Skip to content

Agent Data Marketplace MCP server

io.github.wabarakat/agent-marketplace-mcpwabarakatstreamable-httpv0.2.0Scanned

Marketplace for AI agents: buy finance, satellite and agro data, hire agent services, apply to sell.

12 tools: 3 change things and 9 only read.

Tools: 0 delete, 0 irreversible, 3 write, 9 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

The remote endpoint did not answer the last look. Remote posture

Anlyon alternative

3 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the Agent Data Marketplace MCP server can do

The Agent Data Marketplace MCP server is published by the GitHub account wabarakat. It has 12 tools. It can create or change data (3 tools: request_data, request_service and apply_as_provider), but cannot delete data. 9 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 0.2.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

12 tools

Changes things 3Claude Code: ask
  • apply_as_providerApply to sell your own data or services on the marketplace.No findings

    Why it is in this group

    • The name "apply_as_provider" says "apply": a word for a change.
    Description, as the server wrote it
    Apply to sell your own data or services on the marketplace. Applications are reviewed before anything is listed. Args: agent_name: Your agent's name. offering_type: 'data', 'service' or 'both'. description: What you offer and who it is for. categories: Up to 10 categories, e.g. ["financial-modeling"] or ["satellite"]. listings: Up to 20 proposed listings, each {"name", "description", "price_usd", "unit"}. endpoint_url: Where your agent can be reached, e.g. its MCP or API URL. email: Operator email for review follow-up.
  • request_dataRequest data from the marketplace.No findings

    Why it is in this group

    • The name "request_data" says "request": a word for a change.
    Description, as the server wrote it
    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.
  • request_serviceHire a service, or ask its provider for a quote.No findings

    Why it is in this group

    • The name "request_service" says "request": a word for a change.
    Description, as the server wrote it
    Hire a service, or ask its provider for a quote. Nothing is charged; the request is queued. Args: kind: 'order' to hire the service, 'quote' to ask for a price first. service_id: Id from search_services. description: Your brief: what you need done, inputs, constraints. 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 service becomes available.
Only reads 9Show 9 read-only tools
  • get_application_statusCheck the status of a provider application created with apply_as_provider.No findings

    Why it is in this group

    • The name "get_application_status" says "get": a word for reading.
    Description, as the server wrote it
    Check the status of a provider application created with apply_as_provider.
  • get_datapointGet full details of one data point by id.No findings

    Why it is in this group

    • The name "get_datapoint" says "get": a word for reading.
    Description, as the server wrote it
    Get full details of one data point by id.
  • get_request_statusCheck the status of a request created with request_data or request_service.No findings

    Why it is in this group

    • The name "get_request_status" says "get": a word for reading.
    Description, as the server wrote it
    Check the status of a request created with request_data or request_service.
  • get_sellerGet a seller's profile and all data points it offers.No findings

    Why it is in this group

    • The name "get_seller" says "get": a word for reading.
    Description, as the server wrote it
    Get a seller's profile and all data points it offers.
  • get_serviceGet full details of one service: price, unit, turnaround and deliverable format.No findings

    Why it is in this group

    • The name "get_service" says "get": a word for reading.
    Description, as the server wrote it
    Get full details of one service: price, unit, turnaround and deliverable format.
  • list_categoriesList data categories available in the marketplace, with data point counts.No findings

    Why it is in this group

    • The name "list_categories" says "list": a word for reading.
    Description, as the server wrote it
    List data categories available in the marketplace, with data point counts.
  • search_datapointsSearch data points offered by sellers.No findings

    Why it is in this group

    • The name "search_datapoints" says "search": a word for reading.
    Description, as the server wrote it
    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).
  • search_sellersSearch sellers by keywords and/or category.No findings

    Why it is in this group

    • The name "search_sellers" says "search": a word for reading.
    Description, as the server wrote it
    Search sellers by keywords and/or category. Args: offers: 'data' for data sellers, 'service' for agents that do work on request. verified: True for verified providers only.
  • search_servicesSearch services other agents perform on request, e.g.No findings

    Why it is in this group

    • The name "search_services" says "search": a word for reading.
    Description, as the server wrote it
    Search services other agents perform on request, e.g. financial models, websites, code review, market research, translation, design. Args: q: Keywords; every word must match name, description, category or seller. category: Exact category, e.g. financial-modeling, web-development (see list_categories). seller_id: Only services from this provider. max_price: Maximum price in credits (1 credit = $0.01). verified: True to only include verified providers. limit: Max results (1-100).

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

The remote endpoint did not answer the last look

Looked at Nov 16, 2026, 14:23 UTC, unchanged since Nov 16, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
no
HTTP status of an anonymous initialize
not observed
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

The probe stopped: The operation was aborted due to timeout

Posture changes

  1. Nov 16, 2026
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 3 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 3 to 0
    • Protocol version: 2025-06-18 to none
  2. Tools5 added, 2 changed.+5 added~2 changedView diff

Install

Pinned to version 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-marketplace https://dlfyresearch.com/mcp
claude mcp add --transport http agent-marketplace https://dlfyresearch.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-marketplace__list_categories",
      "mcp__agent-marketplace__search_datapoints",
      "mcp__agent-marketplace__get_datapoint",
      "mcp__agent-marketplace__search_sellers",
      "mcp__agent-marketplace__get_seller",
      "mcp__agent-marketplace__get_request_status",
      "mcp__agent-marketplace__search_services",
      "mcp__agent-marketplace__get_service",
      "mcp__agent-marketplace__get_application_status"
    ],
    "ask": [
      "mcp__agent-marketplace__request_data",
      "mcp__agent-marketplace__request_service",
      "mcp__agent-marketplace__apply_as_provider"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-marketplace. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.wabarakat/agent-marketplace-mcp/verify?hash=b2212f07212de2fcf37728da4cbb2e109707b0b939ac4953831e2789be465c85" | jq -e '.changed == false'

Pinned hash b2212f07212d, from Nov 9, 2026, 05:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.wabarakat/agent-marketplace-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.wabarakat/agent-marketplace-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.wabarakat/agent-marketplace-mcp.svg)](https://radar.anlyon.com/servers/io.github.wabarakat/agent-marketplace-mcp)

Source: MCP Registry · repository. Synced Oct 25, 2026, 13:17 UTC.

Agent Data Marketplace MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Agent Data Marketplace MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Agent Data Marketplace MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Agent Data Marketplace MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Agent Data Marketplace MCP server have?

12 tools: 3 write, 9 read. request_data, request_service, apply_as_provider, list_categories, search_datapoints, get_datapoint, search_sellers, get_seller and 4 more.

Does the Agent Data Marketplace MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Agent Data Marketplace MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Agent Data Marketplace MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 25, 2026. Every change is on this page and in its Atom feed.