at-ris-mcp

Name: at-ris-mcp
Author: paragraflabs

by paragraflabs

Overview Schema Related Servers Score Discussions

Python

Remote

at-ris-mcp

PyPI Python License

A generic MCP server and standalone Python client library for the Austrian RIS (Rechtsinformationssystem des Bundes), the official legal information system of the Republic of Austria, operated by the Bundeskanzleramt.

It covers federal law (Bundesrecht — including consolidated law BrKons, the official gazettes, drafts and government bills), state law (Landesrecht of the nine Bundesländer), case law (Judikatur — OGH, VfGH, VwGH, BVwG, LVwG and more), ministerial decrees, district and municipal law, plus a change-monitoring feed — via the keyless OGD API at https://data.bka.gv.at/ris/api/v2.6/.

Why this exists

Compared with existing RIS tooling, at-ris-mcp adds:

Consolidated law (BrKons) — the currently applicable text, not just the gazette novellas.
Section-precise access — retrieve a single §/Artikel/Anlage (Abschnitt.*).
Historical version — the law as it stood on a given date (Fassung.FassungVom).
Clean Markdown — RIS HTML (≈40 KB of CSS boilerplate per document) is stripped to the legal text, with a raw switch for the untouched original.

Related MCP server: ris-mcp

Two packages, one repo

ris_client — a standalone, MCP-independent library. Import it directly.
ris_mcp — a thin FastMCP/stdio wrapper exposing 10 tools. Contains no logic of its own.

Install

pip install at-ris-mcp          # library only
pip install "at-ris-mcp[mcp]"   # + the MCP server (FastMCP)

Run the MCP server (stdio)

at-ris-mcp
# or
python -m ris_mcp

Remote transport (HTTP / SSE)

For hosted or remote deployments the server can also speak streamable HTTP or SSE instead of stdio:

at-ris-mcp --transport http --host 0.0.0.0 --port 8000   # streamable HTTP
at-ris-mcp --transport sse  --port 9000                  # SSE
# or via environment:
RIS_MCP_TRANSPORT=http RIS_MCP_PORT=8000 at-ris-mcp

The HTTP endpoint is served at /mcp by default (override with --path / RIS_MCP_PATH). stdio remains the default when no transport is given.

Tools

Tool	Purpose
`ris_search_law`	Search Bundesrecht (default `BrKons`; also `BgblAuth`, `Begut`, `RegV`, …). Section + Fassung filters.
`ris_get_law_text`	Full text of a statute/section (markdown \| html \| xml \| raw).
`ris_search_case`	Search Judikatur (default `Justiz`; all courts). Filter by applied `norm`.
`ris_get_case_text`	Full text of a decision.
`ris_search_state_law`	Search Landesrecht (9 Bundesländer; default `LrKons`). Select states via `bundeslaender`.
`ris_search_misc`	Search `Sonstige` (ministerial decrees `Erlaesse`, `Avsv`, …).
`ris_search_district`	Search district authority notices (`Bezirke` / `Bvb`).
`ris_search_municipality`	Search municipal law (`Gemeinden` / Gemeinderecht `Gr`/`GrA`).
`ris_list_collections`	Which endpoints/applications are covered.
`ris_list_changes`	Change/early-warning feed (RIS History) via the OGD SOAP endpoint, incl. deleted documents.

Library usage

import asyncio
from ris_client import RisClient, LawSearchRequest, TextFormat

async def main():
    async with RisClient() as c:
        res = await c.search_law(LawSearchRequest(suchworte="Datenschutzgesetz",
                                                  page_size="Ten"))
        hit = res.items[0]
        print(hit.human_readable_citation, hit.eli_uri)
        text = await c.get_text(hit.content_urls["html"], TextFormat.markdown)
        print(text.content[:500])

asyncio.run(main())

Configuration (environment variables)

Variable	Default	Meaning
`RIS_BASE_URL`	`https://data.bka.gv.at/ris/api/v2.6`	API base (version isolation).
`RIS_SOAP_URL`	`https://data.bka.gv.at/ris/ogd/v2.6/`	OGD SOAP endpoint (used by `ris_list_changes`).
`RIS_USER_AGENT`	`at-ris-mcp/<version> (+…)`	Descriptive UA (netiquette).
`RIS_RATE_MS`	`1200`	Minimum delay between requests (ms).
`RIS_TIMEOUT_S`	`30`	HTTP timeout.
`RIS_MAX_RETRIES`	`3`	Retries on 429/5xx (incl. 503).
`RIS_CACHE_DIR`	`~/.cache/at-ris-mcp`	SQLite cache location.
`RIS_CACHE_ENABLED`	`true`	Toggle the cache.
`RIS_AUDIT_DIR`	(unset)	If set, append a JSONL audit line per call (no full text, no client data).
`RIS_MCP_TRANSPORT`	`stdio`	Server transport: `stdio` \| `http` \| `sse` \| `streamable-http`.
`RIS_MCP_HOST`	`127.0.0.1`	Bind host for http/sse.
`RIS_MCP_PORT`	`8000`	Bind port for http/sse.
`RIS_MCP_PATH`	(transport default)	URL path for the HTTP endpoint.

Netiquette & rate limiting

Per the RIS OGD FAQ: a 1–2 s pause per page is enforced by the client; bulk access should occur outside office hours (18:00–06:00) or on weekends and be announced to ris.it@bka.gv.at. A descriptive User-Agent is sent by default.

Licensing

Code: Apache-2.0 (see LICENSE).
Data: the retrieved documents are provided by the Republic of Austria under CC BY 4.0. Every tool response carries an attribution field:
Quelle: RIS – Rechtsinformationssystem des Bundes (data.bka.gv.at), CC BY 4.0
No legal advice. Only the authentic promulgation text (Bundesgesetzblatt/Landesgesetzblatt authentisch) is legally binding. Consolidated law and all other documents are for information only. Every response carries a legal_notice to that effect.

Scope (v1.0)

Covered: Bundesrecht (BrKons, BgblAuth, BgblPdf, BgblAlt, Begut, RegV, Erv — English translations), Judikatur (all courts), the History change-feed (ris_list_changes, incl. deleted documents), Landesrecht (9 Bundesländer: LrKons, LgblAuth, Lgbl, LgblNO, Vbl), Sonstige (Erlaesse, Avsv, Avn, Spg, KmGer, Upts, Mrp, PruefGewO — with app-specific fine filters), Bezirke (Bvb) and Gemeinden (Gr, GrA).

English translations (Erv): search via ris_search_law with applikation="Erv". suchworte/titel map to the RIS SearchTerms/Title parameters automatically.

State-law note: for consolidated state law (LrKons), select the states via bundeslaender (e.g. ["Kaernten","Tirol"]); this maps to the dotted Bundesland.SucheIn<Land>=true flags the API requires (the flat form is silently ignored for LrKons).

History note: consolidated federal law is monitored under the application name Bundesnormen (not BrKons), consolidated state law under Landesnormen. The History query uses the OGD SOAP endpoint, since it is not exposed via the REST GET API.

Development

pip install -e ".[dev,mcp]"
pytest                       # offline tests
RIS_SMOKE=1 pytest -m smoke  # live smoke tests against the real API

Release

Releases are automated. Pushing a version tag (vX.Y.Z) triggers GitHub Actions to build the distributions, publish to PyPI (via Trusted Publishing / OIDC — no API token), create a GitHub Release, and register the new version in the MCP Registry.

# bump the version in pyproject.toml, src/ris_client/config.py and server.json,
# update CHANGELOG.md, then:
git tag -a vX.Y.Z -m "vX.Y.Z"
git push origin vX.Y.Z

To build locally without publishing:

python -m build              # sdist + wheel into dist/
python -m twine check dist/*

The MCP-registry entry is described by server.json (name io.github.paragraflabs/at-ris-mcp); the matching mcp-name: marker is embedded near the top of this README.

Contributing & support

Issues and pull requests are welcome at https://github.com/paragraflabs/at-ris-mcp. See CHANGELOG.md for the release history. This project is not affiliated with or endorsed by the Republic of Austria or the Bundeskanzleramt; it is an independent client for the public RIS OGD interface.

Available Tools

2 tools

ris_get_law_textA

Fetch the full text of a statute/section from a hit's content_urls.

format: markdown (default) | html | xml | raw (unaltered original). Pass eli_uri and human_readable_citation from the search hit so the text stays citable. content_url must be a .html or .xml URL on ris.bka.gv.at.

ParametersJSON Schema

Name	Required	Default
`format`	No	markdown
`eli_uri`	No
`content_url`	Yes
`human_readable_citation`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.3/5.0

Behavior3/5

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

No annotations provided, so description carries full burden. It discloses format options and URL constraints, but omits details on side effects, rate limits, or error conditions. Adequate but not rich.

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?

Two sentences plus a short line. Front-loaded with main action, then parameter details. No 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?

Output schema exists, so return values are covered. Description covers what is fetched, source, format, and citation parameters. Complete for a retrieval tool.

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 has 0% description coverage, so description compensates by explaining the format parameter with options, and clarifying the purpose of eli_uri and human_readable_citation for citability. Adds significant meaning beyond the schema.

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 clearly states the tool fetches the full text of a statute/section from a hit's content_urls, with a specific verb and resource. It distinguishes from the sibling ris_search_law, which is for searching.

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 guidance on passing eli_uri and human_readable_citation for citability, and constrains content_url to .html or .xml on ris.bka.gv.at. Does not explicitly state when not to use, but the context of retrieval after search is clear.

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

ris_search_lawA

Search Austrian federal law (Bundesrecht).

applikation: BrKons (consolidated law, default) | BgblAuth | BgblPdf | BgblAlt | Begut | RegV | Erv. Use paragraph/artikel/anlage="N" or "N-M" for section access (BrKons), fassung_vom=YYYY-MM-DD for a historical version snapshot. For Begut/RegV use einbringende_stelle, in_begutachtung_am (Begut) or beschluss_von/beschluss_bis (RegV). Each hit carries eli_uri, human_readable_citation, source_url and content_urls for ris_get_law_text.

ParametersJSON Schema

Name	Required	Default
`typ`	No
`index`	No
`titel`	No
`anlage`	No
`artikel`	No
`page_size`	No	Twenty
`paragraph`	No
`suchworte`	No
`applikation`	No	BrKons
`fassung_vom`	No
`page_number`	No
`in_kraft_bis`	No
`in_kraft_von`	No
`beschluss_bis`	No
`beschluss_von`	No
`geaendert_seit`	No
`gesetzesnummer`	No
`kundmachungsorgan`	No
`in_begutachtung_am`	No
`einbringende_stelle`	No
`kundmachungsorgannummer`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries full burden. It discloses that each hit includes eli_uri, human_readable_citation, source_url, content_urls, and that fassung_vom provides historical snapshots. It does not mention rate limits or authentication, but for a search tool these are less critical.

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 concise, front-loads purpose, and uses structured listing of applikation values and parameter usage. Every sentence adds specific detail without redundancy.

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

Completeness4/5

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

Given 21 parameters and an existing output schema, the description covers many usage scenarios and output fields. It could explicitly mention pagination parameters (page_number, page_size) but still provides substantial 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?

Schema coverage is 0%, so description must add meaning. It explains several parameters (applikation, paragraph, artikel, anlage, fassung_vom, etc.) but omits many others like suchworte, titel, gesetzesnummer. It adds value but not for all 21 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 clearly states it searches Austrian federal law (Bundesrecht), which is a specific verb+resource. It distinguishes from the sibling tool ris_get_law_text by focusing on search functionality, not text retrieval.

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 provides clear guidance on using different applikation types and parameters (e.g., paragraph/artikel/anlage for BrKons, einbringende_stelle for Begut). It implicitly separates use cases but does not explicitly state when not to use this tool or when to prefer the sibling.

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

Install Server

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

TDQS

A4.3/5.0

Disambiguation5/5

The two tools have clearly distinct purposes: one for searching Austrian federal law, the other for fetching the full text of a specific statute or section. There is no overlap or ambiguity.

Naming Consistency5/5

Both tools follow a consistent 'ris_verb_noun' pattern: ris_search_law and ris_get_law_text. The naming is predictable and clear.

Tool Count3/5

With only two tools, the server is minimal. While they cover search and retrieval, the scope suggests more tools might be expected (e.g., browsing, categorizing), making it borderline but not inadequate.

Completeness4/5

The tool surface covers the essential workflow of searching for a law and retrieving its full text. Minor gaps exist, such as direct access to law lists or metadata, but the core functionality is complete.

Maintenance

ActivitySlowing

ResponsivenessSyncing

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

ris-austria-mcp-server A
io.github.cyanheads
Search Austrian federal and state law, court decisions, and the authentic Bundesgesetzblatt (RIS).
Government Data Legal & Compliance
922
Austrian Firmenbuch A
io.github.jkbngb
Austria's official company register (Firmenbuch) – master data, financials & ratios for AI agents.
Government Data Finance
2
botcorpus A
io.github.mixall11
Sourced, dated SK/CZ/AT/EU civic, tax and legal facts for AI agents. Read via MCP, not guesswork.
Government Data Open Data
72
Gridbert
at.gridbert
Austrian energy data: 119 electricity tariffs daily, grid fees, subsidies, bill analysis.
Energy Open Data
1

Related MCP Servers

ris-mcp
Government Data Search Legal & Compliance
Honeyfield-Org
A
license
A
quality
B
maintenance
An MCP server that gives you access to Austria's official legal database, the Rechtsinformationssystem (RIS).
Updated a month ago (2026-08-07 09:37 UTC)
13
169
16
MIT
ris-mcp
Legal & Compliance Government Data Search
noahpfi
F
license
Not graded
quality
B
maintenance
MCP server that exposes Austrian federal law (Bundesrecht) to LLMs, enabling full-text search, paragraph retrieval, historical versions, statute lookup, BGBl lookups, amendment timelines, and citation searches via the public RIS OGD API.
Updated 16 days ago (2026-08-18 19:23 UTC)
at-eli-mcp
Legal & Compliance Government Data Search
matematicsolutions
A
license
A
quality
A
maintenance
Enables searching and retrieving Austrian federal legislation and case law from the official legal information system RIS, with verifiable ELI and ECLI identifiers.
Updated 7 days ago (2026-08-27 13:08 UTC)
6
Apache 2.0
Slovenian Law MCP Server
Legal & Compliance Search Government Data
Ansvar-Systems
A
license
Not graded
quality
F
maintenance
Enables querying 40 Slovenian statutes with full-text search, provision retrieval, and EU law integration, providing verified references from official PISRS sources.
Updated a month ago (2026-07-22 10:37 UTC)
72
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/paragraflabs/at-ris-mcp'

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

at-ris-mcp

Why this exists

Two packages, one repo

Install

Run the MCP server (stdio)

Remote transport (HTTP / SSE)

Tools

Library usage

Configuration (environment variables)

Netiquette & rate limiting

Licensing

Scope (v1.0)

Development

Release

Contributing & support

Available Tools

Output Schema

TDQS

Output Schema

TDQS

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

ris-mcp

ris-mcp

at-eli-mcp

Slovenian Law MCP Server

Latest Blog Posts

MCP directory API