diff --git a/docs-website/docs/concepts/agents.mdx b/docs-website/docs/concepts/agents.mdx index 3423686865..7e30a2bf1d 100644 --- a/docs-website/docs/concepts/agents.mdx +++ b/docs-website/docs/concepts/agents.mdx @@ -44,6 +44,7 @@ Key capabilities include: - **Streaming**: Stream token-by-token output with a `streaming_callback`. - **Human-in-the-loop**: Intercept tool calls for human review before execution. See [Human in the Loop](../pipeline-components/agents-1/human-in-the-loop.mdx). - **Multi-agent systems**: Wrap an `Agent` as a `ComponentTool` to build coordinator/specialist architectures. See [Multi-Agent Systems](./agents/multi-agent-systems.mdx). +- **MCP server exposure**: Expose your agent as an MCP server using [Hayhooks](../development/hayhooks.mdx), making it callable from any MCP-compatible client such as Claude Desktop or Cursor. Check out the [Agent](../pipeline-components/agents-1/agent.mdx) documentation, or the [example](#tool-calling-agent) below to get started. diff --git a/docs-website/docs/development/hayhooks.mdx b/docs-website/docs/development/hayhooks.mdx index ac2546f12d..99e319a638 100644 --- a/docs-website/docs/development/hayhooks.mdx +++ b/docs-website/docs/development/hayhooks.mdx @@ -137,7 +137,7 @@ For the full CLI reference, see the [Hayhooks CLI documentation](https://deepset ## MCP Support -Hayhooks supports the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) and can act as an MCP Server. It automatically lists your deployed pipelines as MCP Tools using Server-Sent Events (SSE) as the transport method. +Hayhooks supports the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) and can act as an MCP Server. It automatically lists your deployed pipelines and agents as MCP Tools using Server-Sent Events (SSE) as the transport method. Agents are deployed using the same `PipelineWrapper` mechanism as pipelines. To start the Hayhooks MCP server, run: diff --git a/docs-website/docs/pipeline-components/agents-1/agent.mdx b/docs-website/docs/pipeline-components/agents-1/agent.mdx index 149c415984..1e10283a88 100644 --- a/docs-website/docs/pipeline-components/agents-1/agent.mdx +++ b/docs-website/docs/pipeline-components/agents-1/agent.mdx @@ -340,6 +340,13 @@ You can wrap an `Agent` as a tool to build multi-agent systems where specialist See [Multi-Agent Systems](../../concepts/agents/multi-agent-systems.mdx) for a full guide, including the recommended `@tool` decorator approach for full interface control and `ComponentTool` for declarative configuration. +## MCP Integration + +Agents work with MCP in two directions: + +- **Consuming MCP tools**: Pass `MCPTool` or `MCPToolset` instances in the `tools` list to call tools on any MCP-compatible server (filesystem, browser, databases, and more). See [MCPTool](../../tools/mcptool.mdx) and [MCPToolset](../../tools/mcptoolset.mdx). +- **Exposing as an MCP server**: Use [Hayhooks](../../development/hayhooks.mdx) to deploy your agent and expose it as an MCP server, making it callable from any MCP-compatible client such as Claude Desktop or Cursor. + ## Additional References 📖 Related docs: diff --git a/docs-website/versioned_docs/version-2.28/concepts/agents.mdx b/docs-website/versioned_docs/version-2.28/concepts/agents.mdx index 3423686865..7e30a2bf1d 100644 --- a/docs-website/versioned_docs/version-2.28/concepts/agents.mdx +++ b/docs-website/versioned_docs/version-2.28/concepts/agents.mdx @@ -44,6 +44,7 @@ Key capabilities include: - **Streaming**: Stream token-by-token output with a `streaming_callback`. - **Human-in-the-loop**: Intercept tool calls for human review before execution. See [Human in the Loop](../pipeline-components/agents-1/human-in-the-loop.mdx). - **Multi-agent systems**: Wrap an `Agent` as a `ComponentTool` to build coordinator/specialist architectures. See [Multi-Agent Systems](./agents/multi-agent-systems.mdx). +- **MCP server exposure**: Expose your agent as an MCP server using [Hayhooks](../development/hayhooks.mdx), making it callable from any MCP-compatible client such as Claude Desktop or Cursor. Check out the [Agent](../pipeline-components/agents-1/agent.mdx) documentation, or the [example](#tool-calling-agent) below to get started. diff --git a/docs-website/versioned_docs/version-2.28/development/hayhooks.mdx b/docs-website/versioned_docs/version-2.28/development/hayhooks.mdx index ac2546f12d..99e319a638 100644 --- a/docs-website/versioned_docs/version-2.28/development/hayhooks.mdx +++ b/docs-website/versioned_docs/version-2.28/development/hayhooks.mdx @@ -137,7 +137,7 @@ For the full CLI reference, see the [Hayhooks CLI documentation](https://deepset ## MCP Support -Hayhooks supports the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) and can act as an MCP Server. It automatically lists your deployed pipelines as MCP Tools using Server-Sent Events (SSE) as the transport method. +Hayhooks supports the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) and can act as an MCP Server. It automatically lists your deployed pipelines and agents as MCP Tools using Server-Sent Events (SSE) as the transport method. Agents are deployed using the same `PipelineWrapper` mechanism as pipelines. To start the Hayhooks MCP server, run: diff --git a/docs-website/versioned_docs/version-2.28/pipeline-components/agents-1/agent.mdx b/docs-website/versioned_docs/version-2.28/pipeline-components/agents-1/agent.mdx index 149c415984..1e10283a88 100644 --- a/docs-website/versioned_docs/version-2.28/pipeline-components/agents-1/agent.mdx +++ b/docs-website/versioned_docs/version-2.28/pipeline-components/agents-1/agent.mdx @@ -340,6 +340,13 @@ You can wrap an `Agent` as a tool to build multi-agent systems where specialist See [Multi-Agent Systems](../../concepts/agents/multi-agent-systems.mdx) for a full guide, including the recommended `@tool` decorator approach for full interface control and `ComponentTool` for declarative configuration. +## MCP Integration + +Agents work with MCP in two directions: + +- **Consuming MCP tools**: Pass `MCPTool` or `MCPToolset` instances in the `tools` list to call tools on any MCP-compatible server (filesystem, browser, databases, and more). See [MCPTool](../../tools/mcptool.mdx) and [MCPToolset](../../tools/mcptoolset.mdx). +- **Exposing as an MCP server**: Use [Hayhooks](../../development/hayhooks.mdx) to deploy your agent and expose it as an MCP server, making it callable from any MCP-compatible client such as Claude Desktop or Cursor. + ## Additional References 📖 Related docs: