150,000+ agents registered. Trust scores show their math.Explore →
Explorer/MCP/tvermolaev-source/deep-research-mcp
REMOTE

Deep Research MCP Server

tvermolaev-source/deep-research-mcp

Enables iterative deep web research through MCP clients, using SearXNG search, Crawl4AI parsing, and LLM synthesis.

↗tvermolaev-source/deep-research-mcpExternal link; availability not verifiedRemote-capable
The Newcomer
Hasn't been around long. Nothing caught our attention, but there isn't much history to go on yet.
Time indexed (2mo)
0toolsRemote/ HTTP2moindexed
Checked Aug 1, 2026
The scanner shows
Not enough data to score this server yet.
First indexed Aug 1, 2026
Server Profile
⚙
Tools catalogued
0
No tools reported by this server.
☁
Hosting
Remote / HTTP
Runs on the internet. No access to your filesystem, SSH keys, or environment variables.
○
Registry presence
Not verified
Not yet verified by the Official MCP Registry.
●
Liveness
—
No liveness checks recorded yet.
Publisher Verification
Not listed on the Official MCP Registry.
Source repository is available for review.
↗tvermolaev-source/deep-research-mcpExternal link; availability not verified
Environment variables (31)
MCP_HOSTstringOPTIONALdefault: 0.0.0.0
Хост MCP-сервера
MCP_PORTstringOPTIONALdefault: 8765
Порт
LLM_MODELstringOPTIONALdefault: qwen2.5:7b
Базовая модель (используется обеими ролями, если роли не заданы)
LLM_API_KEYstringOPTIONALdefault: ollama
API-ключ
SEARXNG_URLstringOPTIONALdefault: http://searxng:8080
URL SearXNG
Show all 31 environment variables
LLM_BASE_URLstringOPTIONALdefault: http://localhost:11434/v1
OpenAI-совместимый endpoint
NEWS_DOMAINSstringOPTIONAL
Домены мировых СМИ — для режима «новости/статьи»
SOCIAL_DOMAINSstringOPTIONAL
Домены соцсетей — поднимаются в режиме «ищи в социальных сетях»
BLOCKED_DOMAINSstringOPTIONAL
Список доменов под безусловный отсев (opt-in)
QUERY_REPHRASERstringOPTIONALdefault: true
Включён ли Query Rephraser
SEARXNG_ENGINESstringOPTIONALdefault: google,bing,duckduckgo
Список движков
ACADEMIC_DOMAINSstringOPTIONAL
Домены научных/академических источников — для режима «факт-чек»
INTENT_DETECTIONstringOPTIONALdefault: true
Включён ли детектор намерений в запросе пользователя
LLM_WORKER_MODELstringOPTIONALdefault:
Слабая/дешёвая модель для извлечения фактов из чанков (пусто → LLM_MODEL)
MAX_QUERY_LENGTHstringOPTIONALdefault: 120
Максимальная длина запроса для рефразера
MIN_RESULT_SCOREstringOPTIONALdefault: 0.0
Фильтр по SearXNG-score. 0 = не фильтровать
PRIORITY_DOMAINSstringOPTIONAL
Список доменов-экспертов, +100 к рангу (opt-in)
SEARXNG_LANGUAGEstringOPTIONALdefault: ru
Язык поиска (можно `en`, `en-all`)
CRAWL_TIMEOUT_SECstringOPTIONALdefault: 60
Таймаут парсинга URL
LLM_PLANNER_MODELstringOPTIONALdefault:
Сильная модель для планирования источников и финального синтеза (пусто → LLM_MODEL)
LLM_WORKER_API_KEYstringOPTIONALdefault:
Опц. отдельный API-ключ для worker'а (пусто → LLM_API_KEY)
SEARXNG_CATEGORIESstringOPTIONALdefault: general
Дефолтные SearXNG-категории (используются, если LLM-планировщик не сработал). Допустимые: `general news science social videos images files music it map`
SEARXNG_SAFESEARCHstringOPTIONALdefault: 0
0/1/2
LLM_WORKER_BASE_URLstringOPTIONALdefault:
Опц. отдельный endpoint для worker'а (например, локальный Ollama с 3B-моделью) (пусто → LLM_BASE_URL)
MAX_PARALLEL_CRAWLSstringOPTIONALdefault: 5
Одновременных парсингов
MAX_ITERATIONS_SPEEDstringOPTIONALdefault: 2
Лимиты итераций по режимам: speed
MAX_RESULTS_PER_QUERYstringOPTIONALdefault: 10
Сколько просить у SearXNG на запрос
DOMAIN_BOOST_THRESHOLDstringOPTIONALdefault: 2
Буст домена, если он встретился по ≥N запросам
MAX_ITERATIONS_QUALITYstringOPTIONALdefault: 25
Лимиты итераций по режимам: quality
MAX_ITERATIONS_BALANCEDstringOPTIONALdefault: 6
Лимиты итераций по режимам: balanced
RESULTS_TOP_K_PER_QUERYstringOPTIONALdefault: 10
Сколько URL оставлять на запрос после реранкинга

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
More from tvermolaev-source
Yandex Wordstat MCP
MCP server for Yandex Wordstat v2 API enabling keyword research and search trend analysis with in-memory caching, integrated via mcpo proxy with Open WebUI.
Similar servers
keycloak-source-mcp
An MCP server that enables AI assistants to navigate, search, and analyze local Keycloak source code to support developer customizations like SPIs and authenticators. It provides tools for searching classes, generating boilerplate code, detecting breaking changes between versions, and tracing dependencies.
MCP Web Research Server
The MCP Web Research Server enables real-time web research with Claude by integrating Google search, capturing webpage content and screenshots, and tracking research sessions.
JS Reverse MCP
An MCP server for JavaScript reverse engineering that enables AI to perform browser debugging, script analysis, and automated hook injection. It streamlines complex workflows like deobfuscation, network tracing, and risk assessment through direct browser integration.
Memory Store MCP Server
A lightweight, stateless MCP server utilizing Puppeteer for web searches, returning structured JSON results, easily integratable with other MCP-enabled systems.
devdoc
A documentation MCP server that crawls websites and Git repositories, stores them as Markdown, and provides tools to search and retrieve documentation for local LLMs and AI agents.
BerryRAG
A local vector database RAG system that integrates with Playwright MCP for web scraping, enabling users to build searchable knowledge bases from web content with multiple embedding providers and Claude-optimized context formatting.
Indexed from Glama · Updates nightly