kindly-web-search-mcp-server — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Monitor this implementation for changes in adoption, MCP interface, maintenance and permission boundary.

Reviewed Oct 10, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Search the web through Serper, Tavily or SearXNG and retrieve content

What we know

Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG. Search the web through Serper, Tavily or SearXNG and retrieve content.

Maintenance / activity evidence

GitHub REST pushed_at 2026-10-01T20:24:09Z

Tracking evidence observed Oct 10, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: medium.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Scoped by connected account, local OS, and configuration; verify exact permissions before installation. Complete write authority is not verified.
Provider API keys or private SearXNG endpoint
Web searches and third-party search queries

Provider costs and search-query transfer depend on configuration; fetched pages can contain prompt injection.

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

397 repository stars

Stars observed Oct 9, 2026.

Repository total for Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server.

All limitations / Review context

Has kindly-web-search-mcp-server changed its specific MCP integration, install method or privilege scope, and does it justify shortlist promotion?

High-impact permissions explicitly documented; no known blocker to an accurately caveated public Radar listing in limited first-party review.

Provider costs and search-query transfer depend on configuration; fetched pages can contain prompt injection.
Scoped by connected account, local OS, and configuration; verify exact permissions before installation.
Provider API keys or private SearXNG endpoint
Web searches and third-party search queries
Complete write authority is not verified.
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
No exhaustive advisory or runtime review performed; never infer installation safety.
Write actions/tool inventory not confirmed against exact tool documentation; listed action classes remain illustrative or context-dependent. Empty inventory does not establish read-only.
Setup and runtime permissions are implementation- and account-specific; follow linked upstream documentation.
Repository pushed_at explicitly observed

Original activity observations

GitHub REST pushed_at 2026-10-01T20:24:09Z

Technical identity

github.com/Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server

Exact implementation source: https://github.com/Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server ↗
Reviewed resource type: MCP Server
Repository identity: Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 10, 2026 · Latest source observation Oct 10, 2026

GitHub repository ↗
shelpuk-ai-technology-consulting/kindly-web-search-mcp-server
Recorded repository material and project history.

Setup · Watchlist

Install & Agents

Codex

Publisher instructions with a documented client setup path.

Source evidence observed Oct 12, 2026.

Additional setup details required — see the specific gaps below.

Warning

Search requires one supported backend; Serper is NOT universally required.
Browser requirement is limited to universal page_content extraction; GitHub token optional.
Publisher-specific exact credential-revocation procedure not established; use the issuing provider controls only if credentials actually exist.
Credential revocation is external-provider-specific or not documented in examined official project Setup/README; do not assert exact revocation CLI.
Set SERPER_API_KEY in your shell first, or choose the documented alternative provider. Example omits publisher optional GITHUB_TOKEN/browser path parameters. Do not copy with an unset key.
Run the removal command in the same client and configuration scope used for registration; this does not uninstall an application, revoke third-party authorization, or delete data.

Install / connect
MCP100 setup guide
Install uv/uvx first. At least ONE supported search backend is required; Chromium is necessary for arbitrary page_content extraction, not for all specialized-source searches.
uvx --version
Advanced configuration · client registration
client registration · Review before use
codex mcp add kindly-web-search \ --env SERPER_API_KEY="$SERPER_API_KEY" \ -- uvx --from git+https://github.com/Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server \ kindly-web-search-mcp-server start-mcp-server
Configure / authenticate
Publisher instructions
REQUIRED: set ONE supported search-provider credential/endpoint before registration: SERPER_API_KEY, SERPBASE_API_KEY, TAVILY_API_KEY, SEARXNG_BASE_URL, SOFYA_API_KEY, YDC_API_KEY, SERPLY_API_KEY, or APIFARE_TOKEN. SERPER is only one option. GITHUB_TOKEN is optional for improved GitHub content and rate limits. KINDLY_BROWSER_EXECUTABLE_PATH is conditional, not a required search credential. Chromium-based browser needed for universal page_content only.
Check connection
Suggested check
After setting exactly one supported search-provider key or endpoint, use codex mcp list, inspect the Kindly tool discovery in the session, then try a low-risk non-sensitive search. Seeing the server entry alone does not prove provider credentials are working.
Remove / uninstall / revoke
MCP100 setup guide
Remove the matching MCP configuration from the client. This does not uninstall the local package or revoke provider credentials. Client disconnect (codex, only if registered using the name `kindly-web-search`): `codex mcp remove kindly-web-search`. This unregisters the client entry; it does not uninstall packages or revoke remote service credentials.
codex mcp remove kindly-web-search

Official Documentation & Sources

What it does

Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG. Search the web through Serper, Tavily or SearXNG and retrieve content.

Capability: Search & Web
Resource type: MCP Server
Best fit: Search the web through Serper, Tavily or SearXNG and retrieve content

Representative uses

Find technical documentation online
Search provider-backed web indices
Fetch structured page results for analysis
Search the web through Serper, Tavily or SearXNG and retrieve content

Limitations

Provider costs and search-query transfer depend on configuration; fetched pages can contain prompt injection.
Setup and runtime permissions are implementation- and account-specific; follow linked upstream documentation.
Repository pushed_at explicitly observed

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Provider API keys or private SearXNG endpoint
Permissions: Scoped by connected account, local OS, and configuration; verify exact permissions before installation.
Data handling: Web searches and third-party search queries
Cost: may incur external API or infrastructure charges; unverified
Risk and cautions: Provider costs and search-query transfer depend on configuration; fetched pages can contain prompt injection.

Access scope and cautions

Write actions: Not verified
Risk level: moderate
Security notes: Provider costs and search-query transfer depend on configuration; fetched pages can contain prompt injection.

The reviewed evidence does not establish the complete write authority of this MCP. Consult the unresolved evidence before granting write access.

FAQ

Based on reviewed evidence as of 2026-10-09. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Find technical documentation online; Search provider-backed web indices; Fetch structured page results for analysis; Search the web through Serper, Tavily or SearXNG and retrieve content.

What setup and authentication are documented?

A complete connection procedure is not verified. Client notes: Command provided only where first-party command or package existence is established; verify the client configuration against upstream documentation. Installation/authentication detail is incomplete; do not infer settings from package name. These facts do not supply missing installation commands, credentials or a verified authentication procedure. Authentication: Provider API keys or private SearXNG endpoint

Can it modify data or perform write operations?

Not verified. The available evidence does not establish the complete write authority. Recorded permission context: Scoped by connected account, local OS, and configuration; verify exact permissions before installation.

What data-handling boundary should I consider?

Web searches and third-party search queries

What limitations and risks should I check before use?

Provider costs and search-query transfer depend on configuration; fetched pages can contain prompt injection. Setup and runtime permissions are implementation- and account-specific; follow linked upstream documentation. Repository pushed_at explicitly observed. No exhaustive advisory or runtime review performed; never infer installation safety.