Pebbler MCP
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Pebbler MCP Compare these two images and tell me the quote before buying"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Pebbler MCP
Let your agent collect human feedback on two images and explain the results. Pebbler runs image preference tests with participants on the Pebbler app.
Your agent retrieves current pricing, package details and availability before creating a test. The purchase uses a live quote and stays within the spending limits you configure. Pricing and package sizes are not fixed by this connector.
Version 1 supports image A/B preference tests. These measure which image people prefer, rather than product conversion or causal effects. Completed response counts are not guaranteed. Surveys and text-only comparisons are not supported.
Connect your agent
Use an MCP app that supports local servers and Node.js 22 or later. Add this configuration to your app:
{
"mcpServers": {
"pebbler": {
"command": "npx",
"args": ["-y", "@pebbler/pebbler-mcp@0.1.0"]
}
}
}Pebbler's production settings are included. You can explore current packages and create drafts without enabling payments.
Related MCP server: GetABrain🧠 | Live Human-in-the-Loop MCP for AI Agents
Enable purchases
Use a dedicated wallet funded with native USDC on Base. Configure these settings locally in your MCP app's environment or secret settings:
Setting | What to provide |
| Set to |
| Your wallet's signing key, supplied privately |
| Your chosen maximum spend per test, as a positive decimal USDC amount |
| Your chosen cumulative spending limit, as a positive decimal USDC amount |
Both spending limits are required when payments are enabled. They are your budget, not the price of a test. If a quote exceeds either limit, the connector stops instead of raising your budget. Payments stay disabled until you enable them explicitly.
The wallet key remains local. Do not put it in a prompt or share it in a conversation. Prices and quotes are fetched by the agent; you do not need to configure them.
Ask for a test
For example:
Check the current package and price, then compare these two image URLs. Tell me the quote before buying and stay within my configured budget.
Provide two publicly accessible HTTPS image URLs and a clear question. Use images you own or have permission to use, and keep the URLs available while responses are collected.
Your agent can show the current offer, create a draft, purchase the test and check progress. You can read partial results while collection continues or return later to ask for the final counts and vote shares. Retrieving results is included in the purchase.
Available tools
Tool | Purpose |
| Retrieve current packages, prices, supported inputs and availability |
| Prepare an image comparison and obtain its quote |
| Refresh a quote before payment has been signed |
| Purchase the quoted test within your wallet's spending limits |
| Check progress and when to check again |
| Retrieve aggregate A/B votes and shares |
| Find your saved tests after returning or restarting |
The agent learns each tool's inputs automatically when connected. It should read the catalog first, use the quote for the purchase, and follow the returned polling interval when checking progress.
Returning to your results
Keep the connector's private local state folder backed up. It retains access to your tests and their purchase history across restarts. You can choose a folder with PEBBLER_STATE_DIR; use the same folder when returning to existing tests.
Your total spending limit counts retained signed purchases, including unresolved attempts, and does not reset automatically. Increase it deliberately if you want to buy more tests. Keep the original state rather than deleting it to reset your budget.
If a purchase is interrupted or pending, ask the agent to retry that same purchase. The connector preserves its identifiers and payment authorization instead of signing another payment. Reading progress and results does not require another purchase.
Try an example
The included examples/run-study.mjs demonstrates discovery and creating an image comparison. It prints the live catalog and quote; purchasing requires the --purchase flag and your locally configured wallet and budgets.
License
MIT. Original example image assets are included under the same license.
Available Tools
7 toolscreate_studyAIdempotent
Validate an immutable preference comparison with two HTTPS image options. Version 1 supports A vs B image tests only. Free. Reuse request_key to recover a failed creation. Returns the study ID and quote; access credentials stay in the local adapter.
Inputs: study (required), request_key (required).
get_catalogARead-only
Read supported image comparison format, price, respondent slots and schemas. Free; use before creating a study.
Inputs: no named parameters.
get_study_resultsARead-only
Retrieve aggregate image preference votes. Free and included in purchase. Responses are from incentivised Pebbler app participants and may be incomplete.
Inputs: study_id (required).
get_study_statusARead-only
Get order state and collection progress. Free; honour poll_after_seconds. For pending settlement or launch, retry purchase_study with its original identifiers.
Inputs: study_id (required).
list_local_studiesARead-only
List study IDs and purchase identifiers retained by this adapter. Free; use to recover work after restarting. Does not expose wallet keys or access credentials.
Inputs: no named parameters.
purchase_studyADestructiveIdempotent
Purchase and schedule the quoted study using the locally configured wallet. Charges USDC, subject to code-enforced budgets. Reuse the original idempotency_key on every retry. Pending payment/launch responses must be recovered through this same tool without another payment.
Inputs: study_id (required), idempotency_key (required).
quote_studyA
Refresh an unpaid study's quote. Free. Do not refresh after signing a payment; recover that purchase instead.
Inputs: study_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool maps to a clearly distinct lifecycle step: catalog discovery, study creation, quote refresh, local recovery, purchase, status polling, and results retrieval. Descriptions explicitly differentiate overlapping terms like quote vs. create and status vs. results.
All tool names follow a predictable snake_case verb_noun pattern (get_catalog, create_study, list_local_studies, purchase_study, etc.). The convention is consistent and readable throughout.
Seven tools appropriately cover the full workflow from format discovery through purchase, status tracking, and results retrieval, plus local recovery. No tool feels redundant or missing for the core scope.
The toolset covers the full study lifecycle: discovery, creation, quoting, purchase, status polling, results, and local recovery. Minor gaps exist for cancellation/refund or explicit study metadata retrieval, though immutability and the payment model may make these out of scope.
Maintenance
Related MCP Connectors
Create, launch, and analyze user research studies, AI interviews, and AI tests from your AI agent.
Paid agent work and paid verification, settled in USDC. Verified outcomes get signed receipts.
Human judgment for AI agents: discover capabilities, get quotes, and track paid human tasks.
Run data annotation and evaluation tasks with vetted domain experts: create, publish, get results.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI agents to recruit real humans for evaluation tasks like surveys, A/B tests, and ratings on text, images, audio, and video, returning aggregated results directly into the conversation.137MIT
- AlicenseAqualityCmaintenanceReal human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.747 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables cost-parity benchmarking of agent loops by starting, extending, and monitoring paired trials, and retrieving receipts with statistical verdicts.38 npmMIT
- AlicenseNot gradedqualityBmaintenanceHosted MCP server (OAuth, no API keys) that makes short drama series (micro-dramas, sitcoms, K-drama style, any language) and other short vertical videos from Claude, ChatGPT or Codex, with the same cast every episode.1Apache 2.0