Skip to main content
Glama
zbkm

mmnt-mcp-server

by zbkm

mmnt_search

Search the Mamont search engine to find web content using specific queries and page navigation.

Instructions

Search in Mamont search engine

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesquery string
pageYespage number

Implementation Reference

  • The core handler function `searchMamont` that fetches search results from mmnt.ru, decodes the response, parses HTML with cheerio, and extracts title, description, URL, cache, and web_archive for each result.
    export async function searchMamont(request: string, page: number = 0): Promise<SearchResult> {
        const ot = page * 10 + 1;
        const response = await fetch(`https://www.mmnt.ru/get?st=${encodeURIComponent(request)}&in=w&ot=${ot}`);
    
        const buffer = await response.arrayBuffer();
        const text = iconv.decode(Buffer.from(buffer), "windows-1251"); // convert win1251 -> utf8
        const $ = cheerio.load(text);
    
        const result: SearchResult = [];
        $(".link_block").each((i, elem) => {
            if (i == 0) return;
    
            const linkElement = $(elem).find("p.link_p a").first();
            const title = linkElement.text().trim();
            const description = $(elem).find("p.desc_p").text().trim();
            const url = $(elem).find("p.link_p a").first().attr("href")!;
            const cache = $(elem).find("p.cache_p a").first().attr("href")?.match(/\/cache\/([a-f0-9]+)\.html/)?.[1];
            const web_archive = $(elem).find("p.arch_p a").first()?.attr("href");
    
            result.push({
                title,
                description,
                url,
                ...(cache ? {cache} : {}),
                ...(web_archive ? {web_archive} : {}),
            });
        });
    
        return result;
    }
  • Zod schema definition for input parameters of the mmnt_search tool: query (string) and page (number). Also defines SearchResult type used by the handler.
    export const SearchParams = {
        query: z.string({description: "query string"}),
        page: z.number({description: "page number"})
    };
  • src/index.ts:15-25 (registration)
    MCP server tool registration for 'mmnt_search', specifying name, description, input schema (SearchParams), and inline handler that calls searchMamont and returns JSON stringified result.
    server.tool(
        "mmnt_search",
        "Search in Mamont search engine",
        SearchParams,
        async ({query, page}) => ({
            content: [{
                type: "text",
                text: JSON.stringify(await searchMamont(query, page))
            }]
        })
    );
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action 'search' without detailing behavioral traits such as whether it's read-only or mutative, authentication requirements, rate limits, error handling, or what the search returns (e.g., results format, pagination). This is inadequate for a tool with no annotation coverage, as it leaves critical operational aspects unspecified.

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 with a single sentence 'Search in Mamont search engine', which is front-loaded and wastes no words. It efficiently conveys the core purpose without unnecessary elaboration, making it easy to parse quickly. Every word earns its place, adhering well to conciseness principles.

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

Completeness2/5

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

Given the tool's complexity (a search operation with 2 parameters), lack of annotations, and no output schema, the description is incomplete. It fails to explain key contextual elements such as what the search returns, how results are structured, any limitations or constraints, or how it relates to the sibling tool. This leaves significant gaps for an agent to understand and use the tool effectively in practice.

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?

The input schema has 100% description coverage, with parameters 'query' and 'page' clearly documented in the schema. The description adds no additional meaning beyond what the schema provides (e.g., it doesn't explain query syntax, page numbering conventions, or default behaviors). According to the rules, with high schema coverage (>80%), the baseline score is 3, as the schema does the heavy lifting and the description doesn't compensate or add value.

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

Purpose3/5

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

The description 'Search in Mamont search engine' states the action (search) and target (Mamont search engine), providing a basic purpose. However, it's vague about what exactly is being searched (e.g., web content, documents, data) and doesn't distinguish from the sibling tool 'mmnt_cache', which might involve caching search results or similar functionality. This leaves ambiguity about the tool's specific scope.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention the sibling tool 'mmnt_cache', so there's no indication of when to choose search over cache operations or other potential tools. It lacks context about use cases, prerequisites, or exclusions, leaving the agent to infer usage based on the tool name alone.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zbkm/mmnt-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server