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

See more AI Examples

Demonstrates Ai.UseMcp in a streaming Model Context Protocol (MCP) workflow. This is the same idea as the non-streaming MCP example, but the answer is streamed token-by-token and the automatic MCP tool call is driven by the application's event loop rather than happening invisibly inside Ask.

A tool-using conversation spans more than one streamed turn. In the first turn the model streams a js_function_call event; the example hands that event's JSON to StreamingJsToolCall, which routes MCP tools to the server and appends the result to the transcript, and the turn ends with null_terminator. The example then calls Ask again (with no new input, since the tool result is already in the transcript) so the model can continue and stream its final answer. The loop ends when a streamed turn finishes with no tool call outstanding.

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

Dim success As Boolean
success = False

//  Streaming, end-to-end MCP example.  Same idea as the non-streaming MCP example, but the answer is
//  streamed token-by-token, and the automatic MCP tool call is driven by the application's event loop
//  instead of happening invisibly inside Ask.
//  
//  A tool-using conversation spans more than one streamed turn:
//  
//    turn 1:  the model streams a "js_function_call" event (it wants a tool).  We hand that event's
//             JSON to StreamingJsToolCall, which routes MCP tools to the server (Mcp.CallTool) and
//             appends the result to the transcript.  The turn then ends with "null_terminator".
//    turn 2:  we call Ask again (no new input -- the tool result is already in the transcript) so the
//             model can continue.  It streams the final answer and ends with "null_terminator", with
//             no pending tool call.
//  
//  The loop ends when a streamed turn finishes with no tool call outstanding.
//  
//  MCP server: DeepWiki -- a free, public, no-authentication Streamable HTTP server that answers
//  questions about public GitHub repositories.  Swap in any URL; set mcp.AuthToken before Connect if
//  it needs a bearer token.

//  1) Connect to the MCP server.
Dim mcp As New Chilkat.Mcp
//  mcp.AuthToken = "...";   // <-- only if the server requires a bearer token
success = mcp.Connect("https://mcp.deepwiki.com/mcp")
If (success = False) Then
    System.DebugLog(mcp.LastErrorText)
    Return
End If

System.DebugLog("Connected to MCP server: " + mcp.ServerName + " (version " + mcp.ServerVersion + ")")

//  2) Set up the AI conversation and register the MCP tools.
Dim ai As New Chilkat.Ai
ai.Provider = "anthropic"
//  The API key should come from a secure source rather than being hard-coded.
ai.ApiKey = "AI_PROVIDER_API_KEY"
ai.Model = "claude-sonnet-5"

//  Automatic tool use requires a conversation (not a stateless query).
success = ai.NewConvo("test_conversation","You are a helpful assistant.  Use the available tools when they can help answer the question.","")
If (success = False) Then
    System.DebugLog(ai.LastErrorText)
    Return
End If

//  Namespace the server's tools with "deepwiki" -- e.g. "deepwiki_ask_question".  The Mcp object must
//  stay connected and in scope for the whole conversation.
success = ai.UseMcp(mcp,"deepwiki")
If (success = False) Then
    System.DebugLog(ai.LastErrorText)
    Return
End If

//  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.  For example:
//      success = ai.UseMcp(mcpWeather,"weather");
//      success = ai.UseMcp(mcpGitHub,"github");

success = ai.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 (success = False) Then
    System.DebugLog(ai.LastErrorText)
    Return
End If

//  3) Start streaming.
ai.Streaming = True
success = ai.Ask("text")
If (success = False) Then
    System.DebugLog(ai.LastErrorText)
    Return
End If

//  4) Drive the streaming event loop.
Dim sbEventName As New Chilkat.StringBuilder
Dim sbDelta As New Chilkat.StringBuilder
Dim sbFullResponse As New Chilkat.StringBuilder
Dim bConversationDone As Boolean
bConversationDone = False
Dim bToolCallPending As Boolean
bToolCallPending = False
Dim bCaseSensitive As Boolean
bCaseSensitive = True
Dim bAbort As Boolean
bAbort = False
Dim loopGuard As Int32
loopGuard = 0
Dim result As Int32
result = 0

While (bConversationDone <> True) And (loopGuard < 8000)
    loopGuard = loopGuard + 1
    result = ai.PollAi(bAbort)
    If (result < 0) Then
        System.DebugLog(ai.LastErrorText)
        Return
    End If

    If (result = 0) Then
        //  No event ready yet.
        ai.SleepMs 100
    Else
        success = ai.NextAiEvent(5000,sbEventName,sbDelta)
        If (success = False) Then
            System.DebugLog(ai.LastErrorText)
            Return
        End If

        If (sbEventName.ContentsEqual("js_function_call",bCaseSensitive) = True) Then
            //  (a) The model is requesting a tool call.  sbDelta holds the function-call JSON.
            //  StreamingJsToolCall runs the tool -- routing MCP tools to the server -- and appends the
            //  result to the transcript.  It must be called before this turn's null_terminator.
            System.DebugLog("[tool call requested]")
            System.DebugLog(sbDelta.GetAsString())
            success = ai.StreamingJsToolCall(sbDelta)
            If (success = False) Then
                System.DebugLog(ai.LastErrorText)
                Return
            End If

            bToolCallPending = True
        Else
            If (sbEventName.ContentsEqual("null_terminator",bCaseSensitive) = True) Then
                //  (c) This streamed turn has finished.
                If (bToolCallPending = True) Then
                    //  Continue the conversation so the model can use the tool result.  No new
                    //  InputAddText -- the tool result is already in the transcript.
                    bToolCallPending = False
                    success = ai.Ask("text")
                    If (success = False) Then
                        System.DebugLog(ai.LastErrorText)
                        Return
                    End If

                Else
                    bConversationDone = True
                End If

            Else
                //  (b) An "empty" event reports nothing this poll.  (d) Any other event is a normal
                //  streamed text delta, which we display and accumulate.
                If (sbEventName.ContentsEqual("empty",bCaseSensitive) <> True) Then
                    System.DebugLog("Event: " + sbEventName.GetAsString() + "  Delta: " + sbDelta.GetAsString())
                    success = sbFullResponse.AppendSb(sbDelta)
                End If

            End If

        End If

    End If

Wend

System.DebugLog("Final streamed response:")
System.DebugLog(sbFullResponse.GetAsString())
System.DebugLog("----")

//  (Optional) The full transcript, including the tool call and its result.
Dim convoJson As New Chilkat.JsonObject
convoJson.EmitCompact = False
success = ai.ExportConvo("test_conversation",convoJson)
If (success = False) Then
    System.DebugLog(ai.LastErrorText)
    Return
End If

System.DebugLog("Full Conversation:")
System.DebugLog(convoJson.Emit())

//  5) Close the MCP session.
success = mcp.Close()
If (success = False) Then
    System.DebugLog(mcp.LastErrorText)
    Return
End If