Skip to main content
Glama

🎯 gibwork-hunter-mcp

Autonomous AI Agent Bounty Hunting Toolset & Model Context Protocol (MCP) Server for Gibwork on Solana.

TypeScript License: MIT MCP Solana Vitest

Built for the Gibwork Developer Hackathon ($1,000 USDC), gibwork-hunter-mcp is a specialized, production-ready non-web-app developer tool that connects autonomous LLM coding assistants (Claude Desktop, Cursor, Antigravity, Gemini) directly to Gibwork on Solana.


⚑ Overview

Coding AI agents typically operate in isolation from real-world economic incentives. Gibwork Hunter MCP bridges this gap:

  1. Discovery: Agents query active, funded bounties locked in Solana escrows, filtered by ROI, skills, and reward thresholds.

  2. Deterministic Verification: Before submitting, agents evaluate their local workspace against the bounty's exact requirements checklist (file patterns, strict typechecks, test suite execution, and SHA-256 fingerprinting).

  3. Cryptographic Proof Submission: Agents prepare, sign (Ed25519), and register verifiable deliverable proofs directly to Gibwork and Solana.


Related MCP server: Escrow Sentinel

πŸ›οΈ Architecture & Workflow

 β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
 β”‚       LLM Coding Assistants / Autonomous AI Agents          β”‚
 β”‚       (Claude Desktop, Cursor, Antigravity, Gemini)         β”‚
 β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                β”‚ Stdio JSON-RPC (MCP)
                                β–Ό
 β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
 β”‚                    gibwork-hunter-mcp                       β”‚
 β”‚                                                             β”‚
 β”‚   β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”     β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”   β”‚
 β”‚   β”‚  Bounty Query Engine  β”‚     β”‚ Deterministic Verifierβ”‚   β”‚
 β”‚   β”‚  - ROI Scoring        β”‚     β”‚ - File existence      β”‚   β”‚
 β”‚   β”‚  - Escrow Inspection  β”‚     β”‚ - Pattern matching    β”‚   β”‚
 β”‚   β”‚  - Skill Filtering    β”‚     β”‚ - Test suite runner   β”‚   β”‚
 β”‚   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜     β”‚ - SHA256 Fingerprint  β”‚   β”‚
 β”‚              β”‚                  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜   β”‚
 β”‚              β”‚                              β”‚               β”‚
 β”‚              β–Ό                              β–Ό               β”‚
 β”‚   β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”   β”‚
 β”‚   β”‚            Ed25519 Cryptographic Signer             β”‚   β”‚
 β”‚   β”‚         - Solana Keypair / TweetNaCl detached       β”‚   β”‚
 β”‚   β”‚         - Verifiable Payload Attestation            β”‚   β”‚
 β”‚   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜   β”‚
 β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                β”‚ Live SDK / Staging API
                                β–Ό
 β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
 β”‚                     Gibwork on Solana                       β”‚
 β”‚   - Escrow Smart Contract (USDC / SPL)                      β”‚
 β”‚   - Task Registry & Submission Settlement                   β”‚
 β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

πŸ› οΈ MCP Tools Exposed

When added to your LLM assistant (e.g. Claude Desktop or Cursor), the following 4 tools become available:

Tool Name

Parameters

Description

gibwork_list_bounties

min_reward, skill, status, keyword, sort_by, limit

Lists open bounties sorted by prize/ROI with summary table

gibwork_get_bounty

id

Fetches full specification, requirements checklist, escrow address, and sponsor reputation

gibwork_verify_deliverable

bounty_id, workspace_path, run_tests

Deterministically validates local workspace code against requirements checklist

gibwork_submit_proof

bounty_id, submission_url, workspace_path, notes, dry_run

Prepares, cryptographically signs with Ed25519 Solana keypair, and submits proof


πŸ’» CLI Commands (gibwork-cli)

gibwork-hunter-mcp doubles as an interactive developer terminal utility:

1. Hunt Bounties

# List top bounties sorted by ROI
npx gibwork-cli hunt

# Filter by reward and skill
npx gibwork-cli hunt --min-reward 500 --skill TypeScript --sort reward

2. Inspect Bounty Details

npx gibwork-cli inspect gibwork-hackathon-2026

3. Verify Local Deliverables

# Deterministically evaluate current directory against requirements
npx gibwork-cli verify gibwork-hackathon-2026 .

# Run with automated test validation
npx gibwork-cli verify gibwork-hackathon-2026 . --run-tests

4. Cryptographically Sign & Submit Proof

# Generate signed proof receipt (simulated / dry-run)
npx gibwork-cli submit gibwork-hackathon-2026 \
  --url https://github.com/rishiiicreates/gibwork-hunter-mcp \
  --dir . \
  --notes "Production-grade TypeScript MCP Server and CLI"

βš™οΈ Configuration & Installation

Option A: Use directly via npx

npx gibwork-hunter-mcp

Option B: Clone & Build Locally

git clone https://github.com/rishiiicreates/gibwork-hunter-mcp.git
cd gibwork-hunter-mcp
npm install
npm run build
npm test

Setup in Claude Desktop (claude_desktop_config.json)

Add this entry to your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "gibwork-hunter": {
      "command": "node",
      "args": [
        "/Users/rishii/gibwork-hunter-mcp/dist/index.js"
      ],
      "env": {
        "SOLANA_PRIVATE_KEY": "",
        "GIBWORK_LIVE": "false"
      }
    }
  }
}

Note: If SOLANA_PRIVATE_KEY is not provided, the server automatically operates in safe mock/simulation mode with ephemeral session keypairs, allowing instant inspection and verification without touching real mainnet funds.


πŸ”’ Solana Escrow & Cryptographic Attestation

Each deliverable proof generated by gibwork-hunter-mcp contains:

  • Deliverable Fingerprint: SHA-256 hash of all non-ignored project files (deterministic manifest hash).

  • Idempotency Key: UUIDv4 ensuring replay protection against network instability.

  • Ed25519 Detached Signature: Signed by the hunter's Solana keypair over the canonical JSON payload.

  • Escrow Verification: Validates target smart contract escrow address on Solana mainnet.

{
  "proofId": "proof-a92c817f",
  "bountyId": "gibwork-hackathon-2026",
  "hunterAddress": "7b5vF9...vXqN",
  "submissionUrl": "https://github.com/rishiiicreates/gibwork-hunter-mcp",
  "deliverableFingerprint": "63e0b2c2e13b916094170254765f3743...",
  "verificationScore": 100,
  "status": "MOCK_CONFIRMED",
  "signature": "3K6xU9...ed25519...base58",
  "messageDigest": "8f81ad562a...",
  "signedAt": "2026-10-25T16:50:00.000Z"
}

πŸ§ͺ Testing

The test suite runs with Vitest in strict mode:

npm test

All 28 tests across 6 test suites verify:

  • Solana Ed25519 signature creation & verification

  • Deterministic workspace hasher & ignore logic

  • Bounty query filtering & dynamic ROI scoring

  • Verifier engine requirements evaluation (file existence, regex, exit codes)

  • Submitter service & MCP tool endpoints


πŸ“„ License

MIT Β© Rishii (Hrishikesh Yadav)

Available Tools

4 tools
gibwork_get_bountyB

Fetch full bounty metadata, escrow details, sponsor reputation, deadline, and requirements checklist.

Inputs: id (required).

gibwork_list_bountiesC

List live and ecosystem Gibwork bounties on Solana with query filters (min_reward, skill, status, keyword, sort_by).

Inputs: limit, skill, status, keyword, +2 more.

gibwork_submit_proofB

Prepares, cryptographically signs with a Solana Ed25519 keypair, and registers a bounty submission proof packet on Gibwork.

Inputs: bounty_id (required), submission_url (required), notes, dry_run, +1 more.

gibwork_verify_deliverableC

Deterministically analyzes a local workspace against a Gibwork bounty requirements checklist, scoring compliance from 0-100% and generating a cryptographic deliverable fingerprint.

Inputs: bounty_id (required), run_tests, workspace_path.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool maps to a distinct stage of a bounty workflow: browse (list_bounties), inspect (get_bounty), evaluate local work (verify_deliverable), and sign/register (submit_proof). There is no plausible confusion between listing many bounties versus fetching one, or between local verification and on-chain submission.

    Naming Consistency5/5

    All four names use a uniform `gibwork_` namespace prefix followed by a verb_noun pattern in snake_case (list_bounties, get_bounty, verify_deliverable, submit_proof). The convention is fully predictable and readable.

    Tool Count4/5

    Four tools is on the lean side but each earns its place within a narrow bounty-hunting scope, and there is no filler. It sits just below the ideal mid-range, leaving little room for auxiliary operations.

    Completeness4/5

    The core discovery-to-submission lifecycle is fully covered, including a verification step most servers would omit. Minor gaps remain: no way to check submission status or withdraw/resubmit a proof, and no agent-side profile or submission history lookup.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to discover Gibwork bounties, verify their Solana escrow accounts on-chain, rank opportunities by value, competition and deadline, diff captures over time, and export Markdown/CSV/JSON reports through four read-only MCP tools requiring no wallet or API key.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP-compatible AI clients and coding agents to turn vague GitHub requests into structured, testable task contracts, inspect repository evidence, simulate execution, validate readiness, and preview or publish Gibwork bounties only after explicit confirmation.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables developers and AI agents to discover, rank, watch, and draft submissions for Gibwork coding bounties through MCP tools, with optional wallet-authenticated SDK support.
      1
      MIT