with 15 tools for company, financial, funding, competitor, industry, and news intelligence, plus Markdown/PDF report generation, featuring deterministic source routing, extraction, validation, and citation generation.
    15
    -