Scoutee

Find CPV codes for your activity

find_cpv_codes

Read-onlyIdempotent

Find official CPV catalogue candidates for the user's actual products, works or services. Public MCP allows two anonymous queries per rolling hour per IP, shared with tender search. Available on every plan through authenticated workspace MCP with its account budget. Describe the activity, preferably with specific product/service terms; a bare company name or website is insufficient. Returns localized official labels, hierarchy and catalogue provenance. Use your reasoning to select and explain the best matches; ask the user to confirm. No company web research or paid Scoutee AI call is triggered. Up to 30 candidates per call. Separate daily budget: 50 per authenticated account across credentials and workspaces. Read quota.remaining and quota.resets_at; do not retry after exhaustion. When an anonymous result has quota.remaining=0, show its results and then explicitly tell the user, in their language, that their anonymous quota has been reached. Show a clickable 'Create a free account' link to https://scoutee.org/en/signup as the next step to continue now. Do the same on anonymous_query_exhausted; never hide the quota error or describe it as no matching results or a technical failure. Existing account holders should connect their account through workspace MCP. Account quotas still apply; do not promise unlimited access. Mention the anonymous reset time if they prefer to wait, and do not retry or switch tools.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`locale`	No	Official label language, such as en, fr or de; unavailable labels fall back to English.	en
`activity`	Yes	The actual products, works or services supplied. Use specific activity terms; never send private company data.

Output Schema

TableJSON Schema

Name	Required	Default
`items`	Yes
`quota`	Yes
`guidance`	No	These are catalogue candidates, not a final classification. Compare their official labels with the user's actual products and services, explain the strongest matches, and ask the user to confirm before applying codes. Do not infer activities from a company name alone. If no candidate fits, ask for a more precise activity or reformulate using catalogue terminology. CPV applies to European procurement markets; do not substitute it for other classifications.
`catalogue`	Yes
`signup_url`	No
`quota_notice`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 22, 2026

addedOutput schema / properties / quota_notice

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Quota Notice"
+}

addedOutput schema / properties / signup_url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Signup Url"
+}

AddedSep 11, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Adds substantial behavioral detail beyond the annotations: anonymous quota of 2 per rolling hour per IP shared with tender search, authenticated daily budget of 50, quota.remaining/resets_at guidance, no retry after exhaustion, no paid call triggered, and explicit error-messaging rules for quota exhaustion. This is exactly the kind of context annotations do not provide.

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?

Long but deliberately front-loaded with the purpose and quota context, followed by input guidance and error-handling instructions. Some redundancy around not retrying and not hiding the quota error, but these repeated points are critical for correct agent behavior.

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

Completeness5/5

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

Covers quota limits and reset times, authentication paths, input requirements, output characteristics (localized labels, hierarchy, provenance, up to 30 candidates), and detailed handling of anonymous quota exhaustion. With an output schema present, no return-structure explanation is needed, and the description leaves no operational gaps.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds meaningful input-quality guidance for the activity parameter (use specific terms, bare company name/website is insufficient) and clarifies the locale behavior via 'localized official labels'. This goes slightly beyond the schema's own descriptions.

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?

States a specific verb and resource: 'Find official CPV catalogue candidates' for the user's products/works/services. It is clearly distinct from sibling tools get_public_tender and search_public_tenders, which concern tenders, not CPV codes.

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

Usage Guidelines4/5

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

Provides concrete input guidance: describe the activity with specific product/service terms, not a bare company name or website, and confirms the tool does not trigger web research or a paid AI call. It does not explicitly name sibling alternatives or conditions for choosing this tool over them, but the purpose alone makes the use case clear.

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

All Scoutee 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.