How do I use hr-eli-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@hr-eli-mcp list documents in NN issue 42/2018" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

hr-eli-mcp

by matematicsolutions

Overview Schema Source Related Servers Score Discussions Admin

Python

Remote

hr-eli-mcp

An MCP server for the Croatian Narodne novine official gazette (narodne-novine.nn.hr). It fetches Croatian legislation with European ELI identifiers and verifiable citations.

Part of the MateMatic eu-legal-mcp production line - after PL, DE, AT, ES, FI, IE, NL, SE, FR, LU, DK and CZ. Same citation contract, Narodne novine source. Croatia is ELI-native on the European ELI ontology (data.europa.eu/eli), with JSON-LD metadata per document.

Scope. This MVP lists the documents of a gazette issue, returns per-document metadata from JSON-LD, and fetches the official HTML text. Documents are addressed by year + issue + document number; the gazette is path-based, not keyword search. Coverage 1990-present. Language: Croatian. Every response carries a dataset_note.
Licence. Narodne novine is the official public gazette of Croatia. This connector relays it read-only with attribution and a source_url.

The tools

Tool	What it does
`hr_list_issue`	List the documents of a gazette issue by year + issue (discovery).
`hr_get_act`	Metadata for a document by year + issue + doc number.
`hr_get_text`	Full official HTML text of a document.
`hr_coverage`	Declare what this connector covers, when each family was captured, and - explicitly - what it does NOT cover. Every gap carries a fallback.

Every response carries the contract: eli_uri (the European ELI URL, e.g. https://narodne-novine.nn.hr/eli/sluzbeni/2018/42/805), human_readable_citation (title + NN 42/2018), and source_url.

Related MCP server: sk-eli-mcp

Install

Run it with no install step (once published to PyPI):

uvx hr-eli-mcp

Or from source:

cd hr-eli-mcp
pip install -e .

Configure (Claude Code / any MCP client)

{
  "mcpServers": {
    "hr-eli-mcp": { "command": "hr-eli-mcp" }
  }
}

Windows 11 with Smart App Control

Smart App Control blocks unsigned executables, which covers uvx.exe, pip.exe and the hr-eli-mcp.exe launcher that pip writes at install time. The python.exe and py.exe from the python.org installer are signed by the Python Software Foundation, so running the module through the interpreter works:

python -m pip install hr-eli-mcp
python -m hr_eli_mcp

pip.exe is blocked for the same reason, so install with python -m pip, not pip install. If python is not on PATH, use the Windows launcher: py -3 -m hr_eli_mcp.

{ "mcpServers": { "hr-eli-mcp": { "command": "python", "args": ["-m", "hr_eli_mcp"] } } }

Do not turn Smart App Control off to work around this - it cannot be re-enabled without reinstalling Windows.

Environment:

HR_ELI_BASE_URL - default https://narodne-novine.nn.hr
HR_ELI_CACHE_DIR - default ~/.matematic/cache/hr-eli
HR_ELI_AUDIT_DIR - default ~/.matematic/audit

No API key. Narodne novine open data is keyless.

Governance

Public data only - read-only against Narodne novine; no client data leaves the machine.
Audit log - every tool call appends one JSON line to ~/.matematic/audit/hr-eli-mcp.jsonl.
Vendor-neutral - talks only to narodne-novine.nn.hr; no LLM provider, no telemetry.
Verifiable citations - every response is independently checkable via source_url.

See CONSTITUTION.md and DISCOVERY.md.

Tests

pip install -e ".[dev]"
pytest tests/test_instructions_drift.py tests/test_parse.py -v   # offline
pytest tests/test_smoke.py -v                                    # hits live Narodne novine

Licence

Apache-2.0. © Matematic Solutions / Wieslaw Mazur.

Available Tools

4 tools

hr_coverageA

Read-onlyIdempotent

Declare what this connector covers, how it is sourced, and what it does NOT cover.

Call this before telling a user that the law "does not contain" something, and whenever a search comes back empty: the absence may be a gap in this connector rather than in the law. Every gap carries a fallback saying where to look instead.

Returns: Coverage with families, an as-of note, and a non-empty list of known gaps.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`status`	No
`families`	No
`as_of_note`	Yes	States what the dates mean, and what they do not promise.
`known_gaps`	No	Never empty. An empty list would mean 'not checked', not 'no gaps'.

TDQS

A4.9/5.0

Behavior5/5

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

The description goes beyond the annotations by explaining the open-world behavior in operational terms: absence may indicate a connector gap, not a legal gap. It also discloses return value specifics, including families, as-of note, and a non-empty list of known gaps with fallbacks. No contradiction with annotations exists.

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

Conciseness5/5

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

The description is compact and front-loaded. Each sentence earns its place: the first defines scope, the second gives the exact trigger conditions, and the third summarizes the return structure. No filler or redundancy.

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 zero parameters, rich annotations, and an output schema, the description is fully complete for an agent to select and call the tool correctly. It covers purpose, triggers, behavioral nuance, and expected return content.

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?

The tool has zero parameters, so there is no parameter documentation burden. The description appropriately focuses on behavior and return semantics rather than parameters.

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 states a specific verb and resource: 'Declare what this connector covers, how it is sourced, and what it does NOT cover.' It clearly distinguishes this tool from the sibling retrieval tools by framing it as the coverage/gap declaration tool rather than an act/text/issue tool.

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?

Explicit usage guidance is given: 'Call this before telling a user that the law does not contain something, and whenever a search comes back empty.' This tells the agent exactly when to invoke it and why, including the fallback behavior for gaps.

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

hr_get_actA

Read-onlyIdempotent

Fetch document metadata by ELI coordinate (year + issue + doc).

ParametersJSON Schema

Name	Required	Description
`doc`	Yes	document number within the issue, e.g. ``805``.
`year`	Yes	e.g. ``2018``.
`issue`	Yes	gazette issue, e.g. ``42``.

Output Schema

ParametersJSON Schema

Name	Required	Description
`doc`	No
`year`	No
`issue`	No
`title`	No
`number`	No
`eli_uri`	No
`source_url`	No
`dataset_note`	No
`date_document`	No
`type_document`	No
`date_publication`	No
`human_readable_citation`	No

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, and not destructive. The description adds that this returns 'metadata' rather than the full text, which is a behavioral distinction beyond the annotations. No contradiction found.

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

Conciseness5/5

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

The description is a single, concise sentence that front-loads the action and resource, with zero wasted words.

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 a simple 3-parameter metadata fetch with a full output schema and clear annotations, the description provides enough context. It clarifies the domain (ELI) and the distinction between metadata and text, making the tool complete for an agent to invoke correctly.

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?

The input schema provides 100% coverage with descriptions and examples for all three parameters. The description merely restates them as 'year + issue + doc' without adding any extra meaning, so it meets the baseline for high schema coverage.

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 uses a specific verb ('Fetch'), names the resource ('document metadata'), and specifies the unique identifier type ('ELI coordinate'), which clearly distinguishes it from siblings like hr_get_text (which retrieves text) and hr_list_issue (which lists issues).

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?

The description implies the tool is for retrieving metadata by a precise coordinate, contrasting with siblings that handle listing or text retrieval. However, it does not explicitly state when to use this tool over alternatives or call out exclusions, so it stops short of a 5.

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

hr_get_textA

Read-onlyIdempotent

Fetch the full official HTML text of a document by ELI coordinate.

ParametersJSON Schema

Name	Required	Description
`doc`	Yes	document number within the issue, e.g. ``805``.
`year`	Yes	e.g. ``2018``.
`issue`	Yes	gazette issue, e.g. ``42``.

Output Schema

ParametersJSON Schema

Name	Required	Description
`doc`	No
`year`	No
`issue`	No
`title`	No
`format`	No
`content`	No
`eli_uri`	No
`byte_size`	No
`source_url`	No
`dataset_note`	No
`human_readable_citation`	No

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description's 'Fetch' aligns with these hints but adds no extra behavioral detail such as authentication requirements or potential errors, so the description adds no value beyond annotations.

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

Conciseness5/5

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

The description is a single sentence that states the action and object succinctly, with no wasted words or redundant details. It is excellently front-loaded.

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 the complete input schema, rich safety annotations, and an output schema (not shown but indicated), the tool is fully specified. The short description is sufficient for a simple document-fetch operation.

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% with each parameter (year, issue, doc) having clear descriptions and examples. The description itself does not add further parameter meaning, but the schema already carries the full load, meeting the baseline.

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 uses a specific verb 'Fetch' and names the resource: 'full official HTML text of a document by ELI coordinate.' This clearly distinguishes it from siblings like hr_list_issue (listing issues) and hr_get_act (retrieving acts specifically).

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

Usage Guidelines3/5

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

No usage guidance is provided beyond the tool's basic function. It does not mention alternatives like hr_get_act or state when to prefer this tool, so the usage context is only implied.

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

hr_list_issueA

Read-onlyIdempotent

List the documents published in a Narodne novine gazette issue.

ParametersJSON Schema

Name	Required	Description	Default
`year`	Yes	e.g. ``2018``.
`issue`	Yes	gazette issue number, e.g. ``42`` (from a citation like "NN 42/2018").

Output Schema

ParametersJSON Schema

Name	Required	Description
`year`	Yes
`issue`	Yes
`items`	No
`total`	Yes
`dataset_note`	No

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds no extra behavioral context beyond the basic listing function, such as pagination, result limits, or authentication requirements. It is consistent with annotations but doesn't go further.

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

Conciseness5/5

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

The description is a single, front-loaded sentence that clearly states the tool's purpose without unnecessary words or repetition. It is concise and immediately understandable.

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?

The tool is simple, has a clear output schema, rich annotations, and a concise description. No critical information is missing for an agent to select and invoke this correctly; the description and schema together cover the necessary context.

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?

The input schema covers both parameters (year and issue) with descriptive examples in comments, achieving 100% schema description coverage. The description itself adds no parameter detail beyond what the schema already provides, so baseline 3 applies.

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 uses a specific verb ('List') with a clear resource ('documents published in a Narodne novine gazette issue'). This distinguishes it from sibling tools (hr_get_act, hr_get_text) which fetch specific items rather than listing all documents in an issue.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention that the user should first list documents before fetching specific acts or texts, nor does it give any context about the typical workflow or exclusions.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

1 tool updatev0.3.3Aug 28, 2026
- Addedhr_coverage
3 tool updatesv0.2.1Aug 5, 2026
- First observedhr_get_act
- First observedhr_get_text
- First observedhr_list_issue

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0

Scored 2026-09-02 00:10 across 4 tools

Disambiguation4/5

hr_get_act and hr_get_text are clearly separated as metadata versus full HTML text, and hr_list_issue handles discovery by gazette issue. hr_coverage is distinct as a meta-tool for gaps. The only minor risk is that hr_get_act and hr_get_text both accept ELI coordinates, but their descriptions resolve the boundary.

Naming Consistency4/5

Tools share a consistent hr_ prefix and mostly follow a verb_noun pattern: hr_list_issue, hr_get_act, hr_get_text. hr_coverage breaks the pattern by using a noun-only name, though it is still understandable and consistent in style.

Tool Count5/5

Four tools is an appropriate, focused scope for an ELI legal document connector. Each tool performs a distinct retrieval or coverage function, and none feel redundant or missing as a core operation.

Completeness4/5

The server covers the core workflow: discovering documents by issue, fetching metadata, and retrieving full text. A full-text or title search is absent, but hr_coverage explicitly documents known gaps and fallback sources, which mitigates the limitation.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

SourceActs
com.sourceacts
Official EUR-Lex, UK, US, and gazette search, metadata fetch, and change-only watches.
Legal & Compliance Search
1
kvasir — verifiable German, Austrian, Swiss & EU lawOAuth
legal.kvasir
Resolve, search and verify legal citations against the official sources, with provenance.
Legal & Compliance Search
2
Lex — Temporal Luxembourg and EU Law A
io.github.SFHAJJI
Temporal search and comparison for official Luxembourg and reviewed EU law, with provenance.
Legal & Compliance Search Government Data
1019
Japan Law A
io.github.pipeworx-io
Japan Law MCP — Japanese national laws & ordinances via the e-Gov Law API.
Legal & Compliance Government Data
332

Related MCP Servers

lu-eli-mcp
Legal & Compliance Government Data
matematicsolutions
A
license
A
quality
A
maintenance
Enables querying Luxembourg legislation metadata and full Akoma Ntoso text via ELI identifiers from Legilux open data.
Updated 16 days ago (2026-08-24 13:57 UTC)
3
1
Apache 2.0
sk-eli-mcp
Legal & Compliance Government Data Open Data
matematicsolutions
A
license
A
quality
B
maintenance
Enables access to Slovak legislation from the Collection of Laws via static.slov-lex.sk. Supports listing consolidated versions, retrieving act metadata, and fetching full text with verifiable citations.
Updated 16 days ago (2026-08-24 13:58 UTC)
4
Apache 2.0
mt-eli-mcp
Government Data Legal & Compliance
matematicsolutions
A
license
A
quality
A
maintenance
Provides access to Maltese legislation via ELI coordinates, fetching metadata and full text from the official legislation.mt portal.
Updated 16 days ago (2026-08-24 13:57 UTC)
3
Apache 2.0
be-eli-mcp
Legal & Compliance Government Data
matematicsolutions
A
license
A
quality
B
maintenance
Enables retrieval of Belgian legislation metadata and full text by ELI coordinates from the official gazette (Moniteur Belge), supporting French, Dutch, and German languages.
Updated 14 days ago (2026-08-26 10:03 UTC)
3
Apache 2.0

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/matematicsolutions/hr-eli-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server