MCP for Russian court practice search
atomno-mcp-sudact
An MCP server searching Russian court rulings by text, statute, court and date, returning the full case text, like sudact.ru
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- Only reads and searches open court rulings, does not file anything with a court
- Requests go through third-party atomno-mcp hosting
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/atomno-mcp-sudactDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run in a terminal
claude mcp add --transport stdio --env 'MCP_SUDACT_TOKEN=<your MCP_SUDACT_TOKEN>' mcp-sudact -- uvx atomno-mcp-sudact==0.1.8Or add to the file .mcp.json, in the project
{
"mcpServers": {
"mcp-sudact": {
"command": "uvx",
"args": [
"atomno-mcp-sudact==0.1.8"
],
"env": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the mcpServers key.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
The button opens the agent and offers to add the server. If nothing happens, copy the config below.
Add to the file ~/.cursor/mcp.json, for all projects
{
"mcpServers": {
"mcp-sudact": {
"command": "uvx",
"args": [
"atomno-mcp-sudact==0.1.8"
],
"env": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the mcpServers key. For a single project, put the same block into .cursor/mcp.json.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
The button opens the agent and offers to add the server. If nothing happens, copy the config below.
Run in a terminal
code --add-mcp '{"name":"mcp-sudact","type":"stdio","command":"uvx","args":["atomno-mcp-sudact==0.1.8"],"env":{"MCP_SUDACT_TOKEN":"<your MCP_SUDACT_TOKEN>"}}'Or add to the file .vscode/mcp.json, in the project
{
"servers": {
"mcp-sudact": {
"type": "stdio",
"command": "uvx",
"args": [
"atomno-mcp-sudact==0.1.8"
],
"env": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the servers key.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Run in a terminal
codex mcp add mcp-sudact --env 'MCP_SUDACT_TOKEN=<your MCP_SUDACT_TOKEN>' -- uvx atomno-mcp-sudact==0.1.8Or add to the file ~/.codex/config.toml, for all projects
[mcp_servers.mcp-sudact]
command = "uvx"
args = ["atomno-mcp-sudact==0.1.8"]
env = { MCP_SUDACT_TOKEN = "<your MCP_SUDACT_TOKEN>" }If the file already exists, append the block to the end.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Run in a terminal
gemini mcp add -s user -e 'MCP_SUDACT_TOKEN=<your MCP_SUDACT_TOKEN>' mcp-sudact uvx atomno-mcp-sudact==0.1.8Or add to the file ~/.gemini/settings.json, for all projects
{
"mcpServers": {
"mcp-sudact": {
"command": "uvx",
"args": [
"atomno-mcp-sudact==0.1.8"
],
"env": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the mcpServers key.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Add to the file ~/.config/devin/mcp_config.json, for all projects
{
"mcpServers": {
"mcp-sudact": {
"command": "uvx",
"args": [
"atomno-mcp-sudact==0.1.8"
],
"env": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the mcpServers key. Legacy Cascade keeps the MCP config in ~/.codeium/windsurf/mcp_config.json.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Formerly Windsurf.
Add to the file cline_mcp_settings.json, for all projects
{
"mcpServers": {
"mcp-sudact": {
"command": "uvx",
"args": [
"atomno-mcp-sudact==0.1.8"
],
"env": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the mcpServers key. Open the settings file in Cline: MCP Servers tab, Configure MCP Servers.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Add to the file .roo/mcp.json, in the project
{
"mcpServers": {
"mcp-sudact": {
"command": "uvx",
"args": [
"atomno-mcp-sudact==0.1.8"
],
"env": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the mcpServers key.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
A fork of Roo Code, same .roo folders.
Add to the file opencode.json, in the project
{
"mcp": {
"mcp-sudact": {
"type": "local",
"command": [
"uvx",
"atomno-mcp-sudact==0.1.8"
],
"environment": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the mcp key.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Add to the file ~/.config/zed/settings.json, for all projects
{
"context_servers": {
"mcp-sudact": {
"command": "uvx",
"args": [
"atomno-mcp-sudact==0.1.8"
],
"env": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the context_servers key.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Add to the file .codeassistant/mcp.json, in the project
{
"mcpServers": {
"mcp-sudact": {
"command": "uvx",
"args": [
"atomno-mcp-sudact==0.1.8"
],
"env": {
"MCP_SUDACT_TOKEN": "<your MCP_SUDACT_TOKEN>"
}
}
}
}If the file already exists, add the server inside the mcpServers key.
Keys and settings
MCP_SUDACT_TOKENsecret, required- API key (Pro tier) for hosted search and document retrieval.
Replace the values in angle brackets with your own. Keys never go into install links and are not stored by us.
Get a key at atomno-mcp.ru/pricing (Pro tier), install the package with pipx install atomno-mcp-sudact or uvx atomno-mcp-sudact, and add the server to mcp.json with the MCP_SUDACT_TOKEN variable.
Other ways from the author
pipx install atomno-mcp-sudactOr uvx atomno-mcp-sudact with no separate install step.
This is third-party code. Review the repository files before installing.
What it does
The server gives the agent two tools: full-text search of court cases with filters by court type, instance, statutes and dates, and fetching the full text of a specific ruling by link or ID with optional personal-data anonymization. The search itself, caching and personal-data masking run on the atomno-mcp hosting service; nothing needs to be scraped or self-hosted. The client just connects with a paid-tier API key.
Who it is for. For lawyers and legal firms who want quick access to court practice right from a chat with an agent.
Good fit when
- You want similar cases by statute and court type to prepare a legal position
- You need the full text of a specific ruling from a link found elsewhere
- You need personal-data anonymization in a ruling's text before sharing it with a client
Not a fit when
- You are not ready to pay for the Pro tier: full-text access only works with a paid key
- You need a data source independent of someone else's hosting: the server fully depends on atomno-mcp infrastructure
Example request
Find court practice on Article 395 of the Russian Civil Code from arbitration courts over the last yearLimitations
The project is not affiliated with sudact.ru, data comes from open sources at your own risk. It only works with a paid Pro-tier key from atomno-mcp.ru, there is no free mode. The server depends on third-party hosting: without internet or if atomno-mcp.ru is down, search does not work.
How to disable. Remove the sudact entry from your MCP client config and cancel the subscription if needed.
MCP
- Transport
- stdio
- Authentication
- API key
| Environment variables | |
|---|---|
| MCP_SUDACT_TOKEN required, secret | Paid Pro-tier API key from atomno-mcp.ru |
| MCP_SUDACT_API_BASE | Backend base URL, defaults to production |
| MCP_SUDACT_TIMEOUT | HTTP timeout in seconds, defaults to 60 |
Security check
- Only reads and searches open court rulings, does not file anything with a court
- Requests go through third-party atomno-mcp hosting
README in short
The README opens by explaining the server runs through atomno-mcp hosting: search, caching and anonymization happen on its side, only a paid key is needed. It shows installation via pipx or uvx, two environment variables, config for Cursor and Claude Desktop, a two-tool table (search_cases and get_citation) with parameters, and a disclaimer that the project is not affiliated with sudact.ru.
FAQ
Is there a free option?
No, full-text access only works with a paid Pro-tier key from atomno-mcp.ru.
Where does the case data come from?
From open sources, similar to sudact.ru; the project is not affiliated with sudact.ru itself.
Related
Microsoft's utility and MCP server that turn PDF, Word, Excel, PowerPoint, HTML and other files into Markdown for models
Anthropic skills
Skills
Anthropic's official skill examples: docx, pdf, pptx and xlsx documents, design, MCP builder and the Agent Skills spec
A skill that builds editable PPTX decks from PDF, DOCX, URLs and Markdown with native shapes, charts and animations
A skill that draws editorial diagrams as standalone HTML and SVG files: architecture, flowcharts, ER, funnels and about forty more types