gibwork-mcp-proof-bridge
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
gibwork-mcp-proof-bridge
MCP addon that brings verifiable proof-of-work to Gibwork agents.
Exposes structured proof bundles, verification policies, and high-trust submissions as first-class agent capabilities.
Pairs with:
Official
@gibwork/mcp
Quick Start
git clone https://github.com/mrphatom/gibwork-mcp-proof-bridge.git
cd gibwork-mcp-proof-bridge
npm install && npm run build
npx tsx src/cli.ts doctor
npx tsx src/cli.ts doctor --json
npx tsx src/cli.ts tools
npx tsx src/cli.ts skill
# Proxy to a local proof-runner
npx tsx src/cli.ts exec -- run --task <id> --dry-runRelated MCP server: Proofpane
Commands
Command | Purpose |
| Locate proof-runner ( |
| Emit MCP tool descriptors (JSON) |
| Emit Claude Code / Codex skill fragment |
| Proxy args to a local gibwork-proof-runner |
Recommended MCP tools
proof_run— execute verification policyproof_inspect— inspect proof bundleproof_submit— submit successful proofpolicy_list— list policies
Integration
Agent → official MCP + proof-bridge → proof-runner → structured proof → Gibwork
Optional: gateway in front for policy + budgets + auditAdditive only — no hard renovation of existing Gibwork MCP required.
License
MIT
This server cannot be deployed
Related MCP Connectors
Public MCP for agent verification, work discovery and governed interoperability.
Governed MCP: agent audit, provenance, deterministic checks, and receipt-backed FragGate execution.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables delegation of work to AI agents with cryptographic verification and token-based settlement via 41 MCP tools.8MIT
- AlicenseBqualityAmaintenanceA governance proxy for AI tools — every MCP/agent tool call is policy-gated, secret-redacted, and written to a hash-chained, offline-verifiable audit trail.13MIT
- FlicenseCqualityAmaintenanceDeterministic <1µs in-band execution governance gateway and W3C DID security guardrail for AI Agent MCP tool calls.116-
- AlicenseNot gradedqualityBmaintenanceEnables 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