DeepResearchSAFE
Deep Research MCP is an intelligent research assistant built on the Model Context Protocol (MCP) that performs comprehensive, multi-step research on any topic.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.typescriptlang.org/) [](https://openai.com/) [](https://nodejs.org/)
📚 Overview
DeepResearch MCP is a powerful research assistant built on the Model Context Protocol (MCP). It conducts intelligent, iterative research on any topic through web searches, analysis, and comprehensive report generation.
🌟 Key Features
- Intelligent Topic Exploration - Automatically identifies knowledge gaps and generates focused search queries
- Comprehensive Content Extraction - Enhanced web scraping with improved content organization
- Structured Knowledge Processing - Preserves important information while managing token usage
- Scholarly Report Generation - Creates detailed, well-structured reports with executive summaries, analyses, and visualizations
- Complete Bibliography - Properly cites all sources with numbered references
- Adaptive Content Management - Automatically manages content to stay within token limits
- Error Resilience - Recovers from errors and generates partial reports when full processing isn't possible
🛠️ Architecture
┌────────────────────┐ ┌─────────────────┐ ┌────────────────┐ │ │ │ │ │ │ │ MCP Server Layer ├────►│ Research Service├────►│ Search Service │ │ (Tools & Prompts) │ │ (Session Mgmt) │ │ (Firecrawl) │ │ │ │ │ │ │ └────────────────────┘ └─────────┬───────┘ └───────────
699475757fe7OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add deep-research-mcp --env FIRECRAWL_API_KEY=${FIRECRAWL_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"deep-research-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (4)
3 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
complete-research | read | |
execute-research-step | write | |
generate-report | read | |
initialize-research | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@modelcontextprotocol/sdk, axios, dotenv, openai, typescript, zod
Gates applied: no_behavioural_pass, no_license.
699475757fe7full audit observations/trust-audit/mcp-server/ameeralns__deepresearch.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 699475757fe7 | SAFE | B | 89 | first audit |
Questions
What is the DeepResearch MCP server?
Deep Research MCP is an intelligent research assistant built on the Model Context Protocol (MCP) that performs comprehensive, multi-step research on any topic.
What tools does DeepResearch expose?
4 in total: 3 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is DeepResearch safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does DeepResearch need?
It reads FIRECRAWL_API_KEY and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does DeepResearch run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as deep-research-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (699475757fe7), read on 2026-10-08. The repository is watched and re-audited when it changes.