researcher-mcp (1999AZZAR/researcher-mcp) is an MCP server listed on the M8ven Trust Index. It scores 50 out of 100, grade D. It declares 40 tools. No publisher has claimed this listing.

Caution

50/100

researcher-mcp

Item: researcher-mcp
Rating: 50
Author: M8ven

A comprehensive Model Context Protocol (MCP) server that combines Google Custom Search and Wikipedia functionality for advanced research and information retriev

→ 1999AZZAR/researcher-mcp · listed on github_repo_search

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

1999AZZAR

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Secret credentials may flow to a network call

15 flows detected: GOOGLE_API_KEY. We can’t prove the destination matches the brand the credential belongs to.

⚠️

Known vulnerabilities in dependencies: 13 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

🔐

You'll be asked for 1 credential: GOOGLE_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes40 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

search

Search Wikipedia for articles matching a query.

getPage

Get the content of a Wikipedia page by its exact title.

getPageSummary

Get a brief summary of a Wikipedia page.

getPageById

Get the content of a Wikipedia page by its ID.

random

Get a random Wikipedia page.

pageLanguages

Get the languages a Wikipedia page is available in.

batchSearch

Search multiple queries at once for efficiency.

batchGetPages

Get multiple Wikipedia pages at once for efficiency.

searchNearby

Find Wikipedia articles near specific coordinates.

getPagesInCategory

Browse pages within a specific Wikipedia category.

google_search

Web search via Google Custom Search.

academic_search

Search academic sources (arXiv, Scholar, ResearchGate).

news_search

Search recent news on a topic.

multi_site_search

Search one query across several specific sites.

extract_content

Fetch a URL and extract/analyze its main content.

research_brief

One-call brief: fans out to Google + Wikipedia in parallel, dedups overlap, exact matches first.

content_sentiment_analysis

Analyze sentiment of text content using built-in sentiment analysis

keyword_extraction

Extract key terms and topics from text content

url_metadata_extractor

Extract metadata from URLs including title, description, and basic info

citation_formatter

Format citations in APA, MLA, or Chicago style

research_session_manager

Manage research sessions, save findings, and organize notes

content_deduplication

Remove duplicate content from search results and consolidate similar items

archive_org_search

Search archived web pages on Archive.org (Wayback Machine)

data_export

Export research data in various formats (JSON, CSV, Markdown)

search_analytics

Analyze search trends and get insights from multiple search queries

news_monitor

Monitor news and get alerts for specific topics

content_summarizer

Summarize content from multiple URLs

fact_checker

Verify claims by searching for fact-checking sources

research_assistant

Comprehensive research assistant with multi-query analysis

search_trends

Track and analyze search interest trends over time

wikipedia_search

Search Wikipedia articles

wikipedia_get_page

Get Wikipedia page content

wikipedia_get_page_by_id

Get Wikipedia page content by ID

wikipedia_get_summary

Get a brief summary of a Wikipedia page

wikipedia_random

Get a random Wikipedia page

wikipedia_page_languages

Get the languages a Wikipedia page is available in

wikipedia_batch_search

Search multiple queries at once for efficiency

wikipedia_batch_get_pages

Get multiple Wikipedia pages at once for efficiency

wikipedia_search_nearby

Find Wikipedia articles near specific coordinates

wikipedia_get_pages_in_category

Browse pages within a specific Wikipedia category

// known CVEs in dependencies13 high6 medium11 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.25.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.25.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

highaxios@1.13.2GHSA-35jp-ww65-95wh

axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`

highaxios@1.13.2GHSA-3g43-6gmg-66jw

axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge

highaxios@1.13.2GHSA-43fc-jf86-j433

Axios is Vulnerable to Denial of Service via __proto__ Key in mergeConfig

Depend on this server? Get alerted when its CVEs change.Watch this server free →

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

🔐 secretGOOGLE_API_KEYOptional

configGOOGLE_CSE_IDOptional

configHELA_ENVELOPESet to true to wrap tool results in the canonical HeLaResult envelope (ok/summary/data/artifacts/provenance/warnings/sideEffects/execution) unset = off (byte-identical legacy output) No

configHELA_RUN_ID

configHELA_STEP_ID

configRESEARCHER_DEFAULT_LANGDefault Wikipedia language (overrides WIKIPEDIA_DEFAULT_LANGUAGE) en No

configRESEARCHER_GOOGLE_CACHE_TTL_MSGoogle cache TTL (ms) 1800000 No

configRESEARCHER_USER_AGENTHTTP User-Agent for fetches hela-enzyme/1.0 (researcher-mcp; …) No

configSERVER_NAMEServer name for identification hela-enzyme No

configWIKIPEDIA_CACHE_MAXMaximum Wikipedia cache entries 100 No

configWIKIPEDIA_CACHE_TTLWikipedia cache TTL (ms) 300000 No

configWIKIPEDIA_DEFAULT_LANGUAGEDefault Wikipedia language en No

// quality suggestions

Tool annotations

6/40 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

40/40 tools missing one or more hints — search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); getPage (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); getPageSummary (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +37 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 10/40 tools referenced in tests (25%)

Write tests that reference each tool by name so every tool has at least one test.

Secrets not logged

2 secret values sent to error

Redact or omit secret values from log output.

Production dependencies are patched

0 critical, 13 high severity in production deps — @modelcontextprotocol/sdk@1.25.1 (high), @modelcontextprotocol/sdk@1.25.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dependency freshness

2/8 production deps stale: sentiment@2022-06-26 (4.2y), axios-retry@2024-08-02 (2.1y)

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/1999azzar/researcher-mcp?variant=verified)](https://m8ven.ai/mcp/1999azzar/researcher-mcp)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 9e2bf63a017e085f7d7536e2bf0ec6ee493e34b4

code hash: 48f3de70c29819515376dc6b84d7c558d2a15500d6fb0219f86b2d42c71841f9

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client