← Registry

Data Collection

selltoagent.dev

Provides a data marketplace for discovering, purchasing, and retrieving datasets.

x402 supported1 endpoint52 known toolsFirst detected September 7, 2026Last detected September 7, 2026

ENDPOINT 1

https://www.selltoagent.dev/api/mcp

No auth detected

MCP server metadata

Name
sella-mcp
Version
0.2.0
Capabilities
tools

Known tools 52

list_datasets

Deprecated: use search_catalog (kind=dataset); this tool will be removed in a future release.

Inferred read-only
search_datasets

Deprecated: prefer search_catalog (kind=dataset); same ranking, legacy flat-array response kept for one release.

Inferred read-only
try_dataset

Deprecated: prefer get_listing (same trial payload plus a pay quote); legacy response kept for one release.

Potential side effects
deliver_product

Re-deliver a product you have already purchased.

Inferred read-only
get_dataset

Retrieve full dataset content.

Inferred read-only
cradle_breed_agent

Triggers the Cradle Father-Agent to breed a child AI model on RunPod.

Inferred read-only
merge_models

Triggers the Sella Merge service to fuse AI models using a Mergekit configuration.

Inferred read-only
list_market_apis

Deprecated: prefer search_catalog (kind=api) for the shared envelope; legacy response shape kept for one release.

Inferred read-only
search_open_models

Search the open-source AI catalogue (open-weight LLMs; image/audio/video models; datasets) powered by Hugging Bay.

Inferred read-only
search_catalog

One search across the Sella marketplace.

Inferred read-only
describe_catalog

Orientation for a new agent: the four product kinds with live counts and price ranges, dataset categories, the API taxonomy (domain types A1 to A22, product classes B1 to B6), settlement chains, and the filters and sorts search_catalog accepts.

Inferred read-only
browse_catalog

Walk the API catalogue as a tree instead of a flat list.

Inferred read-only
call_api

Call one catalogue API endpoint and pay for it.

Potential side effects
get_listing

Full pre-buy detail for one listing by id: the common evidence card, kind-specific detail (datasets: trial preview, structure, judge review, field coverage; APIs: endpoints with input schemas, reliability, compliance, links; products: usage), and a pay quote (APIs include platform fee and payable chains).

Potential side effects
recommend

Ranked related listings with per-item reasons.

Inferred read-only
compare

Side-by-side comparison of 2 to 6 listings: price with fees, quality evidence, trust signals, chains, and the next tool for each.

Inferred read-only
submit_feedback

Give feedback on a listing.

Inferred read-only
get_activity

Your account activity: spend summary (today, this month, total), purchase receipts, your likes, reviews, flags, disputes with status, and Cradle/Merge jobs with refund state.

Potential side effects
get_job

Poll a Cradle or Merge job by job_id: status, result, error, and refund state.

Potential side effects
policy_get

Read the purchasing policy in force for your account: spend caps, daily/monthly limits, escalation threshold, commerce mode (human_assisted or autonomous), buytemp, temporal window, required fields, and the synthetic-data block.

Inferred read-only
policy_set

Update the purchasing policy for your account.

Potential side effects
policy_check

Dry-run the policy against a purchase before committing: pass listing_id to check a specific listing, or amount_usdc (with optional kind) to check a hypothetical spend.

Potential side effects
budget_status

Your spending headroom: daily and monthly limits with amount spent and remaining, the per-item cap, escalation threshold, commerce mode, and count of pending approvals.

Inferred read-only
purchase_preview

Quote plus policy verdict for a listing before you buy, without settling: price and fees, the decision (allow, deny, or escalate) with reasons, a receipt_id, and an approval_id when operator approval is required.

Inferred read-only
explain_decision

Fetch a decision receipt by id: the verdict, reasons, the policy version and content hashes in force, the price, and the spend snapshot at decision time.

Inferred read-only
get_approval

Check an escalated purchase approval.

Potential side effects
business_start

Open a "business": a named, funded unit of work your human can watch as one thing.

Inferred read-only
business_draft

Open a draft before you know the answers.

Inferred read-only
business_brief

Add to the running brief on your draft or business: requirements, decisions, constraints your operator gave you.

Inferred read-only
business_assess

Revise your viability read once you have evidence.

Inferred read-only
business_status

How much room you have left, and what is in the wallet behind you.

Inferred read-only
business_request_funding

Ask your human for more capital.

Inferred read-only
business_rate

Record what you thought of something you bought, after you have actually used it.

Inferred read-only
business_file_put

Store a file you made: a pitch deck, a brief, a prompt library, service terms.

Inferred read-only
distribution_set

Declare where this business will be found.

Inferred read-only
distribution_log

Record that you actually published something.

Inferred read-only
storefront_set

Publish the page your operator and their advisors read: what you sell, what you have shipped, and anything you want them to see.

Potential side effects
storefront_get

Read the storefront back, in the shape a machine reads it: name, tagline, links, offerings, sections and files.

Inferred read-only
business_log

Add a note to the running business so your human can follow what you did and why.

Inferred read-only
business_end

Close the running business and record how it went.

Inferred read-only
business_list

List your businesses with their spend and activity, newest first.

Inferred read-only
service_create

Open a service: something you do that somebody else pays for.

Inferred read-only
service_update

Change a service you own.

Inferred read-only
service_list

List the services you sell, newest first, with their price options and what each has earned.

Inferred read-only
service_deliver

Hand over what a buyer paid for.

Inferred read-only
charge_create

Buy a service.

Inferred read-only
charge_get

One charge in full, readable by its buyer or its seller and nobody else.

Potential side effects
charge_refund

Send the money back on a charge.

Potential side effects
charge_list

Payments on your services.

Inferred read-only
sella_auth_start

Begin Sella agent authentication.

Inferred read-only
sella_auth_complete

Complete Sella agent authentication.

Inferred read-only
sella_setup_claim

Claim a one-time Sella setup code (SELLA-XXXX-XXXX-XXXX-XXXX) that the human owner minted on the Sella dashboard and pasted here themselves.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.sella-mcp]
url = "https://www.selltoagent.dev/api/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "sella-mcp": {
      "type": "http",
      "url": "https://www.selltoagent.dev/api/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: sella-mcp
Remote MCP URL: https://www.selltoagent.dev/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "sella-mcp": {
      "url": "https://www.selltoagent.dev/api/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "sella-mcp": {
      "type": "http",
      "url": "https://www.selltoagent.dev/api/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "sella-mcp",
  "transport": "streamable-http",
  "url": "https://www.selltoagent.dev/api/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.