Skip to main content
Glama

get_proposals

Retrieve your submitted Upwork proposals with status, bid rate, submission date, and client interview status to identify proposals requiring follow-up.

Instructions

Get list of your submitted proposals on Upwork. Shows status, bid rate, submission date, and whether the client is interviewing you. Use this to track which proposals need follow-up.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNoFilter by status. Default: "active"
limitNoMax results. Default: 20

Implementation Reference

  • Main handler function that navigates to Upwork proposals page, scrapes proposal cards from the DOM (title, URL, status, bid rate, client info, interviewing status), and returns filtered results.
    export async function getProposals(input: GetProposalsInput): Promise<ProposalItem[]> {
      const page = await ensureLoggedIn();
    
      try {
        const url =
          input.status === 'archived'
            ? 'https://www.upwork.com/nx/proposals/archived'
            : 'https://www.upwork.com/nx/proposals';
    
        console.error('[getProposals] Navigating to:', url);
        await page.goto(url, { waitUntil: 'domcontentloaded', timeout: 30000 });
        await humanDelay(2000, 4000);
    
        await page.waitForSelector('[data-test="proposal-list"], .proposals-list, article', {
          timeout: 15000,
        }).catch(() => console.error('[getProposals] Selector not found, extracting anyway'));
    
        await humanDelay(1000, 2000);
    
        const proposals = await page.evaluate((limit: number): ProposalItem[] => {
          const cards = document.querySelectorAll(
            '[data-test="proposal-list-item"], .proposal-item, article'
          );
          const results: ProposalItem[] = [];
    
          cards.forEach((card, i) => {
            if (i >= limit) return;
    
            const titleEl = card.querySelector('a[href*="/jobs/"], a[href*="~"]');
            const title = titleEl?.textContent?.trim() ?? '';
            const href = titleEl?.getAttribute('href') ?? '';
            const job_url = href.startsWith('http') ? href : `https://www.upwork.com${href}`;
    
            const idMatch = href.match(/~([a-z0-9]+)/);
            const id = idMatch?.[1] ?? `proposal_${i}`;
    
            results.push({
              id,
              job_title: title,
              job_url,
              status:
                card.querySelector('[data-test="status"], .status-badge')?.textContent?.trim() ?? '',
              bid_rate:
                card.querySelector('[data-test="bid-rate"], .bid-rate')?.textContent?.trim() ?? '',
              submitted_at:
                card.querySelector('time, [data-test="submitted-at"]')?.textContent?.trim() ?? '',
              client_name:
                card.querySelector('[data-test="client-name"]')?.textContent?.trim() ?? '',
              client_location:
                card.querySelector('[data-test="client-location"]')?.textContent?.trim() ?? '',
              interviewing: card.textContent?.toLowerCase().includes('interviewing') ?? false,
            });
          });
    
          return results;
        }, input.limit);
    
        console.error(`[getProposals] Found ${proposals.length} proposals`);
        return proposals.filter((p) => p.job_title);
      } finally {
        await page.close();
      }
    }
  • Zod schema defining input parameters: status (active/archived/all, default 'active') and limit (default 20).
    export const GetProposalsSchema = z.object({
      status: z
        .enum(['active', 'archived', 'all'])
        .optional()
        .default('active')
        .describe('Filter proposals by status'),
      limit: z.coerce.number().optional().default(20).describe('Max proposals to return'),
    });
  • TypeScript interface for ProposalItem output type with id, job_title, job_url, status, bid_rate, submitted_at, client_name, client_location, interviewing fields.
    export interface ProposalItem {
      id: string;
      job_title: string;
      job_url: string;
      status: string;
      bid_rate: string;
      submitted_at: string;
      client_name: string;
      client_location: string;
      interviewing: boolean;
    }
  • src/index.ts:131-146 (registration)
    MCP tool registration in main index.ts with name 'get_proposals', description, and inputSchema (JSON Schema format for MCP protocol).
      {
        name: 'get_proposals',
        description: `Get list of your submitted proposals on Upwork.
    Shows status, bid rate, submission date, and whether the client is interviewing you.
    Use this to track which proposals need follow-up.`,
        inputSchema: {
          type: 'object',
          properties: {
            status: {
              type: 'string',
              enum: ['active', 'archived', 'all'],
              description: 'Filter by status. Default: "active"',
            },
            limit: { type: ['number', 'string'], description: 'Max results. Default: 20' },
          },
        },
  • src/worker.ts:11-11 (registration)
    Worker import and dispatch routing: case 'get_proposals' calls getProposals with GetProposalsSchema.parse(args).
    import { getProposals, GetProposalsSchema } from './tools/get-proposals.js';
Behavior3/5

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

No annotations are provided, so the description must disclose behavior. It indicates a read operation, but lacks details on authentication, rate limiting, or data freshness. For a simple list tool, this is adequate but not comprehensive.

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 two concise sentences that are front-loaded with the core action and key details, with zero wasted words.

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 simplicity of the tool (list operation, two parameters, no output schema), the description adequately covers the returned fields and usage context. Minor missing details like output format do not detract significantly.

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% and parameters are well-defined in the schema. The description adds no additional meaning beyond the schema, making a baseline score of 3 appropriate.

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 it retrieves a list of submitted proposals on Upwork, specifies the fields returned (status, bid rate, submission date, interview indicator), and implicitly distinguishes from siblings like get_job_details, submit_proposal, and search_jobs.

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

Usage Guidelines3/5

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

The description suggests using this tool to track proposals needing follow-up, but does not explicitly state when not to use it or mention alternatives. Usage context is implied but not fully articulated.

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/zcrossoverz/upwork-mcp'

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