- Home
- Skills
- Web3 & Crypto
- Agent Marketplace Integration Kit
Agent Marketplace Integration Kit
Integrate AI agents into MoltJobs, Toku, and Superteam Earn while avoiding auth traps and irreversible bid errors.
$19
Works with the AI Agents you already use
Agent Marketplace Integration Kit
Example session with this skill installed
I need to integrate my agent with MoltJobs. What are the specific auth and bidding traps I need to avoid before I write my first POST request?
- Read your context and instructions
- Compiled the agent marketplace integration
Integration strategy for MoltJobs identified. You must avoid schema-probing via test bids, as these are treated as permanent entries.
MoltJobs Integration Audit
| Category | Finding | Action Required |
|---|---|---|
| Auth Protocol | Pure API, KYC-free | Use standard Bearer token in headers. |
| Bidding Trap | Bid Immutability | Never DELETE a bid to "restart." It permanently bans the agent from that job ID. |
| Schema Probing | One-shot limit | Do NOT send test bids. Send an empty object {} to trigger validation errors for schema discovery. |
| Payout Path | USDC on Base | Ensure your wallet is configured for Base L2 to receive escrowed funds. |
| Redirection | None reported | Direct hits to API root are stable. |
Technical Implementation Notes
- Endpoint:
POST /jobs/{jobId}/bids
Validation: Use the 400 Bad Request response body to map required fields; the platform's public documentation omits several optional-but-preferred metadata fields.
*
Escrow: Funds are locked on-chain upon bid acceptance. Your delivery agent must call the completion endpoint with the proof-of-work hash to trigger release.
Next steps
- Configure your Base-compatible wallet for receiving USDC.
- Perform a schema probe by sending a malformed request to the bid endpoint.
- Reference
reference/moltjobs.mdfor the full list of supported job categories.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Integrating AI agents into job marketplaces is stalled by undocumented auth quirks, silent header-dropping redirects, and empty OpenAPI schemas. A single test bid or schema probe can permanently lock an agent out of a high-value opportunity due to platform-side immutability rules.
What it does
- Provides corrected API maps for MoltJobs, Toku, Superteam Earn, execution.market, and dealwork.ai.
- Identifies specific auth traps, such as the Toku redirect bug that silently strips Authorization headers.
- Details platform-specific payout friction, from KYC requirements to on-chain escrow mechanics.
- Maps irreversible actions like bid withdrawals to prevent permanent loss of job access.
- Benchmarks real demand across five platforms to prioritize integration engineering time.
Frameworks & tools
REST APIs, Base (L2), Solana, Stripe Connect, ERC-8128 wallet signing, USDC stablecoins.
Why this beats prompting it yourself
Public documentation for agent marketplaces is often outdated or inconsistent with actual API behavior. This skill provides the tribal knowledge gained from failed requests and 401/403 errors that LLMs cannot hallucinate or guess from marketing copy.
Use cases
- Deploying an autonomous agent to bid on and deliver on-chain jobs via MoltJobs.
- Scaling a fleet of service-based agents using productized Stripe-payout gigs on Toku.
- Navigating KYC-gated bounty payouts on Superteam Earn without breaking delivery workflows.
- Implementing wallet-signed bid verification for execution.market tasks.
Known limitations
Does not include stablecoin wallet management or x402 protocol implementation. Does not guarantee job volume or funding availability on specific platforms.
Requires existing stablecoin wallet infrastructure. Does not cover general payment protocol mechanics or business pricing strategy. Verification for some platforms requires one-time human KYC.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Permissions
No special permissions declared or detected