eu-parliament-mcp-server

List parliamentary questions

euparl_list_questions

Read-onlyIdempotent

List parliamentary questions by year and work_type or retrieve metadata, source-file links and published answers with mode get and question_id. Human citations such as E-000001/2025 retain their full year; omission of term checks canonical candidates for every overlapping parliamentary term and requires one verified match. Supply term to disambiguate; canonical IDs resolve directly. Use euparl_list_reference topic question_types for work_type codes. No keyword, author or addressee search is available. Empty answers means no answer relation was published in this response. Get rejects list filters and nondefault paging; continue lists with page.next_offset.

Input Schema

Name	Required	Description	Default
`mode`	No	Default list discovers questions; get requires question_id and forbids year and work_type.	list
`term`	No	Get-only term 0–10 to disambiguate a human citation; must agree with a canonical ID. Omit to verify candidates for every term overlapping the citation year.
`year`	No	List-only four-digit question year.
`limit`	No	Whole items requested; default 20, effective maximum 100 with notice.
`offset`	No	Zero-based collection offset; default 0.
`language`	No	Supported EU ISO-639-1 language, case-insensitive; default en; source text is never translated.
`work_type`	No	List-only question code from euparl_list_reference topic question_types; case-insensitive and whitespace-trimmed.
`question_id`	No	Get-only canonical E-{term}-{year}-{six-digit-sequence}, known document prefix/public URI, or human E-NNNNNN/YYYY citation; corresponding P/O prefixes are accepted.

Output Schema

Name	Required	Description
`cap`	No	Effective whole-item page limit.
`mode`	No	Executed question retrieval mode.
`page`	No	List continuation metadata; absent in get mode.
`error`	No	Present when the call failed. Absent on success.
`found`	No	Get-only result; false only after complete citation resolution or missing published detail.
`items`	No	Whole sparse records on a list page; absent in get mode.
`shown`	No	Whole items shown on this partial page.
`notice`	No	Publication, language fallback, empty-result or continuation guidance.
`question`	No	Question detail present only when a published record is found.
`available`	No	Whether the selected source array was published, including a published empty array.
`truncated`	No	True when this page returns only part of the selected collection.
`totalCount`	No	Exact count only when published or computed over a complete collection.
`appliedFilters`	No	Actual normalized retrieval scope and filters.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations establish read-only/idempotent/open-world behavior, and the description adds substantial context beyond that: get rejects list filters and nondefault paging, empty answers mean no answer relation was published, term omission triggers candidate verification and requires exactly one match, and canonical IDs resolve directly. These are precisely the operational quirks an agent needs.

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 the main capabilities and then layers constraints without wasted words. It is dense and mostly earns its sentences, though the single-paragraph format makes some mode-specific rules harder to scan than a short bulleted split would.

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?

Given an output schema and rich annotations, the description covers the remaining gaps: dual-mode behavior, pagination continuation, disambiguation rules, supported work_type lookup, and the absence of keyword/author search. Nothing essential for calling this 8-parameter, two-mode tool correctly is missing.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents every parameter in detail. The description adds some workflow nuance (human citation format, term disambiguation, page.next_offset) but does not add much parameter-level meaning beyond what the schema provides. Baseline 3 is appropriate.

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 description names the resource (parliamentary questions), the two operations (list by year/work_type, get by question_id), and the extra payloads available in get mode (metadata, source-file links, published answers). It also explicitly rules out keyword/author/addressee search, which distinguishes it from search-oriented siblings without needing to name them.

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 gives explicit mode selection rules: default list discovers questions; get requires question_id and forbids year/work_type. It routes the agent to euparl_list_reference for work_type codes and explains how to continue pagination with page.next_offset. It also covers the term-disambiguation workflow and when to supply term versus omitting it.

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

All eu-parliament-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.