A
licenseA
qualityC
maintenanceLegalMCP is a comprehensive US legal MCP server that enables AI assistants to search over 4 million US court opinions, manage Clio practice data, and access PACER federal filings through natural language.
18
68
MIT
legal.ge MCP Server
Officialby infolegalge
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@legal.ge MCP ServerFind a Georgian lawyer for divorce proceedings"
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.
legal.ge MCP server
Find verified legal specialists in Georgia from inside Claude Desktop, Cursor, or any Model Context Protocol client.
This server wraps the public legal.ge Ask API as MCP tools. Ask in natural language; get matched practice areas plus ranked verified specialists with their profile URLs.
What it does
Exposes two tools:
find_legal_specialists— describe a legal situation in natural language; get matched practice areas, specific services, and a ranked list of verified specialists, each with a profile URL on legal.ge.classify_legal_intent— same matcher without the specialist lookup. Returns just the matched categories, useful when you want to identify the legal domain before deciding next steps.
Both tools support Georgian (ka), English (en), and Russian (ru). The matcher handles colloquial phrasings, legal jargon, and cross-script abbreviations (AML, KYC, MLC, ICC, etc.).
Related MCP server: Gyeongguk
Trust contract
Verified profiles only. Every specialist returned is
verification_status='verified'on legal.ge. Many are registered with the Georgian Bar Association — checkprofessional_orgson each result.Contact info is opt-in.
contact.emailandcontact.phoneare populated only when the specialist has chosen to publish them. Otherwise null — the user signs in on legal.ge to send a message.Read-only. This server cannot create inquiries, bookings, or any other side effects. It only queries.
No keys required. The legal.ge Ask API is public; rate-limited per IP.
Installation
Claude Desktop
Edit your claude_desktop_config.json:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add the legal.ge entry under mcpServers:
{
"mcpServers": {
"legal-ge": {
"command": "npx",
"args": ["-y", "@legalge/mcp"]
}
}
}Restart Claude Desktop. The tools will appear in any conversation, callable when you ask about Georgian legal questions.
Cursor
Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per-project):
{
"mcpServers": {
"legal-ge": {
"command": "npx",
"args": ["-y", "@legalge/mcp"]
}
}
}Other MCP-compatible clients
Any client that supports stdio-transport MCP servers can use this. Configuration shape:
Command:
npxArgs:
["-y", "@legalge/mcp"]Transport: stdio
Optional env:
LEGALGE_BASE_URL(defaults tohttps://legal.ge)
Example conversations
After installing, try asking Claude (or any MCP-aware agent):
"Find me a Georgian lawyer who handles eviction defense for tenants in Tbilisi."
"I was just laid off in Georgia without notice. Who can help me?"
"ვინ შემიძლია მქონდეს ბინის ნასყიდობის ხელშეკრულების შესადგენად?"
The agent will call find_legal_specialists with the appropriate locale and surface verified specialists by name + profile URL + practice area.
Development
# install dependencies
npm install
# run locally against legal.ge
npm run dev
# point at staging
LEGALGE_BASE_URL=https://staging.legal.ge npm run dev
# build
npm run buildConfiguration
Env var | Default | Purpose |
|
| Override the API endpoint (e.g. for local testing) |
API reference
The underlying HTTP API is documented at https://legal.ge/api/openapi.json. This MCP server is a thin wrapper — you can also call the API directly without MCP if you prefer.
License
MIT — see LICENSE.
About legal.ge
legal.ge is the verified directory of legal specialists in Georgia (the country). Trilingual platform (Georgian, English, Russian). Browse practice areas, find lawyers and law firms, request consultations.
See legal.ge/llms.txt for the AI-agent contract.
Available Tools
2 toolsclassify_legal_intentA
Classify a free-text legal question into matched practice areas (categories and specific services) without returning specialists. Lighter weight than find_legal_specialists. Use this when you want to understand the legal domain of a query before deciding next steps, or when you only need the practice area, not specialist recommendations. Returns matched categories with parent chains so you can cite either the specific service or the broader practice area.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural-language legal question or situation. | |
| locale | No | User's language. Defaults to 'en'. | en |
TDQS
A4.4/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It clearly says the tool does not return specialists and that it returns 'matched categories with parent chains'. This provides concrete expectations beyond the basic purpose. It does not mention error handling or rate limits, but for a read-only classification tool, this is sufficient.
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 four sentences, each contributing meaningfully: primary purpose, differentiation, usage context, and output detail. It is front-loaded and contains no filler or redundant repetition.
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?
Without an output schema, the description explains what is returned (matched categories with parent chains) and how to use it (cite specific service or broader practice area). It also covers when to use the tool. Minor gaps like limits or edge-case behavior are not addressed, but the tool is simple enough that this is reasonably complete.
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%: both 'query' and 'locale' have descriptions in the schema. The description adds no extra parameter-level detail beyond rephrasing that the input is a 'free-text legal question'. Since the schema already documents parameters fully, the baseline of 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 clearly states the verb 'classify' and the resource 'free-text legal question', with output 'matched practice areas'. It explicitly distinguishes itself from the sibling tool by stating 'without returning specialists' and 'Lighter weight than find_legal_specialists'.
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?
The description gives explicit when-to-use guidance: 'Use this when you want to understand the legal domain of a query before deciding next steps, or when you only need the practice area, not specialist recommendations.' It also implies when not to use (when specialist recommendations are needed) and names the alternative find_legal_specialists.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
find_legal_specialistsA
Find verified legal specialists in Georgia (the country, not the US state) from a natural-language description of a legal situation or need. Returns matched practice areas (and specific services where applicable) plus a ranked list of verified specialists, each with a canonical profile URL on legal.ge. Use this tool when a user needs to find a lawyer or legal expert for a specific issue in Georgia — eviction, divorce, corporate law, criminal defense, immigration, tax, etc. Supports Georgian (ka), English (en), and Russian (ru). Pass the user's language as locale. Sending an actual inquiry requires the user to sign in on legal.ge — this tool returns profile URLs so the user can click through.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of specialists to return (1-50). Default 10. The API also returns matched_categories regardless of this limit. | |
| query | Yes | Natural-language description of the legal situation or need. Example: 'I was evicted from my apartment without notice', 'I need help registering an LLC in Tbilisi', 'my employer is changing my contract'. | |
| locale | No | User's language. ka = Georgian, en = English, ru = Russian. Defaults to 'en'. | en |
TDQS
A4.1/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool returns canonical profile URLs, that matched categories are always returned separately, and that sending a real inquiry requires user sign-in on legal.ge. It also notes language support, adding behavioral context beyond the schema.
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 core purpose and groups related information into four sentences. It includes useful examples and caveats without being overly verbose, though it could be slightly tightened without losing value.
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 the moderate tool complexity and no output schema, the description adequately covers inputs, outputs, language support, and the sign-in caveat. It would be more complete if it explicitly mentioned how it relates to `classify_legal_intent`, but the purpose and usage are clear enough for an agent to select and call this tool 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?
Schema coverage is 100%, so the baseline is 3. The description reinforces the meaning of `query` (natural-language description) and `locale` (supports ka/en/ru), but does not add meaningful detail beyond what the schema already provides. It does not explain `limit` behavior 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 opens with a specific verb ('Find') and resource ('verified legal specialists in Georgia'), clearly scoping to the country not the US state, and explains the input (natural-language description) and output (matched practice areas and ranked list with profile URLs). This distinguishes it from the sibling `classify_legal_intent`, which likely focuses on categorization rather than finding specialists.
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 explicit usage context: 'Use this tool when a user needs to find a lawyer or legal expert for a specific issue in Georgia' with examples. It also instructs to pass the user's language as `locale`. It doesn't state when not to use or mention the sibling as an alternative, so it's clear but lacks explicit exclusionary guidance.
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.
2 tool updates
v0.1.1- First observed
classify_legal_intent - First observed
find_legal_specialists
TDQS
A4.1/5.0
Scored across 2 tools
Disambiguation4/5
The two tools have distinct primary purposes: one returns specialist recommendations, the other only classifies legal intent. However, both return matched practice areas, which could cause some confusion if an agent only needs classification and sees the specialist tool as a heavier version.
Naming Consistency5/5
Both tools follow a consistent verb_noun pattern: 'find_legal_specialists' and 'classify_legal_intent'. The naming is clear, predictive, and uses the same structural style.
Tool Count3/5
With only two tools, the server feels minimal. While the scope is narrow (legal specialist matching and intent classification), two tools are on the border of being too thin for a general-purpose legal assistant.
Completeness4/5
The server covers the two core operations described in its purpose: classifying legal intent and finding specialists. A minor gap is the lack of a tool to fetch detailed specialist profiles, but the returned URLs serve as a workaround for the user to access full information.
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
Connect AI to millions of laws and court cases with the Lawstronaut MCP.
Dispatch litigation work to legal-services vendors from any MCP-compatible AI workflow.
Law firm management MCP: manage cases, clients, tasks, calendar and documents via Claude AI.
Hire specialists by the hour — search, schedule, and pay via MCP protocol.
Related MCP Servers
- AlicenseBqualityBmaintenanceEnables Korean legal document processing, case analysis, and consultation using MCP, with OCR parsing, fact extraction, claim identification, subsumption grid, legal API verification, and document drafting.24MIT
- FlicenseNot gradedqualityCmaintenanceProvides access to German court decisions and laws via MCP tools, enabling legal document search and retrieval.-
- FlicenseNot gradedqualityAmaintenanceEnables law firm staff to automate case intake, conflict-of-interest checks, and attorney assignment through secure MCP tools without exposing sensitive data directly to LLMs.-