Outils

Transmettez tools au moment de la création, de la mise à jour ou de l'appel :

tools = [
    # MCP server
    {
        "type": "remote_mcp",
        "name": "exa",
        "config": {"remoteMcp": {"url": "https://mcp.exa.ai/mcp"}},
    },
    # MCP server with authentication headers (plain text)
    {
        "type": "remote_mcp",
        "name": "my-private-mcp",
        "config": {"remoteMcp": {
            "url": "https://mcp.example.com/api",
            "headers": {"Authorization": "Bearer <your-token>"}
        }},
    },
    # MCP server with API key stored in AgentCore Identity Token Vault.
    # Use ${arn:...} to reference a credential provider - the ARN is resolved
    # to the actual API key at invocation time.
    {
        "type": "remote_mcp",
        "name": "exa-secure",
        "config": {"remoteMcp": {
            "url": "https://mcp.exa.ai/mcp",
            "headers": {"x-api-key": "${arn:aws:bedrock-agentcore:us-west-2:123456789012:token-vault/default/apikeycredentialprovider/my-exa-key}"}
        }},
    },
    # For managed credential rotation and OAuth-protected tools, put your MCP server
    # behind AgentCore Gateway and use AgentCore Identity instead of raw headers.
    #
    # AgentCore Gateway with SigV4 auth (default)
    {
        "type": "agentcore_gateway",
        "name": "my-gateway",
        "config": {"agentCoreGateway": {"gatewayArn": "arn:aws:bedrock-agentcore:us-west-2:123456789012:gateway/my-gateway"}},
    },
    # AgentCore Gateway with OAuth auth
    {
        "type": "agentcore_gateway",
        "name": "my-oauth-gateway",
        "config": {"agentCoreGateway": {
            "gatewayArn": "arn:aws:bedrock-agentcore:us-west-2:123456789012:gateway/my-oauth-gateway",
            "outboundAuth": {"oauth": {
                "credentialProviderName": "my-oauth-provider",
                "scopes": ["read", "write"]
            }}
        }},
    },
    # AgentCore Browser
    {"type": "agentcore_browser", "name": "browser"},
    # AgentCore Code Interpreter
    {"type": "agentcore_code_interpreter", "name": "code_interpreter"},
    # Inline function - executes on the client side, not on the harness VM.
    # When the agent calls this tool, the call is returned to your code for handling.
    {
        "type": "inline_function",
        "name": "approve_purchase",
        "config": {
            "inlineFunction": {
                "description": "Request human approval for a purchase.",
                "inputSchema": {
                    "type": "object",
                    "properties": {
                        "item": {"type": "string"},
                        "amount": {"type": "number"},
                    },
                    "required": ["item", "amount"],
                },
            }
        },
    },
]

response = client.invoke_harness(
    harnessArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    tools=tools,
    messages=[{"role": "user", "content": [{"text": "Find a mechanical keyboard under $200 and request approval."}]}],
)

Lorsque vous créez un nouveau harnais de manière interactive, l'agentcore add harnessassistant vous permet de sélectionner des outils. Pour ajouter des outils via la CLI, utilisez agentcore add tool après avoir créé le harnais :

# Add a remote MCP server
agentcore add tool --harness my-agent --type remote_mcp \
  --name exa --url https://mcp.exa.ai/mcp

# Create a harness with a remote MCP server and request headers.
# Use ${arn:...} syntax to reference a credential provider.
agentcore add harness \
  --name secure_agent \
  --model-provider bedrock \
  --model-id us.anthropic.claude-sonnet-4-5-20250514-v1:0 \
  --tools remote_mcp \
  --mcp-name exa-secure \
  --mcp-url https://mcp.exa.ai/mcp \
  --mcp-headers '{"x-api-key":"${arn:aws:bedrock-agentcore:us-west-2:123456789012:token-vault/default/apikeycredentialprovider/my-exa-key}"}'

# Add Browser
agentcore add tool --harness my-agent --type agentcore_browser --name browser

# Add Code Interpreter
agentcore add tool --harness my-agent --type agentcore_code_interpreter --name code-interpreter

# Add Gateway by ARN
agentcore add tool --harness my-agent --type agentcore_gateway \
  --name my-gateway --gateway-arn arn:aws:bedrock-agentcore:us-west-2:123456789012:gateway/my-gateway

# Add Gateway by project-local name
agentcore add tool --harness my-agent --type agentcore_gateway \
  --name my-gateway --gateway my-gateway

# Add an inline function tool (executes client-side, not on the harness VM)
agentcore add tool --harness my-agent --type inline_function \
  --name approve_purchase \
  --description "Request human approval for a purchase" \
  --input-schema '{"type": "object", "properties": {"item": {"type": "string"}, "amount": {"type": "number"}}, "required": ["item", "amount"]}'

Déployez pour postuler.

Remplacez les outils sur une seule invocation :

agentcore invoke --harness research-agent --tools agentcore_browser "Find the latest news on AI agents"

Exécutez agentcore dans un répertoire de projet, sélectionnez Ajouter, choisissez Harness, puis passez aux paramètres avancés. Activez Outils avec espace, puis appuyez sur Entrée.

Exécutez ensuite agentcore deploy pour postuler.

Attachez la passerelle au moment de la création (ou tools transmettezupdate_harness/invoke_harness) :

tools = [
    {
        "type": "agentcore_gateway",
        "name": "web-search",
        "config": {"agentCoreGateway": {
            "gatewayArn": "arn:aws:bedrock-agentcore:us-east-1:123456789012:gateway/my-web-search-gateway",
            "outboundAuth": {"awsIam": {}}
        }},
    },
]

client.create_harness(
    harnessName="research-agent",
    executionRoleArn="arn:aws:iam::123456789012:role/MyHarnessRole",
    tools=tools,
)

Les outils de la passerelle sont désormais à la disposition de l'agent. Invoquez le harnais avec une invite qui nécessite des informations à jour :

response = client.invoke_harness(
    harnessArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    messages=[{"role": "user", "content": [{"text": "Search the web for the latest AWS announcements and cite your sources."}]}],
)

# Attach the web-search gateway to your harness
agentcore add tool --harness research-agent --type agentcore_gateway \
  --name web-search \
  --gateway-arn arn:aws:bedrock-agentcore:us-east-1:123456789012:gateway/my-web-search-gateway

# Deploy, then invoke
agentcore deploy
agentcore invoke --harness research-agent "Search the web for the latest AWS announcements and cite your sources."

Transmettez un outil de fonction en ligne au moment de l'invocation :

# 1. Invoke with an inline function tool
response = client.invoke_harness(
    harnessArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    tools=[{
        "type": "inline_function",
        "name": "get_weather",
        "config": {"inlineFunction": {
            "description": "Get the current weather for a city.",
            "inputSchema": {
                "type": "object",
                "properties": {"city": {"type": "string"}},
                "required": ["city"]
            }
        }}
    }],
    messages=[{"role": "user", "content": [{"text": "What's the weather in Seattle?"}]}],
)

# 2. The agent calls the tool - capture the toolUseId and input from the stream
tool_use_id = None
tool_name = None
tool_input = None
for event in response["stream"]:
    if "contentBlockStart" in event:
        start = event["contentBlockStart"].get("start", {})
        if "toolUse" in start and start["toolUse"].get("name") == "get_weather":
            tool_use_id = start["toolUse"]["toolUseId"]
            tool_name = start["toolUse"]["name"]
    if "contentBlockDelta" in event:
        delta = event["contentBlockDelta"].get("delta", {})
        if "toolUse" in delta:
            tool_input = (tool_input or "") + delta["toolUse"].get("input", "")

# 3. Execute the tool yourself and send the result back
# Include the assistant's toolUse message followed by your toolResult
client.invoke_harness(
    harnessArn=HARNESS_ARN,
    runtimeSessionId=SESSION_ID,
    messages=[
        {
            "role": "assistant",
            "content": [{"toolUse": {"toolUseId": tool_use_id, "name": tool_name, "input": json.loads(tool_input)}}],
        },
        {
            "role": "user",
            "content": [{
                "toolResult": {
                    "toolUseId": tool_use_id,
                    "content": [{"text": "72°F, partly cloudy"}],
                    "status": "success",
                }
            }],
        },
    ],
)

L'agent reprend le raisonnement à partir du résultat de l'outil et diffuse la réponse finale.

Ajoutez un outil fonctionnel intégré à un harnais :

agentcore add tool --harness my-agent --type inline_function \
  --name get_weather

Définissez ensuite la description et le schéma de saisie dans app/my-agent/harness.json :

{
  "type": "inline_function",
  "name": "get_weather",
  "config": {
    "inlineFunction": {
      "description": "Get the current weather for a city.",
      "inputSchema": {
        "type": "object",
        "properties": { "city": { "type": "string" } },
        "required": ["city"]
      }
    }
  }
}

Courez agentcore deploy pour postuler. Lorsque l'agent appelle la fonction en ligne pendant une invocation, le TUI fait une pause et vous invite à fournir le résultat de l'outil en ligne. En mode non interactif (CLI), le flux revient avec stopReason: "tool_use" et vous renvoyez le résultat avec un appel d'appel de suivi.