Skip to main content
Glama
Parado-xy

Seroost Search MCP Server

by Parado-xy

seroost_search

Search indexed codebases using semantic or fuzzy matching to find functions, classes, variables, or code patterns with ranked results including line numbers and file paths.

Instructions

Search through indexed codebase using semantic/fuzzy matching. Returns ranked results with line numbers, file paths, and relevance scores. Ideal for finding functions, classes, variable usage, or code patterns across the entire project including dependencies.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch term or phrase to find in the codebase. Can be function names, variable names, code snippets, or natural language descriptions of functionality.

Implementation Reference

  • src/index.ts:19-52 (registration)
    Registration of the seroost_search MCP tool, including tool name, description, input schema with zod validation for 'query' parameter, and the handler function that executes runSearch and formats the response as MCP content blocks.
    server.tool(
      "seroost_search",
      "Search through indexed codebase using semantic/fuzzy matching. Returns ranked results with line numbers, file paths, and relevance scores. Ideal for finding functions, classes, variable usage, or code patterns across the entire project including dependencies.",
      {
        query: z
          .string()
          .describe(
            "Search term or phrase to find in the codebase. Can be function names, variable names, code snippets, or natural language descriptions of functionality."
          ),
      },
      async ({ query }) => {
        try {
          let content = await runSearch(query);
    
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify(content),
              },
            ],
          };
        } catch (error) {
          return {
            content: [
              {
                type: "text",
                text: "failure",
              },
            ],
          };
        }
      }
    );
  • Core handler function for executing the search: prepares CLI arguments for seroost ('-m code search <query>') and invokes the runSeroost utility.
    export function runSearch(query: string, mode = "code") {
      const args = ["-m", mode, "search", query];
      return runSeroost(args);
    }
  • Helper utility that spawns the external 'seroost' binary with given arguments, captures stdout as the result (expected to be JSON), handles stderr on error, and resolves/rejects the promise accordingly.
    function runSeroost(args: string[]) {
      return new Promise((resolve, reject) => {
        const proc = spawn("seroost", args);
        let out = "";
        let err = "";
    
        proc.stdout.on("data", (d) => (out += d.toString()));
        proc.stderr.on("data", (d) => (err += d.toString()));
    
        proc.on("close", (code) => {
          if (code === 0) {
            try {
              resolve(out);
            } catch {
              reject(new Error("Invalid JSON from Seroost: " + out));
            }
          } else {
            reject(new Error(err || "Seroost failed"));
          }
        });
      });
    }
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the search method ('semantic/fuzzy matching'), scope ('across the entire project including dependencies'), and output format ('ranked results with line numbers, file paths, and relevance scores'). However, it lacks details on potential limitations like rate limits, error handling, or performance implications, which are important for a search tool. The description adds value but does not fully cover all behavioral aspects.

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 appropriately sized and front-loaded, with two sentences that efficiently convey the tool's purpose, behavior, and ideal usage without any wasted words. Every sentence earns its place by adding critical information, such as the search method and output details, making it highly concise and well-structured for quick understanding.

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

Completeness4/5

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 semantic/fuzzy matching), no annotations, and no output schema, the description does a good job of covering key aspects: purpose, usage, and behavioral traits. It explains the search scope and output format, which compensates for the lack of output schema. However, it could be more complete by addressing potential constraints like search limits or error cases, but overall it provides sufficient context for effective use.

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 the 'query' parameter well-documented in the schema itself. The description adds some semantic context by elaborating on what the query can include ('function names, variable names, code snippets, or natural language descriptions of functionality'), but this mostly reinforces the schema's description. Since the schema already does the heavy lifting, the description provides marginal additional value, meeting the baseline for high schema coverage.

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 with specific verbs ('Search through indexed codebase') and resources ('codebase'), distinguishing it from siblings like 'seroost_index' and 'seroost_set_index' by focusing on search rather than indexing operations. It explicitly mentions what it searches ('indexed codebase using semantic/fuzzy matching') and what it returns ('ranked results with line numbers, file paths, and relevance scores'), making the purpose highly specific and well-defined.

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 clear context on when to use this tool ('Ideal for finding functions, classes, variable usage, or code patterns across the entire project including dependencies'), which helps guide usage. However, it does not explicitly state when not to use it or name alternatives among the sibling tools, such as clarifying if 'seroost_index' should be used first for indexing. This omission prevents a perfect score, but the guidance is still strong and actionable.

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/Parado-xy/semantic-search-mcp'

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