← MCP servers · u14app

Deep Research

BLOCKgrade F · trust 57/100

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

anthropicdeep researchdeep research apideepresearchdeepseekgeminigrokmcp server

Overview

From the repository's own README, as read at the audited commit.

<div align="center"><h1>Deep Research</h1>![GitHub deployments](https://img.shields.io/github/deployments/u14app/gemini-next-chat/Production)![GitHub Release](https://img.shields.io/github/v/release/u14app/deep-research)![Docker Image Size](https://img.shields.io/docker/image-size/xiangfa/deep-research/latest)![Docker Pulls](https://img.shields.io/docker/pulls/xiangfa/deep-research)[![License: MIT](https://img.shields.io/badge/License-MIT-default.svg)](https://opensource.org/licenses/MIT)[![Gemini](https://img.shields.io/badge/Gemini-8E75B2?style=flat&logo=googlegemini&logoColor=white)](https://ai.google.dev/)[![Next](https://img.shields.io/badge/Next.js-111111?style=flat&logo=nextdotjs&logoColor=white)](https://nextjs.org/)[![Tailwind CSS](https://img.shields.io/badge/Tailwind%20CSS-06B6D4?style=flat&logo=tailwindcss&logoColor=white)](https://tailwindcss.com/)[![shadcn/ui](https://img.shields.io/badge/shadcn/ui-111111?style=flat&logo=shadcnui&logoColor=white)](https://ui.shadcn.com/)[![Vercel](https://img.shields.io/badge/Vercel-111111?style=flat&logo=vercel&logoColor=white)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fu14app%2Fdeep-research&project-name=deep-research&repository-name=deep-research)[![Cloudflare](https://img.shields.io/badge/Cloudflare-F69652?style=flat&logo=cloudflare&logoColor=white)](./docs/How-to-deploy-to-Cloudflare-Pages.md)[![PWA](https://img.shields.io/badge/PWA-blue?style=flat&logo=pwa&logoColor=white)](https://research.u14.app/)[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/u14app/deep-research)</div>**Lightning-Fast Deep Research Report**Deep Research uses a variety of powerful AI models to generate in-depth research reports in just a few minutes. It leverages advanced "Thinking" and "Task" models, combined with an internet connection, to provide fast and insightful analysis on a variety of topics. **Your privacy is paramount - all data is processed and stored locally.**## ✨ Features- **R

Connect

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-code
claude mcp add deep-research --env ACCESS_PASSWORD=${ACCESS_PASSWORD} --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env ATLASCLOUD_API_KEY=${ATLASCLOUD_API_KEY} --env AZURE_API_KEY=${AZURE_API_KEY} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "deep-research": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "ACCESS_PASSWORD": "${ACCESS_PASSWORD}",
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
        "ATLASCLOUD_API_KEY": "${ATLASCLOUD_API_KEY}",
        "AZURE_API_KEY": "${AZURE_API_KEY}"
      }
    }
  }
}

Exposed tools (5) 3 read · 2 write · 0 destructive

ToolRiskDescription
deep-researchread
generate-SERP-queryread
search-taskread
write-final-reportwrite
write-research-planwrite

Details

Source
u14app/deep-research
npm
deep-research@0.11.1
Transports
sse · streamable-http
Credentials it reads
ACCESS_PASSWORDANTHROPIC_API_KEYATLASCLOUD_API_KEYAZURE_API_KEYBOCHA_API_KEYCRW_API_KEYDEEPSEEK_API_KEYEXA_API_KEYFIRECRAWL_API_KEYGOOGLE_GENERATIVE_AI_API_KEYGOOGLE_PRIVATE_KEYGOOGLE_PRIVATE_KEY_ID
License
MIT
Stars
4,684 · pushed 87d ago

Trust audit

Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)FAIL
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (8 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
found

Findings (18)

CRITICALHard-coded secrets · secret.private_key · CWE-798, CWE-321
src/utils/vertexAuth.ts:30
const pemHeader = "-----BEGIN PRIVATE KEY-----";
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
README.md:233
// AI provider, Possible values include: google, openai, anthropic, deepseek, atlascloud, xai, mistral, azure, openrouter, openaicompatible, pollinations, ollama
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
README.md:239
// Search provider, Possible values include: model, tavily, firecrawl, crw, exa, bocha, searxng
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
README.md:327
# Possible values include: google, openai, anthropic, deepseek, atlascloud, xai, mistral, azure, openrouter, openaicompatible, pollinations, ollama
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
README.md:330
# Possible values include: model, tavily, firecrawl, crw, exa, bocha, searxng
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
docs/deep-research-api-doc.md:39
// AI provider, Possible values include: google, openai, anthropic, deepseek, xai, mistral, azure, openrouter, openaicompatible, pollinations, ollama
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
env.tpl:73
# (Optional) Server-side Ollama API Proxy URL. Default, `http://0.0.0.0:11434`
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
env.tpl:106
# (Optional) Server-side Searxng API Proxy URL. Default, `http://0.0.0.0:8080`
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
next.config.ts:33
process.env.OLLAMA_API_BASE_URL || "http://0.0.0.0:11434";
LOWInventory / provenance · inv.hidden_file · CWE-1104
.node-version
.node-version
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/app/api/sse/live/route.ts:10
} from "../../utils";
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:296
"url": "http://127.0.0.1:3000/api/mcp",
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:312
"url": "http://127.0.0.1:3000/api/mcp",
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@ai-sdk/anthropic, @ai-sdk/azure, @ai-sdk/deepseek, @ai-sdk/google, @ai-sdk/google-vertex, @ai-sdk/mistral, @ai-sdk/openai, @ai-sdk/openai-compatible
Why it matters. 85 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README.md:257
// If you set an access password
Why it matters. asks the agent to read credentials
LOWPrompt injection · prompt.credential_read · CWE-94, CWE-1427
docs/deep-research-api-doc.md:79
// If you set an access password
Why it matters. asks the agent to read credentials
LOWPrompt injection · prompt.credential_read · CWE-94, CWE-1427
docs/deep-research-api-doc.md:312
// If you set an access password
Why it matters. asks the agent to read credentials
INFOInventory / provenance · inv.oversize · CWE-1104
public/scripts/pdf.worker.min.mjs
public/scripts/pdf.worker.min.mjs
Why it matters. 1032428 bytes not read

Gates applied: critical_finding, no_behavioural_pass.

Audited 2026-09-14 · audit v0.4.0 · source sha ecca09b0af1d · full audit: observations/trust-audit/mcp-server/u14app__deep-research-8.json · Report an issue or request a re-scan

Audit history

DateSourceVerdictGradeScoreChange
2026-09-14ecca09b0af1dBLOCKF57first audit

Alternatives

Other servers in the same categories, safer ones first.

Questions

What is the Deep Research MCP server?

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

What tools does Deep Research expose?

5 in total: 3 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Deep Research safe to connect to an agent?

No — not without reading the findings first. The audit graded it F (57/100) and found 6 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What credentials does Deep Research need?

It reads ACCESS_PASSWORD, ANTHROPIC_API_KEY, ATLASCLOUD_API_KEY, AZURE_API_KEY, BOCHA_API_KEY, CRW_API_KEY, DEEPSEEK_API_KEY, EXA_API_KEY, FIRECRAWL_API_KEY, GOOGLE_GENERATIVE_AI_API_KEY, GOOGLE_PRIVATE_KEY and GOOGLE_PRIVATE_KEY_ID 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 Deep Research run?

It speaks sse and streamable-http, so it runs as a service you connect to over the network. It is published on npm as deep-research at 0.11.1.

How current is this page?

The grade is for one exact copy of the source (ecca09b0af1d), read on 2026-09-14. The repository is watched and re-audited when it changes.

Provenance: OBSERVED · read 2026-09-14 · job trust-audit-2026-09-14