Contextual MCP Server

Instructions

Implementation Reference

• multi-agent/server.py:10-44 (handler)

  Handler for the 'query' MCP tool. Reranks available agents by relevance to the user prompt and queries the most relevant agent using the ContextualAI client.

  @mcp.tool()
  def query(prompt: str) -> str:
      """An enterprise search tool that can answer questions about any sort of knowledge base"""
  
      client = ContextualAI(
          api_key=API_KEY,  # This is the default and can be omitted
      )
  
      instruction = "Rank documents based on their ability to answer the question/query"
  
      agents = {}
      for agent in client.agents.list():
          agents.update({agent.id: f"{agent.name} - {agent.description}"})
      documents = list(agents.values())
  
      results = client.rerank.create(
          model="ctxl-rerank-en-v1-instruct",
          instruction=instruction,
          query=prompt,
          documents=documents,
          metadata=metadata,
          top_n=1
      )
  
      agent_index = results.results[0].index
      agent_id = list(agents.keys())[agent_index]
  
      query_result = client.agents.query.create(
          agent_id=agent_id,
          messages=[{
              "content": prompt,
              "role": "user"
          }]
      )
      return query_result.message.content

• single_agent/server.py:11-24 (handler)

  Handler for the 'query' MCP tool. Directly queries a predefined specific agent using the ContextualAI client.

  @mcp.tool()
  def query(prompt: str) -> str:
      """An enterprise search tool that can answer questions about a specific knowledge base"""
      client = ContextualAI(
          api_key=API_KEY,  # This is the default and can be omitted
      )
      query_result = client.agents.query.create(
          agent_id=AGENT,
          messages=[{
              "content": prompt,
              "role": "user"
          }]
      )
      return query_result.message.content