Diavgis — Greek Public Procurement

Search Greek Procurement Acts

search_tenders

Read-onlyIdempotent

Search Greek public-procurement acts across THREE cross-linked sources — Διαύγεια, ΚΗΜΔΗΣ (Central Electronic Public Procurement Registry) and EU TED. Filter by source (diavgeia|kimdis|ted), lifecycle status (request|tender|award|contract|payment), buyer or supplier ΑΦΜ (9-digit tax id), CPV code, EUR budget range, NUTS region, submission deadline (deadline_after=TODAY + status=tender ⇒ the OPEN tenders a supplier can still bid on), free-text q over the act title, and procurement signals (published facts from ΚΗΜΔΗΣ): direct_award (απευθείας ανάθεση), single_bidder (≤1 bid on the contract), cancelled. Returns a paginated envelope; 'next' is the next PAGE NUMBER or null. Natural-person counterparties are redacted. Summing amount_net across results double-counts, because one procurement appears at several stages; rank_entities and spend_by_cpv count each procurement once.

Input Schema

Name	Required	Description
`q`	No	free-text search over the act title
`cpv`	No	CPV code (e.g. 79710000)
`page`	No	1-based page number; pagination DEPTH is capped per plan
`year`	No	4-digit issue year, e.g. 2026 — restricts to acts issued that year
`region`	No	NUTS region code prefix, e.g. EL30 (Attica), EL52 (Central Macedonia). Matches by prefix, so EL3 covers all of Attica.
`source`	No	filter by data source
`status`	No
`buyer_afm`	No	9-digit buyer ΑΦΜ
`cancelled`	No	only acts the source marked as cancelled
`has_chain`	No	only acts linked into a reconstructed lifecycle chain (request→tender→award→contract→payment)
`page_size`	No	max 200
`budget_max`	No	maximum amount_net in EUR
`budget_min`	No	minimum amount_net in EUR
`price_only`	No	only awards/contracts decided on lowest-price alone (award_criteria = Βάσει τιμής / Χαμηλότερη Τιμή), excluding most-economically-advantageous (MEAT) criteria
`direct_award`	No	only direct awards (procedure = απευθείας ανάθεση) — a published ΚΗΜΔΗΣ fact
`supplier_afm`	No	9-digit supplier ΑΦΜ
`single_bidder`	No	only contracts where ≤1 bid was submitted (maxBidsSubmitted; single bidder)
`deadline_after`	No	ISO date (YYYY-MM-DD). Only acts whose submission deadline is on/after this date. Pass TODAY to get OPEN tenders — the ones a supplier can still bid on. Combine with status="tender".

Output Schema

Name	Required	Description
`data`	Yes
`next`	Yes	next page NUMBER, or null when there are no more pages — not a URL
`page`	Yes
`total`	Yes	total acts matching the filters
`page_size`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 27, 2026

changedOutput schema / properties / data / items / properties / supplier_afm / description

Previous value: -"null when the counterparty is a redacted natural person"New value: +"9-digit ΑΦΜ of a company supplier; a pseudonym \"Φ-XXXXXXXXXX\" for a natural-person contractor; null when the counterparty is a redacted natural person"

Changed2 schema fields changedAug 27, 2026

addedInput schema / properties / deadline_after

Added value: +{
+  "description": "ISO date (YYYY-MM-DD). Only acts whose submission deadline is on/after this date. Pass TODAY to get OPEN tenders — the ones a supplier can still bid on. Combine with status=\"tender\".",
+  "type": "string"
+}

addedInput schema / properties / region

Added value: +{
+  "description": "NUTS region code prefix, e.g. EL30 (Attica), EL52 (Central Macedonia). Matches by prefix, so EL3 covers all of Attica.",
+  "type": "string"
+}

First observedAug 14, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses that results are a paginated envelope where 'next' is a page number or null, that natural-person counterparties are redacted, and that one procurement appears at multiple lifecycle stages causing double-counting. Those are exactly the non-obvious behaviors an agent needs before trusting results.

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?

Front-loaded with the core scope and filter list, then the caveats in the final sentences, with no filler. It is a dense single block with a long parenthetical filter enumeration, which costs a little readability.

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?

For an 18-parameter open search with an output schema, the description covers purpose, filter semantics, pagination return shape, redaction, and the main analytical pitfall. An agent can call it correctly without reading anything else.

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 already 94%, so the baseline is 3; the description earns more by explaining intent-level meaning — lifecycle status values, procurement signals as published ΚΗΜΔΗΣ facts (direct_award = απευθείας ανάθεση, single_bidder = ≤1 bid), and the TODAY/deadline idiom. It does not cover every parameter (e.g. has_chain, price_only, page_size caps) in prose, leaving minor gaps.

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 (search Greek public-procurement acts) and names the three cross-linked sources it spans (Διαύγεια, ΚΗΜΔΗΣ, EU TED). It also distinguishes itself from aggregation siblings by warning that summing amount_net double-counts and naming rank_entities and spend_by_cpv as the correct alternatives.

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?

Gives concrete combinatorial guidance — deadline_after=TODAY with status=tender yields open tenders — and routes aggregate questions to rank_entities/spend_by_cpv. It does not explicitly state when to prefer get_act, get_chain, or find_entity over this tool, so the sibling routing is partial rather than complete.

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

All Diavgis — Greek Public Procurement 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.