okun-koneosa
Server Details
Finnish industrial supplies store. Read-only MCP with 4 tools.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.8/5 across 4 of 4 tools scored.
Each tool serves a distinct function: searching products, getting details, building cart links, and searching policies. No overlap in purpose.
All tools follow a consistent verb_noun snake_case pattern (create_cart_link, get_product_details, search_catalog, search_shop_policies_and_faqs).
Four tools cover the essential operations for an industrial supplies shop: search, detail, cart link, and policies. The count is well-scoped without being too few or too many.
The tool set provides a complete workflow: customers can search and browse catalog, get detailed product info, create a cart link, and look up policies. Missing category listing is documented as an external endpoint.
Available Tools
4 toolscreate_cart_linkARead-onlyIdempotentInspect
Build a link that puts the given products into the customer's cart.
This tool writes nothing. It returns a URL; the products are added only when the customer opens that URL in their own browser. Give the URL to the customer and let them click it.
Args: items: 1-20 rows of {"product_id": int >= 1, "quantity": int 1-50}. Unknown fields are rejected. Repeated product_ids are merged into one row and their quantities summed.
Returns: JSON with cart_url, the normalised items, item_count, total_quantity and a short note to show the customer.
Errors (isError=true, body {"error": {...}}): - products_not_found: one or more product_ids do not exist or are not published. The message lists the offending ids. - shop_api_unavailable: the shop could not be reached; retryable.
Notes: - The link SETS the quantities, it does not add to what is already in the cart. Opening the same link twice gives the same result as opening it once, so the customer can safely click it again. - Stock is re-checked when the link is opened. If stock ran out in the meantime, the quantity is reduced or the row skipped — the link can never oversell. - Checkout requires a customer account, so the customer may be asked to log in or register before paying.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | 1-20 products to put in the cart |
Output Schema
| Name | Required | Description |
|---|---|---|
| note | Yes | |
| items | Yes | |
| cart_url | Yes | Open in a browser to fill the cart |
| item_count | Yes | Number of distinct products |
| total_quantity | Yes | Sum of quantities |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint, idempotentHint, openWorldHint) are fully explained: writes nothing, idempotent, stock re-check on open. No contradiction; adds rich behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with Args, Returns, Errors, Notes sections. Every sentence adds value; no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given output schema exists, description still covers return fields, errors, and important behavioral notes. No gaps for a tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers parameters fully (100%). Description adds merging behavior for duplicate product_ids and rejection of unknown fields, which is not in schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool creates a cart link, not actual product addition. Distinguishes from siblings (none are cart-related). Includes specific verb 'build' and resource 'link'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to give URL to customer and let them click. Implicitly says when to use (when preparing a cart for a customer) but no direct comparison to siblings (not needed as siblings are unrelated).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_product_detailsARead-onlyIdempotentInspect
Get full details and current stock for one Okun Koneosa product.
Args: product_id: The numeric product id returned by search_catalog.
Returns: JSON with the full product record: id, name, name_raw, sku, ean, brand, category, full description (not truncated), price_gross, price_net, vat_percent, currency, unit, weight_kg, product_url, image_url, plus a freshly checked in_stock / stock_quantity.
Notes: - Stock is read at call time from a separate availability endpoint, so it is more current than the value returned by search_catalog. - Returns {"error": "product_not_found"} for unknown or unpublished ids. Products that are out of stock are unpublished, so a previously valid id can stop resolving. - To let the user buy, pass product_url, or build a cart link with create_cart_link.
| Name | Required | Description | Default |
|---|---|---|---|
| product_id | Yes | Product ID from search_catalog |
Output Schema
| Name | Required | Description |
|---|---|---|
| id | Yes | Product ID — pass to get_product_details or create_cart_link |
| ean | No | EAN/GTIN barcode, when known |
| sku | No | Ordering number used by the shop |
| name | Yes | Readable product name |
| unit | No | Selling unit, e.g. 'kpl' |
| brand | No | Manufacturer |
| category | No | |
| currency | No | |
| in_stock | Yes | |
| name_raw | No | Supplier's own spelling, often ALL CAPS |
| image_url | No | Null for most products — photography is still being collected |
| price_net | Yes | Price excl. VAT |
| weight_kg | No | |
| disclaimer | Yes | |
| description | No | Full description, not truncated |
| price_gross | Yes | Price incl. Finnish VAT 25.5% |
| product_url | Yes | Public product page |
| vat_percent | No | |
| stock_checked | Yes | True if stock was re-read from the availability endpoint |
| stock_quantity | Yes | Units available right now |
| description_truncated | No | True if description was cut — use get_product_details |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable context: stock is fetched fresh from a separate endpoint, it returns an error for unknown/unpublished ids, and out-of-stock products become unpublished. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections: Args, Returns, Notes. It is concise (every sentence adds value) and front-loaded with the primary purpose. No unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool with 1 param, annotations, and output schema, the description is complete. It covers behavior, error conditions, sourcing of parameters, and relationship to other tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 1 param with description 'Product ID from search_catalog'. The description clarifies it is numeric and from search_catalog, adding meaning beyond the schema. Since schema coverage is 100%, baseline is 3, but the description provides useful sourcing context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get full details and current stock for one Okun Koneosa product.' It uses a specific verb ('get') and resource ('product details'), and distinguishes itself from sibling tools like 'search_catalog' (searching) and 'create_cart_link' (building a cart link).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use this tool (to get more current stock than search_catalog) and provides error handling notes. It also mentions that product_id comes from search_catalog, but does not explicitly state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_catalogARead-onlyIdempotentInspect
Search the Okun Koneosa product catalog.
Okun Koneosa Oy (okunkoneosa.fi) is a Finnish industrial supplies store in Outokumpu, North Karelia. Around 6500 products: bearings, belts, seals, hydraulics, pneumatics, fasteners, hand tools, protective equipment and machine parts. Everything listed is physically in stock. Prices in EUR, including Finnish VAT 25.5%. Free shipping on orders over 150 EUR.
Args: query: Free-text search — matches product name, ordering number (SKU) or EAN code. Leave empty to browse a category. category_id: Restrict to one category. The category list is available at https://okunkoneosa.fi/api/v1/categories (a plain REST endpoint, not an MCP tool). in_stock_only: True by default. The shop only publishes products that are in stock, so this rarely changes the result. sort: "name" (default), "price_asc", "price_desc" or "newest". limit: Products per page, 1-50 (default 10). page: Page number for paging through larger result sets.
Returns: JSON with: - products: list of products, each with id, name, name_raw, sku, ean, brand, category, price_gross (incl. VAT), price_net, currency, unit, in_stock, stock_quantity, weight_kg, product_url, image_url and a shortened description (description_truncated tells if it was cut). - total, page, per_page, total_pages - disclaimer: prices and availability are confirmed at checkout
Notes:
- name is cleaned for reading; name_raw is the supplier's own
spelling, useful for exact matching against a supplier catalogue.
- image_url is null for most products — the shop is still collecting
product photography from suppliers. A missing image does not mean the
product is unavailable.
- Use get_product_details(id) for the full description and a fresh
stock check.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (>= 1) | |
| sort | No | name | |
| limit | No | 1-50 | |
| query | No | Free-text search term | |
| category_id | No | Category ID | |
| in_stock_only | No |
Output Schema
| Name | Required | Description |
|---|---|---|
| page | Yes | |
| total | Yes | Total matches across all pages |
| per_page | Yes | |
| products | No | |
| disclaimer | Yes | |
| total_pages | Yes | |
| suggested_queries | No | Alternative spellings that DO return results — only present when total is 0 |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, idempotentHint), the description adds behavioral details: stock status, pricing including VAT, free shipping conditions, and notes that image_url is often null. It also mentions that prices are confirmed at checkout.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (Args, Returns, Notes) and front-loaded with the purpose. While slightly verbose, it is organized and each sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the 6 parameters and existing output schema, the description is fully comprehensive. It covers the catalog context, parameter details, return structure, and important behavioral notes, leaving no gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides detailed explanations for all 6 parameters, including specific options for sort, valid ranges for limit and page, and the behavior of in_stock_only. This adds significant meaning beyond the input schema, which has 67% coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search the Okun Koneosa product catalog' and provides extensive context about the store and its inventory. It distinguishes itself from sibling tools by explicitly referencing get_product_details for full descriptions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool (e.g., free-text search, browsing by category) and mentions alternatives like get_product_details for full descriptions. However, it does not explicitly say when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_shop_policies_and_faqsARead-onlyIdempotentInspect
Search Okun Koneosa's shop policies and terms.
Covers delivery terms, privacy policy, terms of service, the consumer right of withdrawal / returns, and company information. Use this instead of guessing when the customer asks about delivery times, shipping costs, returns, warranty or how their data is handled.
Args: query: Finnish keyword, e.g. "palautus", "toimitusaika", "takuu", "toimituskulut". Leave empty to list all sections. limit: Maximum sections to return (1-20, default 5).
Returns: JSON with: - sections: each with page, page_title, heading, content and url - total: how many sections matched - query: the term that was searched
Notes:
- Content is split by heading, so you get the relevant paragraph rather
than a whole page. Always cite the url so the customer can read the
full terms.
- These are the shop's own terms. They do not override Finnish consumer
law.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max sections (1-20) | |
| query | No | What to look for, e.g. 'palautus', 'toimitusaika' |
Output Schema
| Name | Required | Description |
|---|---|---|
| query | No | |
| total | Yes | |
| sections | No |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that content is split by heading to return relevant paragraphs, advises to cite url, and notes that shop terms do not override Finnish law. Annotations are consistent and description adds value beyond them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with Args, Returns, and Notes sections. Front-loaded with purpose. Every sentence adds necessary information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 2 simple parameters, an output schema described in Returns, and annotations, the description provides all needed context including behavior, limitations, and guidance. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema covers both parameters with descriptions, and the description adds concrete examples (e.g., 'palautus', 'toimitusaika') and explains behavior when query is empty. Schema coverage is 100% but description enriches usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool searches Okun Koneosa's shop policies and FAQs. Lists specific topics (delivery, privacy, returns, etc.) and distinguishes from sibling tools like search_catalog which handles products.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this instead of guessing when the customer asks about delivery times, shipping costs, returns, warranty or how their data is handled.' Provides concrete usage context and alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!