mcp-server

create_feed

Create a Koongo product feed for a project. Use this when the user asks for a new product feed. feed_code must be one returned by list_feed_templates. Returns {feedId, feedCode, status, customerId, editUrl, categoryMappingNeeded}. project_id is OPTIONAL: omit it when the customer has a single project (it is inferred); if they have several you get project_id_required — call list_projects and pass one. If categoryMappingNeeded is true, map its categories with list_unmapped_categories + search_target_categories + set_category_mapping (pass the returned feedId as feed_id). The core next step is to MAP output attributes: call get_feed + list_source_attributes, then map_feed_attribute per attribute (category mapping only covers categories, not attributes). Requires the project's data imported (dataStatus='ok', see get_import_status). If this Koongo account cannot hold another feed, the call is refused with error 'quota_reached' (HTTP 403); tell the user it is not available for this account and do not retry.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "feed_code": "<feed_code>"
    },
    "name": "create_feed"
  }
}

Input Schema

Name	Required	Description	Default
`feed_code`	Yes
`project_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 1, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses the JSON return shape, a prerequisite (dataStatus='ok' via get_import_status), the project inference behavior and its error mode, and the exact quota_refused/'quota_reached' HTTP 403 behavior with a no-retry instruction. These are material behaviors an agent cannot infer from the supplied annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and usage, then moves to return values, parameter constraints, and error handling in a logical order. It is longer than typical but each sentence carries operational information; the attribute-mapping guidance is dense but earns its place as next-step steering.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly explains the return object, and it covers prerequisites, project inference, category and attribute mapping follow-ups, and quota failure. It is nearly complete; minor gaps like whether feed creation is reversible or what status values mean are not addressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the burden, and it does: feed_code is tied to list_feed_templates, and project_id is explained as optional with inference semantics and the exact error surfaced when ambiguous. This adds substantial meaning beyond the bare integer/string schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a specific verb and resource ('Create a Koongo product feed for a project'), and the second sentence gives the user-facing trigger ('when the user asks for a new product feed'). It is clearly distinct from siblings like create_ad, create_marketplace, and update_feed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says when to use it, constrains feed_code to values from list_feed_templates, explains the optional project_id with the project_id_required fallback to list_projects, and prescribes follow-up tools for category and attribute mapping. The quota error instruction ('do not retry') is also explicit when-not-to-retry guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?