What can you do with this server?

The Scouts-AI-MCP server exposes a single web_search tool for AI agents and LLM applications to search the public web — no API key required. * Search the web using natural-language queries (1–512 characters), powered by the SCOUTS-AI API. * Specify search parameters: optional BCP-47 lang code (e.g., en, fr; defaults to English) and optional page number (1–10). * Receive structured JSON results: up to 10 results per page, each with title, url, content snippet, publishedAt, and engine. * Get fresh, real-time information — ideal for recent events, up-to-date context, or web citations. * Integrate with MCP-compatible hosts (Claude Desktop, Cursor, Open WebUI, Continue, Cline) via stdio or HTTP transport. * Deploy via Docker with the MCP endpoint exposed at http://localhost:8765/mcp. * Configure via environment variables (API base URL, timeout, user-agent, default language, query length limits, etc.). * Handle errors gracefully, including invalid inputs, rate limits (429), and server errors (5xx).

Scouts-AI-MCP

by kecven

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

scouts-ai-mcp

Model Context Protocol (MCP) server that exposes the SCOUTS-AI web search API as a single web_search tool for AI agents, LLM apps, answer engines and GEO workflows.

One tool, no API key. Backed by GET https://scouts-ai.com/api/search.
Drop-in for Claude Desktop, Cursor, Open WebUI, Continue, Cline and any MCP host.
Python ≥ 3.10, fastmcp (>=2.0, currently resolves to 3.x), httpx.
MIT licensed.

Install

pip install scouts-ai-mcp

Related MCP server: Gemini MCP Server

Run (stdio)

scouts-ai-mcp

That's it. Wire it into your MCP host of choice — for example, Claude Desktop's claude_desktop_config.json:

{
  "mcpServers": {
    "scouts-ai": {
      "command": "scouts-ai-mcp"
    }
  }
}

Run (HTTP)

For remote MCP hosts and self-hosted bridges:

scouts-ai-mcp --transport http --host 127.0.0.1 --port 8765

Run (Docker)

A multi-arch (linux/amd64 + linux/arm64) image is published to Docker Hub as kecven/scouts-ai-mcp. It runs the MCP server in streamable HTTP mode on port 8765 and exposes the web_search tool at http://localhost:8765/mcp. No API key, no external dependencies.

Quick start:

docker run --rm -p 8765:8765 kecven/scouts-ai-mcp:0.1.7

Then point any streamable-HTTP MCP host at http://localhost:8765/mcp (or, when run behind a public proxy, https://<your-host>/mcp).

Override the upstream API base URL:

docker run --rm -p 8765:8765 \
  -e SCOUTS_AI_BASE_URL=https://scouts-ai.com \
  kecven/scouts-ai-mcp:0.1.7

Append CLI args (the image entrypoint is scouts-ai-mcp):

docker run --rm -p 8765:8765 kecven/scouts-ai-mcp:0.1.7 --log-level=DEBUG

Available tags:

kecven/scouts-ai-mcp:0.1.7 — pinned, recommended for production.
kecven/scouts-ai-mcp:0.1 — minor-version rolling tag.
kecven/scouts-ai-mcp:latest — latest stable release.

Build and push locally (requires docker buildx):

docker buildx build \
  --platform linux/amd64,linux/arm64 \
  -f Dockerfile.hosted \
  -t kecven/scouts-ai-mcp:0.1.7 \
  -t kecven/scouts-ai-mcp:0.1 \
  -t kecven/scouts-ai-mcp:latest \
  --push .

The image runs as a non-root user (scouts, uid 1001) and includes a TCP-level HEALTHCHECK on 127.0.0.1:8765 (the streamable HTTP endpoint does not return 200 on plain GET, so an HTTP probe would be unreliable).

Tool: `web_search`

Parameter	Type	Default	Description
`query`	string	—	Search query, 1–512 chars.
`lang`	string	`en`	BCP-47 language code (e.g. `en`, `en-US`).
`page`	int	`1`	1-based page number, 1–10. `page=1` is the reliable default; pages `>1` may be empty for some queries because the upstream provider (Bing) does not always return additional pages.

Returns a compact JSON object mirroring the SCOUTS-AI response shape:

{
  "query": "rust async runtime",
  "lang": "en",
  "page": 1,
  "pageSize": 10,
  "cached": false,
  "tookMs": 412,
  "results": [
    {
      "title": "Tokio - An asynchronous runtime for Rust",
      "url": "https://tokio.rs/",
      "content": "Tokio is an asynchronous runtime for the Rust programming language...",
      "publishedAt": "2025-11-14T00:00:00Z",
      "engine": "bing"
    }
  ]
}

Error handling

The tool raises ToolError (rendered as an MCP tool error) when:

The query is empty/too long or lang/page are invalid → invalid arguments.
The upstream returns 429 → rate limit exceeded; honors Retry-After when present.
The upstream returns 5xx or the network call fails → SCOUTS-AI temporarily unavailable.
The upstream returns a structured 4xx error envelope → forwards the code and message.

Configuration

All settings are environment variables. Defaults match the public SCOUTS-AI deployment.

Variable	Default	Description
`SCOUTS_AI_BASE_URL`	`https://scouts-ai.com`	Base URL of the SCOUTS-AI API.
`SCOUTS_AI_TIMEOUT_S`	`5.0`	HTTP timeout in seconds (0.1–60).
`SCOUTS_AI_USER_AGENT`	`scouts-ai-mcp/0.1.7`	User-Agent header.
`SCOUTS_AI_DEFAULT_LANG`	`en`	Default `lang` when the tool omits it.
`SCOUTS_AI_MAX_QUERY_LENGTH`	`512`	Reject queries longer than this.
`SCOUTS_AI_MAX_PAGE`	`10`	Reject page numbers above this.

Development

git clone https://github.com/kecven/scouts-ai-mcp.git
cd scouts-ai-mcp
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
pytest

License

MIT — see LICENSE.

Available Tools

1 tool

web_searchA

Search the public web via SCOUTS-AI and return compact JSON results. Use this when the user asks a question that requires current information, fresh context, or citations from the open web. No API key required. Returns at most 10 results per page.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	Natural-language search query, 1-512 characters.
`lang`	No	Optional BCP-47 language code (e.g. "en", "en-US"). Defaults to "en".
`page`	No	Optional 1-based page number, 1-10. Defaults to 1.

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It mentions that results are 'compact JSON' and 'at most 10 results per page,' which is useful. However, it doesn't discuss other behaviors like rate limits, caching, or the fact that it's a read-only operation. The transparency is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: three sentences that front-load the core purpose, followed by usage guidance and a behavioral note. Every sentence earns its place without unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple, and the output schema exists, so return values are covered. The description provides all necessary context: what it does, when to use it, authentication (none), and a key behavioral constraint (max 10 results). It is complete for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds minimal semantic value beyond the schema—it clarifies the default language ('en') despite the schema saying null, and confirms the page numbering. This is helpful but not transformative.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search the public web via SCOUTS-AI and return compact JSON results.' It uses a specific verb ('search') and resource ('the public web'), and is straightforward with no ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use the tool: 'Use this when the user asks a question that requires current information, fresh context, or citations from the open web.' It also notes that no API key is required. While it doesn't mention when not to use it, the context is clear enough for an AI agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

1 tool updatev0.1.5Jun 9, 2026
- First observedweb_search

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.3/5.0

Scored 2026-06-09 18:55 across 1 tool

Disambiguation5/5

Only one tool exists, so there is no ambiguity. The tool's purpose is clearly defined.

Naming Consistency5/5

The single tool name 'web_search' follows a clear verb_noun pattern (snake_case) and is internally consistent.

Tool Count5/5

One tool is appropriate for a server focused solely on web search. The scope is well-defined and the tool serves its purpose effectively.

Completeness4/5

The tool covers basic web search well, but lacks support for pagination or advanced filters, which are minor gaps for a search-specific server.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

SSearch B
cc.ssearch
Free web search for AI agents. No API key required. Hosted MCP in active development.
Search Browser Automation
71
MESSORA A
dev.messora
Scrape, crawl and search the web for AI agents via MCP.
Web Scraping Browser Automation Search
51
mcp COAuth
com.wix
A Model Context Protocol server for Wix AI tools
Developer Tools Content Management Systems App Automation
216
mcp-serpOAuth
io.github.AceDataCloud
MCP server for Google search results via SERP API
Search Browser Automation Web Scraping
21

Related MCP Servers

MCP Google Custom Search
RAG Systems Search
limklister
A
license
B
quality
D
maintenance
A Model Context Protocol server that enables LLMs to perform web searches using Google's Custom Search API through a standardized interface.
Updated a year ago (2025-10-12 15:46 UTC)
1
47
MIT
Gemini MCP Server
Search RAG Systems
philschmid
A
license
Not graded
quality
D
maintenance
A Model Context Protocol server that enables LLMs to perform web searches using Google's Gemini API and return synthesized responses with citations.
Updated a year ago (2025-06-13 13:47 UTC)
54
MIT
WebQuest MCP
Browser Automation Web Scraping
mustafametesengul
A
license
Not graded
quality
B
maintenance
A Model Context Protocol server that exposes powerful web search and scraping tools to AI agents and MCP-compatible clients.
Updated 7 months ago (2026-02-12 20:56 UTC)
Apache 2.0
tavily-firecrawl-mcp
Web Scraping Search
bpzx
A
license
A
quality
C
maintenance
A Model Context Protocol server for web scraping and searching, with automatic fallback from Tavily to Firecrawl for fetching web content.
Updated 3 months ago (2026-06-21 10:36 UTC)
2
1
MIT

scouts-ai-mcp

Install

Run (stdio)

Run (HTTP)

Run (Docker)

Tool: web_search

Error handling

Configuration

Development

License

Available Tools

Output Schema

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

MCP Google Custom Search

Gemini MCP Server

WebQuest MCP

tavily-firecrawl-mcp

Tool: `web_search`