agent-marketplace-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENT_MARKETPLACE_URL | No | The base URL for the Agent Data Marketplace server. | https://dlfyresearch.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_categoriesA | List data categories available in the marketplace, with data point counts. |
| search_datapointsA | Search data points offered by sellers. Args: q: Keywords; every word must match name, description, category or seller. category: Exact category, e.g. finance, satellite, agriculture (see list_categories). seller_id: Only data points from this seller. max_price: Maximum price in credits (1 credit = $0.01). verified: True to only include verified data providers. limit: Max results (1-100). |
| get_datapointB | Get full details of one data point by id. |
| search_sellersC | Search data sellers by keywords and/or category. verified=True for verified providers only. |
| get_sellerC | Get a seller's profile and all data points it offers. |
| request_dataA | Request data from the marketplace. Nothing is charged; the request is queued. Args: kind: 'purchase' or 'sample' a listed data point (needs datapoint_id), or 'unlisted' to describe data not in the catalog (needs description). datapoint_id: Id from search_datapoints. description: What you need and what it is for. format: Preferred format, e.g. json, csv, parquet. frequency: e.g. once, hourly, daily. max_price_credits: Most you would pay, in credits (1 credit = $0.01). agent_name: A stable name for your agent, so repeat requests are grouped. email: Your operator's email, to be notified when the data becomes available. |
| get_request_statusB | Check the status of a request created with request_data. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a distinct resource and action: listing categories, searching data points, searching sellers, fetching individual details, requesting data, and checking request status. The search vs. get pairs are clearly differentiated by keyword-based discovery versus id-based retrieval, and the two search tools operate on different entity types.
All tools use a consistent snake_case verb_noun convention (list_categories, get_seller, search_datapoints, get_datapoint, search_sellers, request_data, get_request_status). The only slight variation is the three-part get_request_status, which remains predictable and readable.
Seven tools is well-scoped for a data marketplace: category listing, seller discovery, data point discovery, detail views, and the request/status lifecycle. Each tool has a clear role and no redundant tools appear present.
The consumer-side marketplace workflow is well covered from browsing categories and sellers through requesting data and checking status. Minor gaps remain around managing existing requests, such as listing all requests or cancelling a queued request, but agents can work around these.