Non-Streaming End-to-End MCP Tool Use with an AI Model

See more AI Examples

Demonstrates Ai.UseMcp in a complete, non-streaming Model Context Protocol (MCP) workflow. The example connects to an MCP server, registers the server's tools with an AI model via UseMcp, and asks a question the model can only answer well by calling one of those tools. When the model requests a tool, Chilkat automatically calls it on the MCP server, feeds the result back into the conversation, and continues — all inside a single (non-streaming) Ask.

Tip: Code to parse the returned JSON can be generated with Chilkat's online tool at https://tools.chilkat.io/jsonParse.

llSuccess = .F.

//  Non-streaming, end-to-end MCP example.  It connects to an MCP server, hands the server's tools to
//  an AI model via Ai.UseMcp, and asks a question that the model can only answer by calling one of
//  those tools.  When the model requests a tool, Chilkat automatically calls it on the MCP server,
//  feeds the result back into the conversation, and continues -- all inside a single (non-streaming)
//  Ask.
//  
//  The MCP server used here is DeepWiki: a free, public, no-authentication Streamable HTTP server
//  that answers questions about public GitHub repositories.  Swap in any MCP server URL; if it
//  requires a bearer token, set mcp.AuthToken before Connect.

//  1) Connect to the MCP server.
loMcp = createobject("CkMcp")
//  mcp.AuthToken = "...";   // <-- only if the server requires a bearer token
llSuccess = loMcp.Connect("https://mcp.deepwiki.com/mcp")
if (llSuccess = .F.) then
    ? loMcp.LastErrorText
    release loMcp
    return
endif

? "Connected to MCP server: " + loMcp.ServerName + " (version " + loMcp.ServerVersion + ")"

//  (Optional) Show the tools the server advertises.  This is the same set of tools Chilkat registers
//  with the model in the UseMcp call below.
loToolsJson = createobject("CkJsonObject")
loToolsJson.EmitCompact = .F.
llSuccess = loMcp.ListTools(loToolsJson)
if (llSuccess = .T.) then
    ? "Available MCP tools:"
    ? loToolsJson.Emit()
    ? "----"
endif

//  2) Set up the AI conversation and register the MCP tools.
loAi = createobject("CkAi")
loAi.Provider = "anthropic"
//  The API key should come from a secure source rather than being hard-coded.
loAi.ApiKey = "AI_PROVIDER_API_KEY"
loAi.Model = "claude-sonnet-5"
loAi.VerboseLogging = .T.

//  Automatic tool use (MCP or JavaScript) requires a conversation -- it cannot be used with a
//  stateless query, so create one with NewConvo.
llSuccess = loAi.NewConvo("test_conversation","You are a helpful assistant.  Use the available tools when they can help answer the question.","")
if (llSuccess = .F.) then
    ? loAi.LastErrorText
    release loMcp
    release loToolsJson
    release loAi
    return
endif

//  Register the connected server's tools with the model.  Each tool name is namespaced with the
//  "deepwiki" prefix so that tools from different servers (and JavaScript tools) can never collide --
//  e.g. "deepwiki_ask_question".  The Mcp object must stay connected and in scope for as long as its
//  tools are in use during the conversation.
llSuccess = loAi.UseMcp(loMcp,"deepwiki")
if (llSuccess = .F.) then
    ? loAi.LastErrorText
    release loMcp
    release loToolsJson
    release loAi
    return
endif

//  Multiple MCP servers can be used in the same conversation.  Connect each server and call
//  UseMcp once per server, giving each a distinct prefix so their tool names cannot collide.

//  A prompt the model can only answer well by calling one of the MCP tools.
llSuccess = loAi.InputAddText('Use the available tools to look up the GitHub repository "modelcontextprotocol/modelcontextprotocol", then give me a brief, sourced summary of which transports the Model Context Protocol defines.')
if (llSuccess = .F.) then
    ? loAi.LastErrorText
    release loMcp
    release loToolsJson
    release loAi
    return
endif

//  3) Non-streaming Ask.  Any MCP tool the model requests is executed automatically inside this call
//  (Chilkat -> Mcp.CallTool -> result back into the transcript -> continue), so Ask returns only once
//  the model produces its final answer.
llSuccess = loAi.Ask("text")
if (llSuccess = .F.) then
    ? loAi.LastErrorText
    release loMcp
    release loToolsJson
    release loAi
    return
endif

//  The final assistant answer (after any automatic tool calls).
loSbResponse = createobject("CkStringBuilder")
llSuccess = loAi.GetOutputTextSb(loSbResponse)
if (llSuccess = .F.) then
    ? loAi.LastErrorText
    release loMcp
    release loToolsJson
    release loAi
    release loSbResponse
    return
endif

? "Assistant answer:"
? loSbResponse.GetAsString()
? "----"

//  (Optional) Dump the full transcript, which now includes the tool call and the tool result that
//  were added automatically.
loConvoJson = createobject("CkJsonObject")
loConvoJson.EmitCompact = .F.
llSuccess = loAi.ExportConvo("test_conversation",loConvoJson)
if (llSuccess = .F.) then
    ? loAi.LastErrorText
    release loMcp
    release loToolsJson
    release loAi
    release loSbResponse
    release loConvoJson
    return
endif

? "Full Conversation:"
? loConvoJson.Emit()

//  4) Close the MCP session (best effort; releases the server-side session).
llSuccess = loMcp.Close()
if (llSuccess = .F.) then
    ? loMcp.LastErrorText
    release loMcp
    release loToolsJson
    release loAi
    release loSbResponse
    release loConvoJson
    return
endif



release loMcp
release loToolsJson
release loAi
release loSbResponse
release loConvoJson