mcp-adapterUse Model Context Protocol servers to access external tools and data sources. Enable AI agents to discover and execute tools from configured MCP servers (legal databases, APIs, database connectors, weather services, etc.).
Install via ClawdBot CLI:
clawdbot install lunarpulse/mcp-adapterUse the MCP integration plugin to discover and execute tools provided by external MCP servers. This skill enables you to access legal databases, query APIs, search databases, and integrate with any service that provides an MCP interface.
The plugin provides a unified mcp tool with two actions:
list - Discover available tools from all connected serverscall - Execute a specific tool with parametersAlways start by listing available tools to see what MCP servers are connected and what capabilities they provide.
Action:
{
tool: "mcp",
args: {
action: "list"
}
}
Response structure:
[
{
"id": "server:toolname",
"server": "server-name",
"name": "tool-name",
"description": "What this tool does",
"inputSchema": {
"type": "object",
"properties": {...},
"required": [...]
}
}
]
For each tool, examine:
"server:toolname" - split on : to get server and tool namesproperties: Available parameters with types and descriptionsrequired: Array of mandatory parameter namesCommon tool naming patterns:
search_* - Find or search operations (e.g., search_statute, search_users)get_* - Retrieve specific data (e.g., get_statute_full_text, get_weather)query - Execute queries (e.g., database:query)analyze_* - Analysis operations (e.g., analyze_law)resolve_* - Resolve references (e.g., resolve_citation)Before calling a tool:
inputSchema.requiredAction:
{
tool: "mcp",
args: {
action: "call",
server: "<server-name>",
tool: "<tool-name>",
args: {
// Tool-specific parameters from inputSchema
}
}
}
Example - Korean legal search:
{
tool: "mcp",
args: {
action: "call",
server: "kr-legal",
tool: "search_statute",
args: {
query: "μ°μ₯κ·Όλ‘ μλΉ",
limit: 5
}
}
}
Tool responses follow this structure:
{
"content": [
{
"type": "text",
"text": "JSON string or text result"
}
],
"isError": false
}
For JSON responses:
const data = JSON.parse(response.content[0].text);
// Access data.result, data.results, or direct properties
For complex requests, execute multiple tools in sequence:
Example - Legal research workflow:
search_statute to find relevant lawsget_statute_full_text for complete textanalyze_law for interpretationsearch_case_law for related casesEach step uses output from the previous step to inform the next call.
Between tool calls:
"Tool not found: server:toolname"
action: "list" to verify available tools"Invalid arguments for tool"
inputSchema from list response"Server connection failed"
Errors return:
{
"content": [{"type": "text", "text": "Error: message"}],
"isError": true
}
Handle gracefully:
{tool: "mcp", args: {action: "list"}}
Response shows kr-legal:search_statute with:
query (string)limit (number), category (string){
tool: "mcp",
args: {
action: "call",
server: "kr-legal",
tool: "search_statute",
args: {
query: "μ°μ₯κ·Όλ‘ μλΉ",
category: "λ
Έλλ²",
limit: 5
}
}
}
const data = JSON.parse(response.content[0].text);
// Present data.results to user
User-facing response:
Found 5 Korean statutes about overtime pay:
1. κ·Όλ‘κΈ°μ€λ² μ 56μ‘° (μ°μ₯Β·μΌκ° λ° ν΄μΌ κ·Όλ‘)
- Overtime work requires 50% premium
2. κ·Όλ‘κΈ°μ€λ² μ 50μ‘° (κ·Όλ‘μκ°)
- Standard working hours: 40 hours per week
Would you like me to retrieve the full text of any statute?
{tool: "mcp", args: {action: "list"}}
{
tool: "mcp",
args: {
action: "call",
server: "server-name",
tool: "tool-name",
args: {param1: "value1"}
}
}
Tool ID parsing: "server:toolname" β split on : for server and tool names
Parameter validation: Check inputSchema.required and inputSchema.properties[param].type
Response parsing: JSON.parse(response.content[0].text) for JSON responses
Error detection: Check response.isError === true
Remember: Always start with action: "list" when uncertain about available tools.
Generated Mar 1, 2026
Law firms can use MCP servers connected to legal databases to quickly search statutes, retrieve full texts, and analyze case law. This automates preliminary research, saving hours of manual work for attorneys and paralegals.
Logistics companies integrate MCP weather services to monitor real-time conditions and forecast disruptions along shipping routes. This enables proactive rerouting and scheduling adjustments to minimize delays and reduce operational costs.
Support teams use MCP servers to query customer databases and external APIs, pulling order histories and service records during live chats. This provides agents with instant context to resolve issues faster and improve customer satisfaction.
Healthcare providers connect MCP servers to medical databases for retrieving patient records, drug interactions, and clinical guidelines. This supports doctors in making informed decisions during consultations while ensuring data security.
Investment firms leverage MCP servers to access real-time market data APIs and execute analytical tools for trend analysis. This helps analysts generate reports and identify opportunities without switching between multiple platforms.
Offer the MCP integration as a cloud-based service with tiered subscriptions based on server connections and tool usage. This provides recurring revenue from businesses needing scalable access to external data sources.
Sell on-premise licenses to large corporations for integrating proprietary MCP servers with internal systems. This includes customization, support, and training services for seamless deployment.
Operate a marketplace where developers publish MCP servers for specific industries, taking a commission on transactions. This fosters an ecosystem of tools while generating revenue from each tool call or server subscription.
π¬ Integration Tip
Start by listing available tools to understand server capabilities, then validate parameters against input schemas to avoid errors during execution.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection