Skip to main content
Glama
garc33

Bitbucket Server MCP

by garc33

search

Search for code patterns or files across Bitbucket Server repositories. Find specific content by querying file names and contents, with filtering by project or repository.

Instructions

Search for code or files across repositories. Use this to find specific code patterns, file names, or content within projects and repositories. Searches both file contents and filenames. Supports filtering by project, repository, and query optimization.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query string to look for in code or file names.
projectNoBitbucket project key to limit search scope. If omitted, searches across accessible projects.
repositoryNoRepository slug to limit search to a specific repository within the project.
typeNoQuery optimization: "file" wraps query in quotes for exact filename matching, "code" uses default search behavior. Both search file contents and filenames.
limitNoNumber of results to return (default: 25, max: 100)
startNoStart index for pagination (default: 0)

Implementation Reference

  • The primary handler function that implements the 'search' tool. It constructs the search query based on options, calls the Bitbucket search API, processes the results, and returns formatted output.
    private async search(options: SearchOptions) {
      const { query, project, repository, type, limit = 25, start = 0 } = options;
      
      if (!query) {
        throw new McpError(
          ErrorCode.InvalidParams,
          'Query parameter is required'
        );
      }
    
      // Build the search query with filters
      let searchQuery = query;
      
      // Add project filter if specified
      if (project) {
        searchQuery = `${searchQuery} project:${project}`;
      }
      
      // Add repository filter if specified (requires project)
      if (repository && project) {
        searchQuery = `${searchQuery} repo:${project}/${repository}`;
      }
      
      // Add file extension filter if type is specified
      if (type === 'file') {
        // For file searches, wrap query in quotes for exact filename matching
        if (!query.includes('ext:') && !query.startsWith('"')) {
          searchQuery = `"${query}"`;
          if (project) searchQuery += ` project:${project}`;
          if (repository && project) searchQuery += ` repo:${project}/${repository}`;
        }
      } else if (type === 'code' && !query.includes('ext:')) {
        // For code searches, add common extension filters if not specified
        // This can be enhanced based on user needs
      }
    
      const requestBody = {
        query: searchQuery,
        entities: {
          code: {
            start,
            limit: Math.min(limit, 100)
          }
        }
      };
    
      try {
        // Use full URL for search API since it uses different base path
        const searchUrl = `${this.config.baseUrl}/rest/search/latest/search`;
        const response = await axios.post(searchUrl, requestBody, {
          headers: this.config.token
            ? { 
                Authorization: `Bearer ${this.config.token}`,
                'Content-Type': 'application/json'
              }
            : { 'Content-Type': 'application/json' },
          auth: this.config.username && this.config.password
            ? { username: this.config.username, password: this.config.password }
            : undefined,
        });
        
        const codeResults = response.data.code || {};
        const searchResults = {
          query: searchQuery,
          originalQuery: query,
          project: project || 'global',
          repository: repository || 'all',
          type: type || 'code',
          scope: response.data.scope || {},
          total: codeResults.count || 0,
          showing: codeResults.values?.length || 0,
          isLastPage: codeResults.isLastPage || true,
          nextStart: codeResults.nextStart || null,
          results: codeResults.values?.map((result: any) => ({
            repository: result.repository,
            file: result.file,
            hitCount: result.hitCount || 0,
            pathMatches: result.pathMatches || [],
            hitContexts: result.hitContexts || []
          })) || []
        };
    
        return {
          content: [{ type: 'text', text: JSON.stringify(searchResults, null, 2) }]
        };
      } catch (error) {
        if (axios.isAxiosError(error)) {
          if (error.response?.status === 404) {
            throw new McpError(
              ErrorCode.InternalError,
              'Search API endpoint not available on this Bitbucket instance'
            );
          }
          // Handle specific search API errors
          const errorData = error.response?.data;
          if (errorData?.errors && errorData.errors.length > 0) {
            const firstError = errorData.errors[0];
            throw new McpError(
              ErrorCode.InvalidParams,
              `Search error: ${firstError.message || 'Invalid search query'}`
            );
          }
        }
        throw error;
      }
    }
  • The input schema definition for the 'search' tool, specifying parameters like query, project, repository, type, limit, and start.
    inputSchema: {
      type: 'object',
      properties: {
        query: { type: 'string', description: 'Search query string to look for in code or file names.' },
        project: { type: 'string', description: 'Bitbucket project key to limit search scope. If omitted, searches across accessible projects.' },
        repository: { type: 'string', description: 'Repository slug to limit search to a specific repository within the project.' },
        type: { 
          type: 'string', 
          enum: ['code', 'file'],
          description: 'Query optimization: "file" wraps query in quotes for exact filename matching, "code" uses default search behavior. Both search file contents and filenames.'
        },
        limit: { type: 'number', description: 'Number of results to return (default: 25, max: 100)' },
        start: { type: 'number', description: 'Start index for pagination (default: 0)' }
      },
      required: ['query']
    }
  • src/index.ts:344-362 (registration)
    The registration of the 'search' tool in the MCP tools list, including name, description, and input schema.
      name: 'search',
      description: 'Search for code or files across repositories. Use this to find specific code patterns, file names, or content within projects and repositories. Searches both file contents and filenames. Supports filtering by project, repository, and query optimization.',
      inputSchema: {
        type: 'object',
        properties: {
          query: { type: 'string', description: 'Search query string to look for in code or file names.' },
          project: { type: 'string', description: 'Bitbucket project key to limit search scope. If omitted, searches across accessible projects.' },
          repository: { type: 'string', description: 'Repository slug to limit search to a specific repository within the project.' },
          type: { 
            type: 'string', 
            enum: ['code', 'file'],
            description: 'Query optimization: "file" wraps query in quotes for exact filename matching, "code" uses default search behavior. Both search file contents and filenames.'
          },
          limit: { type: 'number', description: 'Number of results to return (default: 25, max: 100)' },
          start: { type: 'number', description: 'Start index for pagination (default: 0)' }
        },
        required: ['query']
      }
    },
  • src/index.ts:547-556 (registration)
    The dispatch/registration case in the CallToolRequestSchema handler that routes 'search' calls to the search method.
    case 'search': {
      return await this.search({
        query: args.query as string,
        project: args.project as string,
        repository: args.repository as string,
        type: args.type as 'code' | 'file',
        limit: args.limit as number,
        start: args.start as number
      });
    }
  • TypeScript interface defining the options for the search function.
    interface SearchOptions extends ListOptions {
      project?: string;
      repository?: string;
      query: string;
      type?: 'code' | 'file';
    }
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 describes what the tool does (searching code/files across repositories) and mentions filtering capabilities, but doesn't address important behavioral aspects like authentication requirements, rate limits, error conditions, or what the response format looks like. The description provides basic operational context but misses key behavioral details.

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

Conciseness4/5

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

The description is appropriately sized with three sentences that each add value. It's front-loaded with the core purpose, followed by usage context and capabilities. While efficient, the third sentence could be slightly more structured by separating the filtering and optimization aspects more clearly.

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

Completeness3/5

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

For a search tool with 6 parameters, no annotations, and no output schema, the description provides adequate context about what the tool does but lacks important completeness elements. It doesn't describe the return format, result structure, pagination behavior, or error handling. The description covers the 'what' but misses the 'what comes back' and operational constraints.

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 description coverage is 100%, so the schema already documents all 6 parameters thoroughly. The description mentions 'filtering by project, repository, and query optimization' which aligns with parameters but doesn't add significant meaning beyond what the schema provides. The baseline of 3 is appropriate when the schema does the heavy lifting.

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 for code or files') and resources ('across repositories'), distinguishing it from sibling tools like browse_repository or get_file_content. It explicitly mentions searching both file contents and filenames, providing a comprehensive scope.

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 for when to use this tool ('to find specific code patterns, file names, or content within projects and repositories'), but doesn't explicitly mention when not to use it or name specific alternatives among the sibling tools. It implies usage for search tasks but lacks explicit exclusions.

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/garc33/bitbucket-server-mcp-server'

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