561 pages for mcp serve.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
sdk
Claude Developer Platform · in the page
manage-claude/opentelemetry/sdk
…current span. Some MCP client libraries send the trace context to the MCP server in `_meta`, so a server that reads it can add its spans to your trace under that tool span. The Python `mcp` package fr…
plugins-api
Claude Developer Platform · in the page
manage-claude/plugins-api
…an event occurs in a session, such as before Claude uses a tool. | | MCP server | A connection from Claude to tools and data in another system (Model Context Protocol). | | CLI…
agent-setup
Claude Developer Platform · in the page
managed-agents/agent-setup
…persona and capabilities. It bundles the model, system prompt, tools, MCP servers, and skills that shape how Claude behaves during a session. Create the agent once as a reusable resource and referenc…
choosing-an-environment
Claude Developer Platform · in the page
managed-agents/choosing-an-environment
…ide your network. Anthropic, not your worker, connects to the agent's MCP servers. A private one might be in front of your internal ticket system or company wiki. To reach it, you can use an [MCP tunn…
environments
Claude Developer Platform · in the page
managed-agents/environments
…: `AllowMcpServers`; go: `AllowMCPServers`) allows outbound access to MCP server endpoints configured on the agent, beyond those listed in the `allowed_hosts` (java, php: `allowedHosts`; csharp, go: `…
github
Claude Developer Platform · in the page
managed-agents/github
…nd session resources First, create an agent that declares the GitHub MCP server. The agent definition holds the server URL but no authentication token: <CodeGroup defaultLanguage="CLI"> ```bash cU…
mcp-connector
Claude Developer Platform · in the page
managed-agents/mcp-connector
….claude.com/docs/en/managed-agents/mcp-connector description: Connect MCP servers to your agents for access to external tools and data sources. featureMetadata: topic: title: Managed Agents…
multiagent-orchestration
Claude Developer Platform · in the page
managed-agents/multiagent-orchestration
…`) block. It uses its own configuration: model, system prompt, tools, MCP servers, and skills. * **Inline agent:** An agent that is not saved. The agent that the session runs, or a workflow, defines i…
onboarding
Claude Developer Platform · in the page
managed-agents/onboarding
…Pick a model and write the system prompt in a full-width editor. * **MCP servers:** Add remote MCP servers by URL and authenticate your agent to take action on your behalf. * **Tools:** Extend your a…
overview
Claude Developer Platform · in the page
managed-agents/overview
…-------------- | | **Agent** | The model, system prompt, tools, MCP servers, and skills | | **Environment** | Configuration f…
permission-policies
Claude Developer Platform · in the page
managed-agents/permission-policies
…sets default to `always_ask`. This ensures that new tools added to an MCP server do not run in your application without approval. To auto-approve tools from a trusted MCP server, set `default_config.p…
quickstart
Claude Developer Platform · in the page
managed-agents/quickstart
…-------------- | | **Agent** | The model, system prompt, tools, MCP servers, and skills | | **Environment** | Configuration f…
reference
Claude Developer Platform · in the page
managed-agents/reference
…nce description: Event types, self-hosted worker CLI flags, supported MCP server types, rate limits, and branding guidelines for Claude Managed Agents. featureMetadata: topic: title: Managed Age…
secure-deployment
Claude Developer Platform · in the page
managed-agents/secure-deployment
…on its traffic in your own firewall. Your firewall does not limit the MCP servers an agent declares, so review them, and any that your application sets for a session. * **Web tools:** The web tools ru…
secure-deployment-risks
Claude Developer Platform · in the page
managed-agents/secure-deployment-risks
…do not limit them. The settings do not secure your custom tools, your MCP servers, or your self-hosted infrastructure. ## What the sandbox can and cannot do Managed Agents keeps the agent loop, sess…
spawn.sh: called once per claimed work item
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes
…agents-and-tools/mcp-tunnels/overview) control *how Anthropic reaches MCP servers in your network*. They are independent: a session running in Anthropic's cloud sandboxes can still reach private MCP s…
self-hosted-sandboxes-custom-tools
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-custom-tools
…on: Serve custom tools from a self-hosted sandbox worker, and wrap an MCP server inside your network as custom tools without running a tunnel. featureMetadata: topic: title: Managed Agents u…
self-hosted-sandboxes-memory
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-memory
…ng from it. Changes made through `bash`, or through a custom tool or MCP server you serve from the sandbox, are not blocked locally. They are never synced to the store, and the next remote change to…
self-hosted-sandboxes-operations
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-operations
…hangs Without a timeout on the MCP client, a hung call to a [wrapped MCP server](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-custom-tools#wrap-an-mcp-server-as-custom-too…
self-hosted-sandboxes-security
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-security
…ude.com/docs/en/managed-agents/self-hosted-sandboxes-custom-tools) or MCP servers you serve from the sandbox, which run with the worker's permissions. Later tool calls in that session read the changed…
sessions
Claude Developer Platform · in the page
managed-agents/sessions
…es within the session, including the model, system prompt, tools, and MCP servers. See [Define your agent](https://platform.claude.com/docs/en/managed-agents/agent-setup) for details. </Tip> ### Set…
tools
Claude Developer Platform · in the page
managed-agents/tools
…which uses them to continue the task. To give the agent tools from an MCP server, use the [MCP connector](https://platform.claude.com/docs/en/managed-agents/mcp-connector) instead. ## Available tools…
vaults
Claude Developer Platform · in the page
managed-agents/vaults
…gress. <Tabs> <Tab title="MCP OAuth"> Use `mcp_oauth` when the MCP server uses OAuth 2.0. If you supply a `refresh` (csharp, go: `Refresh`) block, Anthropic refreshes the access token on your b…
workflow-runs
Claude Developer Platform · in the page
managed-agents/workflow-runs
…r. When something the session depends on fails, such as the model, an MCP server, credentials, or billing, the failing thread's stream gets a `session.error`. That doesn't end a run by itself. But if…
overview
Claude Developer Platform · in the page
release-notes/overview
…: "agent_with_overrides"` to replace the model, system prompt, tools, MCP servers, or skills for a single session. The agent itself is unchanged. * Claude Managed Agents vaults now support an `injecti…
Set up Claude Code for your organization
Claude Code CLI · in the page
admin-setup
…ce Managed settings can lock down tools, sandbox execution, restrict MCP servers and plugin sources, and control which hooks run. Each row is a control surface with the setting keys that drive it. |…
How the agent loop works
Claude Code CLI · in the page
agent-sdk/agent-loop
…eyond built-in tools, you can: * **Connect external services** with [MCP servers](/docs/en/agent-sdk/mcp.md) (databases, browsers, APIs) * **Define custom tools** with [custom tool handlers](/docs/en…
Use Claude Code features in the SDK
Claude Code CLI · in the page
agent-sdk/claude-code-features
…ipts), `"http"` (POST to an endpoint), `"mcp_tool"` (call a connected MCP server's tool), `"prompt"` (LLM evaluates a prompt), and `"agent"` (spawns a verifier agent). These fire in the main agent and…
Give Claude custom tools
Claude Code CLI · in the page
agent-sdk/custom-tools
…m tools > Define custom tools with the Claude Agent SDK's in-process MCP server so Claude can call your functions, hit your APIs, and perform domain-specific operations. Custom tools extend the Agen…
Intercept and control agent behavior with hooks
Claude Code CLI · in the page
agent-sdk/hooks
…passing tests before a task closes | | `Elicitation` | No | Yes | An MCP server requests user input mid-task | Respond to MCP input requests programmatically | | `ElicitationResult` | No | Yes | A us…
Hosting the Agent SDK
Claude Code CLI · in the page
agent-sdk/hosting
…Amazon Bedrock or Google Cloud's Agent Platform. If your agents use [MCP servers](/docs/en/agent-sdk/mcp.md) or external tools, they need outbound access to those endpoints as well. For production, r…
Connect to external tools with MCP
Claude Code CLI · in the page
agent-sdk/mcp
# Connect to external tools with MCP > Configure MCP servers to extend your agent with external tools. Covers transport types, tool search for large tool sets, authentication, and error handling. Th…
Observability with OpenTelemetry
Claude Code CLI · in the page
agent-sdk/observability
…t). Requires Claude Code v2.1.307 or later * `mcp_server_connection`: MCP server connections and connection failures * `permission_mode_changed`: permission mode changes These events export as log re…
Agent SDK overview
Claude Code CLI · in the page
agent-sdk/overview
…de-code-features.md) | | Plugins | Package skills, agents, hooks, and MCP servers, and load them by local path | [Plugins](/docs/en/agent-sdk/plugins.md) | ## Get started Follow the [Quickstart](/do…
Plugins in the SDK
Claude Code CLI · in the page
agent-sdk/plugins
…custom plugins to extend Claude Code with skills, agents, hooks, and MCP servers through the Agent SDK Plugins let you extend Claude Code with custom functionality that can be shared across projects…
Agent SDK reference - Python
Claude Code CLI · in the page
agent-sdk/python
…query']}"}]} ``` ### `create_sdk_mcp_server()` Create an in-process MCP server that runs within your Python application. ```python theme={null} def create_sdk_mcp_server( name: str, version…
Quickstart
Claude Code CLI · in the page
agent-sdk/quickstart
…dk/sessions.md)**: build multi-turn agents that maintain context * **[MCP servers](/docs/en/agent-sdk/mcp.md)**: connect to databases, browsers, APIs, and other external systems * **[Hosting](/docs/en…
Securely deploying AI agents
Claude Code CLI · in the page
agent-sdk/secure-deployment
…re two main approaches: #### Custom tools Provide access through an MCP server or custom tool that routes requests to a service running outside the agent's security boundary. The agent calls the too…
Extend agents with skills
Claude Code CLI · in the page
agent-sdk/skills
…firm skills loaded](#confirm-skills-loaded). Sessions that configure [MCP servers](/docs/en/agent-sdk/mcp.md) can also expose [MCP prompts as commands](/docs/en/mcp.md#use-mcp-prompts-as-commands). #…
Streaming Input
Claude Code CLI · in the page
agent-sdk/streaming-vs-single-mode
…interrupt * **Tool integration**: full access to all tools and custom MCP servers during the session * **Real-time feedback**: see responses as they're generated, not just final results * **Context pe…
Subagents in the SDK
Claude Code CLI · in the page
agent-sdk/subagents
…ng[]` | No | Array of tool names to remove from the agent's tool set. MCP server-level patterns are also accepted: `mcp__server` or `mcp__server__*` removes every tool from that server, and `mcp__*` r…
Track todos
Claude Code CLI · in the page
agent-sdk/todo-tracking
…sdk/custom-tools.md): define your own tools with the SDK's in-process MCP server
Scale to many tools with tool search
Claude Code CLI · in the page
agent-sdk/tool-search
…search applies to all registered tools, whether they come from remote MCP servers or [custom SDK MCP servers](/docs/en/agent-sdk/custom-tools.md). When you use `auto`, the SDK counts every definition…
Troubleshoot the Agent SDK
Claude Code CLI · in the page
agent-sdk/troubleshooting
…ls troubleshooting](/docs/en/agent-sdk/skills.md#troubleshooting) | | MCP server shows `failed` status, tools not being called, a tool missing from an SDK MCP server, connection timeouts, tool output…
Agent SDK reference - TypeScript
Claude Code CLI · in the page
agent-sdk/typescript
…The session's working directory, its `SessionStart` hooks, its stdio MCP servers, and its CLAUDE.md and git context wait for the claim. A spare holds roughly 230 to 260 MB of memory while it waits. I…
Orchestrate teams of Claude Code sessions
Claude Code CLI · in the page
agent-teams
…`--agent` as well. An in-process teammate ignores the field and loads MCP servers from your project and user settings. When Claude messages an in-process teammate that is no longer running, Claude Co…
Manage multiple agents with agent view
Claude Code CLI · in the page
agent-view
…sandbox](/docs/en/sandboxing.md) prompt to allow a network host or an MCP server's [request for input](/docs/en/mcp.md#respond-to-mcp-elicitation-requests). A command that needs an attached terminal,…
Run agents in parallel
Claude Code CLI · in the page
agents
…ude sessions. To involve a different tool, expose it to Claude as an [MCP server](/docs/en/mcp.md). Three more tools support this work without being a way to run agents themselves: * [Worktrees](/do…
Share session output as artifacts
Claude Code CLI · in the page
artifacts
…tion](#how-connector-calls-work-for-viewers) to that connector. Local MCP servers you configure in Claude Code, such as servers from `.mcp.json`, can supply data while Claude builds the page, but the…
Authentication
Claude Code CLI · in the page
authentication
…laude.ai connectors](/docs/en/mcp.md#use-mcp-servers-from-claude-ai). MCP servers you configure locally still work. [Bare mode](/docs/en/headless.md#start-faster-with-bare-mode) does not read `CLAUDE…