deep-research

deep-research is a skill for Claude Code, Codex from SECRET4422/mcp-deep-research-server. It costs 64 tokens per session (1,280 once invoked), scanned A, original, MIT.

A skill for carrying out multi-source web research with an automated research server. It searches, reads webpages, compares sources, checks claims, and produces cited findings.

In plain words
What is it for?
Use it for in-depth research, fact checking, comparing several URLs, and saving or retrieving structured research memory.
Why use it?
It reduces the manual work of gathering evidence from several sources and makes disagreements or supporting facts easier to identify.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for in-depth research, fact checking, comparing several URLs, and saving or retrieving structured research memory.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/secret4422/mcp-deep-research-server/deep-research
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add SECRET4422/mcp-deep-research-server --skill deep-research
Clone the repo
git clone --depth 1 https://github.com/SECRET4422/mcp-deep-research-server

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deep-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/secret4422/mcp-deep-research-server/deep-research/github.svg)](https://agentmods.dev/skills/secret4422/mcp-deep-research-server/deep-research)
Your own site
<a href="https://agentmods.dev/skills/secret4422/mcp-deep-research-server/deep-research"><img src="https://agentmods.dev/badge/skills/secret4422/mcp-deep-research-server/deep-research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deep-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/secret4422/mcp-deep-research-server/deep-research"><img src="https://agentmods.dev/badge/skills/secret4422/mcp-deep-research-server/deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,280 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.01280
Opus 5 $0.00032 $0.00640
Sonnet 5 $0.00013 $0.00256
Haiku 4.5 $0.00006 $0.00128

Measured 6d ago against content hash 0eaf41feeb7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deep-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/deep-research/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Research Agent Skill

This skill guides AI agents on orchestrating multi-step, evidence-backed research using the tools exposed by mcp-deep-research-server.

When to Use

  • When the user asks for in-depth, cited research on a technology, company, scientific topic, or market trend.
  • When an objective fact-check is requested to verify controversial claims or rumors.
  • When comparing 2–5 distinct URLs or source narratives to identify consensus vs contradictions.
  • When saving or retrieving structured research memory across long-running tasks.

Tool Reference & Routing

Operation Primary Tool Description
Full Investigation deep_research Automated pipeline: searches DuckDuckGo, parallel-scrapes 3–8 pages, extracts stats/entities, synthesizes cited report.
Targeted Query search_web Clean search (1–10 results) with time filtering (day, week, month, year).
Page Deep-Dive scrape_page Cleans HTML into Turndown markdown, extracts main content, headings, and links. SSRF-safe.
Cross-Source Analysis compare_sources Scrapes 2–5 URLs in parallel, surfaces common entities, shared consensus, and contradictory claims.
Verification & Audit fact_check_claim Searches supporting and debunking sources, returning an evidence-backed heuristic verdict.
Extract Key Points extract_insights Heuristic scoring of statistics, named entities, key sentences, and answered questions.
Long-Term Memory memory_save / memory_search Persistent storage in ~/.mcp-deep-research/memory.json for cross-session recall.

Autonomous Research Workflow

Follow this 5-stage discipline for every deep investigation:

graph TD
    A[User Request] --> B[1. Check Memory: memory_search]
    B --> C[2. Formulate 2-3 Multi-Angle Queries]
    C --> D[3. Run deep_research or search_web + parallel scrape]
    D --> E[4. Cross-Examine: compare_sources / fact_check]
    E --> F[5. Synthesize & Cite with URL Provenance]
    F --> G[6. Persist Key Findings: memory_save]

Read the full file on GitHub · 119 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 119 lines · 64 tokens per session scan A 0eaf41feeb7f

Subscribe to this mod's changes

deep-research is a skill published in the GitHub repository SECRET4422/mcp-deep-research-server (1 stars, last pushed 9d ago), licensed MIT. It adds 64 tokens to every session and 1,280 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.