Skip to main content
Glama

get-pull-requests

Retrieve pull requests from Azure DevOps repositories with filters for status, creator, and quantity to manage code review workflows.

Instructions

Get pull requests from Azure DevOps repository

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repositoryIdNoRepository ID or name (optional, defaults to all repos)
statusNoPull request status filter (default: active)
createdByNoFilter by creator (user ID or email)
topNoNumber of pull requests to return (default: 25)

Implementation Reference

  • The primary handler function that implements the 'get-pull-requests' tool logic. It constructs the Azure DevOps Git API endpoint with filters for status, creator, repository, and limit, fetches the data using makeApiRequest, processes the pull requests into a formatted response, and returns it in MCP format.
    private async getPullRequests(args: any): Promise<any> {
      try {
        let endpoint = '/git/pullrequests?api-version=7.1';
        
        const params = [];
        
        // Status filter (default to active)
        const status = args.status || 'active';
        if (status !== 'all') {
          params.push(`searchCriteria.status=${status}`);
        }
        
        // Creator filter
        if (args.createdBy) {
          params.push(`searchCriteria.creatorId=${encodeURIComponent(args.createdBy)}`);
        }
        
        // Repository filter
        if (args.repositoryId) {
          params.push(`searchCriteria.repositoryId=${encodeURIComponent(args.repositoryId)}`);
        }
        
        // Top (limit) parameter
        const top = args.top || 25;
        params.push(`$top=${top}`);
        
        if (params.length > 0) {
          endpoint += '&' + params.join('&');
        }
    
        const result = await this.makeApiRequest(endpoint);
    
        const pullRequests = result.value.map((pr: any) => ({
          id: pr.pullRequestId,
          title: pr.title,
          description: pr.description,
          status: pr.status,
          createdBy: {
            displayName: pr.createdBy.displayName,
            uniqueName: pr.createdBy.uniqueName
          },
          creationDate: pr.creationDate,
          repository: {
            id: pr.repository.id,
            name: pr.repository.name
          },
          sourceRefName: pr.sourceRefName,
          targetRefName: pr.targetRefName,
          url: pr._links?.web?.href || `${this.currentConfig!.organizationUrl}/${this.currentConfig!.project}/_git/${pr.repository.name}/pullrequest/${pr.pullRequestId}`,
          isDraft: pr.isDraft || false,
          mergeStatus: pr.mergeStatus
        }));
    
        return {
          content: [{
            type: 'text',
            text: JSON.stringify({
              count: pullRequests.length,
              status: status,
              pullRequests
            }, null, 2),
          }],
        };
      } catch (error) {
        throw new Error(`Failed to get pull requests: ${error instanceof Error ? error.message : 'Unknown error'}`);
      }
    }
  • src/index.ts:261-285 (registration)
    The tool registration in the listTools handler, including the name 'get-pull-requests', description, and input schema definition for MCP tool discovery.
      name: 'get-pull-requests',
      description: 'Get pull requests from Azure DevOps repository',
      inputSchema: {
        type: 'object',
        properties: {
          repositoryId: {
            type: 'string',
            description: 'Repository ID or name (optional, defaults to all repos)',
          },
          status: {
            type: 'string',
            enum: ['active', 'completed', 'abandoned', 'all'],
            description: 'Pull request status filter (default: active)',
          },
          createdBy: {
            type: 'string',
            description: 'Filter by creator (user ID or email)',
          },
          top: {
            type: 'number',
            description: 'Number of pull requests to return (default: 25)',
          },
        },
      },
    },
  • The switch case dispatcher in handleToolCall that routes 'get-pull-requests' calls to the getPullRequests implementation.
    case 'get-pull-requests':
      return await this.getPullRequests(args || {});
  • The input schema definition for the 'get-pull-requests' tool, specifying parameters like repositoryId, status, createdBy, and top.
      inputSchema: {
        type: 'object',
        properties: {
          repositoryId: {
            type: 'string',
            description: 'Repository ID or name (optional, defaults to all repos)',
          },
          status: {
            type: 'string',
            enum: ['active', 'completed', 'abandoned', 'all'],
            description: 'Pull request status filter (default: active)',
          },
          createdBy: {
            type: 'string',
            description: 'Filter by creator (user ID or email)',
          },
          top: {
            type: 'number',
            description: 'Number of pull requests to return (default: 25)',
          },
        },
      },
    },
  • The makeApiRequest helper method used by getPullRequests to make authenticated HTTPS requests to the Azure DevOps REST API.
    private async makeApiRequest(endpoint: string, method: string = 'GET', body?: any): Promise<any> {
      if (!this.currentConfig) {
        throw new Error('No configuration available');
      }
    
      const { organizationUrl, pat, project } = this.currentConfig;
      const baseUrl = `${organizationUrl}/${project}/_apis`;
      const requestUrl = `${baseUrl}${endpoint}`;
      
      return new Promise((resolve, reject) => {
        const urlParts = new url.URL(requestUrl);
        const postData = body ? JSON.stringify(body) : undefined;
        
        const options = {
          hostname: urlParts.hostname,
          port: urlParts.port || 443,
          path: urlParts.pathname + urlParts.search,
          method,
          headers: {
            'Authorization': `Basic ${Buffer.from(`:${pat}`).toString('base64')}`,
            'Content-Type': method === 'PATCH' && endpoint.includes('/wit/workitems/')
              ? 'application/json-patch+json'
              : 'application/json',
            'Accept': 'application/json',
            // For preview APIs, we need to properly handle the API version in the URL, not headers
            ...(postData && { 'Content-Length': Buffer.byteLength(postData) }),
          },
        };
    
        const req = https.request(options, (res) => {
          let data = '';
          
          res.on('data', (chunk) => {
            data += chunk;
          });
          
          res.on('end', () => {
            try {
              if (res.statusCode && res.statusCode >= 200 && res.statusCode < 300) {
                const result = data ? JSON.parse(data) : {};
                resolve(result);
              } else {
                reject(new Error(`HTTP ${res.statusCode}: ${data}`));
              }
            } catch (error) {
              reject(new Error(`Failed to parse response: ${error}`));
            }
          });
        });
    
        req.on('error', (error) => {
          reject(new Error(`Request failed: ${error.message}`));
        });
    
        if (postData) {
          req.write(postData);
        }
        
        req.end();
      });
    }
Behavior2/5

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

With no annotations provided, the description carries full burden but only states the basic operation without behavioral details. It doesn't disclose whether this is a read-only operation, potential rate limits, authentication requirements, pagination behavior, or error handling, which are critical for a data retrieval tool.

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 a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly.

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 complexity of retrieving pull requests (which often involves filtering, pagination, and authentication) and the absence of both annotations and an output schema, the description is insufficient. It lacks details on return format, error cases, or operational constraints, leaving significant gaps for effective tool 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, so parameters like 'repositoryId', 'status', 'createdBy', and 'top' are well-documented there. The description adds no additional parameter semantics beyond implying filtering capabilities, 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.

Purpose4/5

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

The description clearly states the action ('Get') and resource ('pull requests from Azure DevOps repository'), making the purpose immediately understandable. However, it doesn't differentiate this tool from potential siblings like 'get-work-items' or 'get-builds' that might also retrieve Azure DevOps data, missing explicit distinction.

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 prerequisites (e.g., authentication), context for filtering, or comparisons to sibling tools like 'get-work-items' for different data types, leaving usage decisions ambiguous.

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/wangkanai/devops-enhanced-mcp'

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