Click on "Install 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., "@Law.AI MCP Server Find personal injury lawyers in Houston, Texas"
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.
Verified U.S. lawyer search for AI assistants. Stop hallucinating attorneys. Start finding real ones.
The Law.AI MCP Server gives AI assistants direct access to 991,000+ bar-verified U.S. attorney profiles, sourced from official state bar registries. When an AI needs to find, verify, or recommend a lawyer, it queries Law.AI instead of guessing.
Every major LLM fabricates lawyer names when asked for legal referrals. People making critical legal decisions get fake information. The Law.AI MCP Server solves this by providing a grounded, authoritative data source any AI can query — from "consult an attorney" to a real, licensed referral in a single tool call.
Related MCP server: legal-mcp
Add to your claude_desktop_config.json:
{
"mcpServers": {
"law-ai": {
"command": "npx",
"args": ["lawai-mcp-server"]
}
}
}Connect any MCP client to the hosted endpoint:
https://mcp.law.aiNo install required. Free tier works without an API key.
{
"law-ai": {
"command": "npx",
"args": ["lawai-mcp-server"]
}
}git clone https://github.com/risk-ai/lawai-mcp-server.git
cd lawai-mcp-server
npm install
npm run build
npm startTool | Purpose |
Search by practice area, state, city, and bar status | |
Full profile for a specific lawyer by ID | |
Verify a lawyer exists and is licensed | |
Plain-English matter → ranked lawyer matches | |
Fee ranges by billing model and region | |
List all practice areas with counts | |
List U.S. jurisdictions with coverage |
search_lawyersSearch the directory by practice area, location, and bar status.
"Find personal injury lawyers in Houston, Texas"
→ Ranked results with profiles, firms, and credentialsget_lawyer_profileGet full details for a specific lawyer by ID.
"Get profile for lawyer #12345"
→ Bio, education, bar admissions, practice areas, contact infofind_lawyer_by_nameLook up a lawyer by name to verify they exist and are licensed.
"Is there a lawyer named Jane Smith in New York?"
→ Matching profiles with disambiguationmatch_lawyer_to_matterDescribe a legal issue in plain English; receive ranked attorney matches.
"My landlord won't return my deposit in Brooklyn"
→ Classified to Landlord–Tenant / Consumer law → ranked NY tenant attorneysget_legal_cost_estimateEstimated fee ranges by billing model (hourly, flat, contingency), adjusted for case complexity and region.
get_practice_areasList all available practice areas with lawyer counts.
get_jurisdictionsList U.S. states and territories with coverage numbers.
Transport | Use case |
stdio | Local clients (Claude Desktop, Cursor, VS Code) — |
Streamable HTTP | Remote clients, hosted at |
The hosted endpoint is open for unauthenticated read access on the free tier. Bring an API key (Bearer token) for higher limits and bulk export.
Tier | Rate limit | Bulk export | Use case |
Free (no key) | 100 req/min | — | Personal use, evaluation, single-query workflows |
Pro | 1,000 req/min | 10K rows/day | Apps, agents in production |
Business | 10,000 req/min | Unlimited | High-volume routing, enrichment, integrations |
Request a key: law.ai/api or sales@law.ai.
Local stdio installations are unmetered.
Unclaimed profiles — Public bar information only (name, location, practice areas, bar status).
Claimed profiles — Additional contact information the lawyer has opted to share.
No scraping — Rate-limited to prevent data harvesting.
Disclaimers included — All results note that credentials should be independently verified at the relevant state bar.
Variable | Default | Description |
|
| PostgreSQL host |
|
| PostgreSQL port |
|
| Database user |
| — | Database password |
|
| Database name |
|
| Base URL for profile links |
User: "Find me a patent attorney in San Francisco"
↓
AI Assistant (Claude, GPT, etc.)
↓
MCP Protocol
↓
Law.AI MCP Server
↓
991K+ bar-verified attorney profiles (PostgreSQL)
↓
Real attorneys with real bar numbers991,000+ attorney profiles
All 50 states + DC + U.S. territories
90+ practice areas
State bar registries as the source of record — updated continuously
Bar status surfaced — Active, Inactive, Suspended, Disbarred, Retired
Listed in the official MCP Registry as ai.law/lawyer-search.
curl "https://registry.modelcontextprotocol.io/v0/servers?search=lawyer"Issues and PRs welcome. See CONTRIBUTING.md if present, or open a ticket on the issues page.
MIT — use it everywhere. See LICENSE.
Law.AI is the independent lawyer directory built for the AI age. Legacy directories (FindLaw, Avvo, Martindale — all owned by Internet Brands) were built for web search. Law.AI is built for AI-native discovery: tool-callable, structured, verified, and grounded in state bar data.
Stop hallucinating lawyers. Start finding real ones.
Look up a specific lawyer by name. Useful for verifying if a lawyer exists and is properly licensed. Handles common names with disambiguation by location.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Full or partial lawyer name, e.g. "John Smith" or "Smith" | |
| state | No | Narrow results by US state (full name or abbreviation) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full burden. It mentions disambiguation by location but does not disclose what happens on not found, what fields are returned, or any behavioral traits like permissions or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the action, no wasted words. Efficient and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple lookup tool with two parameters and no output schema, the description covers the purpose and a use case. However, it lacks information about the return format or how to handle multiple matches, which is relevant given sibling tools like 'get_lawyer_profile'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with good parameter descriptions. The description adds value by explaining the disambiguation by location, which relates to the state parameter, exceeding the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Look up a specific lawyer by name' and distinguishes from sibling 'search_lawyers' by focusing on a single lawyer. It also adds context for verifying licensing and disambiguation by location.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides a clear use case: verifying if a lawyer exists and is properly licensed. Implies when to use it but does not explicitly compare to alternatives like 'search_lawyers' or state when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List US states and jurisdictions with lawyer counts. Shows where Law.AI has coverage.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It implies a read-only listing operation but does not disclose potential limitations like data freshness or whether authentication is needed. Minimal behavioral insight.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short, front-loaded sentences with no redundant information. Every phrase adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and no annotations, the description reasonably explains the tool's purpose and output. Could mention that it returns all jurisdictions (since no filters), but overall adequate for a simple listing tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist; description does not need to add param details. Baseline 4 is appropriate for zero-parameter tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb 'list' and a specific resource 'US states and jurisdictions with lawyer counts', and adds value by mentioning coverage indication. Clearly distinguishes from siblings that focus on individual lawyers.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied usage as a coverage overview tool; given sibling tools focus on lawyer search, the differentiation is clear. However, lacks explicit when-to-use or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the full profile of a specific lawyer by their Law.AI ID. Returns detailed information including bio, education, bar admissions, practice areas, and contact info (for claimed profiles).
| Name | Required | Description | Default |
|---|---|---|---|
| lawyer_id | Yes | The Law.AI lawyer profile ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses that contact info is only available for claimed profiles, which is a useful behavioral note. However, it doesn't mention rate limits, authentication, or other behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loading the main purpose and then listing returned fields. Every part is necessary, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple profile retrieval tool with one parameter and no output schema, the description covers purpose, return content (bio, education, etc.), and a conditional (contact info for claimed profiles). It is missing error scenarios, but overall fairly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes the single parameter as 'The Law.AI lawyer profile ID' with 100% coverage. The description adds 'Law.AI ID' but this is redundant; it does not provide additional meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'full profile of a specific lawyer', and the identifier ('by their Law.AI ID'). It distinguishes from siblings like search_lawyers and find_lawyer_by_name by specifying retrieval by unique ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage (need the lawyer ID) but does not explicitly state when not to use it or mention alternatives like find_lawyer_by_name for name-based lookup. The sibling list provides context, but the description lacks direct guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get estimated legal costs for a type of legal issue. Returns fee ranges by billing structure (hourly, flat fee, contingency), adjusted for case complexity and region. Complexity is the primary cost driver.
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | US state for regional pricing adjustment | |
| complexity | No | Case complexity — primary cost driver. simple: uncontested/routine, moderate: standard (default), complex: contested/litigation, high_stakes: trial/federal/appeal | |
| description | No | Brief description of the issue — used to auto-classify complexity if not specified | |
| practice_area | Yes | Practice area, e.g. "Criminal Defense", "Family Law", "Personal Injury" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool returns estimated fee ranges adjusted by complexity and region, and that complexity is the primary cost driver. However, it does not discuss limitations, authentication requirements, or the reliability of estimates.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. The first sentence front-loads the purpose, and the second adds crucial detail about billing structures and cost drivers.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the description explains the inputs and general outputs, it lacks an output schema and does not fully specify the return format (e.g., structure of fee ranges). For a tool with 4 parameters and no output schema, more detail on the response would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and each parameter has a description. The description adds minimal extra value beyond the schema, only emphasizing that complexity is the primary cost driver. Baseline is 3 for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get estimated legal costs for a type of legal issue.' It specifies outputs (fee ranges by billing structure) and distinguishes from sibling tools which focus on lawyer profiles and searches.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool (cost estimation) versus siblings (lawyer-related tasks). However, it does not explicitly state when not to use it or mention alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all practice areas available in the Law.AI directory with lawyer counts. Useful for discovering what types of lawyers are available.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations; description discloses that it lists practice areas with counts, but omits potential behavioral traits like auth requirements or response structure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with action and result, no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Sufficient for a simple list-all tool with no params and no output schema; could mention sorting or filtering, but not required.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters; schema coverage is 100% trivially. Description adds context (lawyer counts) beyond empty schema, but baseline is adequate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb 'list' and resource 'practice areas' with added detail 'with lawyer counts'. Distinguishes from sibling tools that search for specific lawyers or profiles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Mentions usefulness for discovering types of lawyers, but lacks explicit when-not-to-use or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Describe a legal issue in plain English and get matched with relevant lawyers. The tool classifies the issue into practice areas and returns ranked lawyer matches based on relevance, credentials, and location.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of matches to return (default 5, max 20) | |
| budget | No | Budget level: "low", "medium", or "high" | |
| urgency | No | How urgent: "low", "medium", or "high" | |
| location | No | Where the issue is — state name/code, or "City, State" format, e.g. "Texas" or "Houston, TX" | |
| description | Yes | Plain-English description of the legal issue, e.g. "My landlord won't return my security deposit" or "I was injured in a car accident" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool classifies the issue into practice areas and returns ranked matches, but does not mention side effects, auth needs, rate limits, or behavior when no match is found. This is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, concise and to the point. Every word contributes to understanding, with no filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 parameters and no output schema, the description covers the purpose and process but lacks details on the output format, such as what fields the matches contain or how to interpret the ranking. It is adequate for a straightforward match tool but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds minimal extra meaning beyond the schema's parameter descriptions. It states the overall process but does not enhance individual parameter semantics, such as what 'budget' or 'urgency' values mean in context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: describe a legal issue and get matched with relevant lawyers. It specifies classification into practice areas and ranking by relevance, credentials, and location, distinguishing it from sibling tools like search_lawyers or find_lawyer_by_name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for matching based on a legal issue, but does not explicitly state when to use this vs alternatives. It lacks guidance on when not to use it or what specific scenarios it is best suited for, though sibling tools provide context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Law.AI directory of 537,000+ verified lawyer profiles. Filter by practice area, state, city, and bar status. Returns ranked results with claimed/verified profiles first.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | City name, e.g. "Chicago", "Houston" | |
| limit | No | Number of results (default 10, max 50) | |
| state | No | US state — full name or abbreviation, e.g. "California" or "CA" | |
| offset | No | Pagination offset | |
| bar_status | No | Bar status filter: "Active" (default), "Inactive", or "Any" | |
| practice_area | No | Practice area to search for, e.g. "Criminal Defense", "Personal Injury", "Family Law" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states that results are ranked with claimed/verified profiles first, which is useful. However, it does not detail other behaviors such as default sorting order, whether partial matching is applied, or pagination behavior beyond parameter definitions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that front-load the tool's action and resource, include key filtering options, and mention the ranking behavior. Every phrase adds value, with no redundancy or wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 6 parameters, no output schema, and no annotations, the description covers the essential aspects: directory size, filtering options, and ranking. It lacks details on edge cases (e.g., empty results) or precise ordering, but for a search tool it provides sufficient context for an agent to understand its basic behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds marginal value by mentioning specific filterable parameters and providing example values (e.g., 'Criminal Defense' for practice_area). It does not elaborate on offset/limit further, but the schema already defines them clearly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: searching the Law.AI directory of verified lawyer profiles. It explicitly lists filtering dimensions (practice area, state, city, bar status) and mentions ranking behavior, distinguishing it from siblings like get_lawyer_profile (individual profile lookup) and find_lawyer_by_name (name-based search).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context by specifying when to use the tool (when filtering by practice area, state, city, bar status is needed). It implies this is the primary search tool for directory lookups. However, it does not explicitly mention when not to use it or list alternatives, though sibling tools are available for reference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.2.1find_lawyer_by_nameget_jurisdictionsget_lawyer_profileget_legal_cost_estimateget_practice_areasmatch_lawyer_to_mattersearch_lawyersEach tool has a clearly distinct purpose: searching, profiling, name lookup, practice areas, jurisdictions, natural language matching, and cost estimation. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., search_lawyers, get_lawyer_profile). No deviations.
7 tools is well-scoped for a legal directory and matching service, covering search, profile, lookup, metadata, matching, and cost estimates without being too many or too few.
The tool set comprehensively covers the domain: finding lawyers by search, name, or natural language; retrieving profiles; exploring practice areas and jurisdictions; and estimating costs. No obvious gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search U.S. case law, fetch opinions, and ask matter-aware legal questions over your documents.
Connect AI to millions of laws and court cases with the Lawstronaut MCP.
Verified, citable German & EU law for any LLM. Daily updates from official sources, hosted in DE.
Verified, citable German & EU law for any LLM. Daily updates from official sources, hosted in DE.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/risk-ai/lawai-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
