Show HN: Representing Agents as MCP Servers

#1

Post by saqadri » Wed, May 21, 2025, 5:19 PM UTC

Hey HN! A few months ago we shared mcp-agent (https://github.com/lastmile-ai/mcp-agent) [1][2], a lightweight framework that implements every agent pattern from Anthropic’s Building Effective Agents blog [3] and handles MCP server/client management seamlessly. Our core bet is that connecting LLMs to tools, resources, and external systems will soon be MCP-native by default.

Today we're launching a significant update: Agents as MCP servers.

Currently "agentic" behavior exists only on the MCP client side – clients like Claude or Cursor use MCP servers to solve tasks. With this update, Agents can be MCP servers themselves, so that any MCP client can invoke, coordinate and orchestrate agents the same way it does with any other MCP server.

This paradigm shift enables: 1. Agent Composition: Build complex multi-agent systems over the same base protocol (MCP). 2. Platform Independence: Use your agents from any MCP-compatible client 3. Scalability: Run agent workflows on dedicated infrastructure, not just within client environments 4. Customization: Develop your own agent workflows and reuse them across any MCP client.

How an agent server is implemented:

We’ve implemented this in mcp-agent with Workflows. Each workflow is an agent application that can interact with other MCP servers (e.g. summarizing GitHub issues → Slack message). mcp-agent exposes workflows as MCP tools on an MCP Agent Server [5]:

- workflows/list – list available workflows - workflows/{WorkflowName}/run – Execute the workflow (async) - workflows/{WorkflowName}/get_status – Check workflow status - workflows/{WorkflowName}/resume – Resume paused workflow (e.g. with human input) - workflows/{WorkflowName}/cancel – Terminate workflow

We’ve also implemented Temporal for durable execution [6], so agent workflows can be paused, resumed and retried in production settings.

This demo [7] shows Claude invoking an MCP agent server, running workflows when appropriate, and polling for status. It basically shows agentic behavior on both the MCP client and MCP server side.

We're excited about the potential this unlocks—especially as more applications become MCP-compatible clients. We'd love your feedback and ideas!

[1] - https://news.ycombinator.com/item?id=42867050

[2] - https://github.com/lastmile-ai/mcp-agent

[3] - https://www.anthropic.com/research/building-effective-agents

[4] - https://github.com/github/github-mcp-server

[5] - https://github.com/lastmile-ai/mcp-agent/tree/main/examples/...

[6] - https://github.com/lastmile-ai/mcp-agent/tree/main/examples/...

[7] - https://youtu.be/pLe2GAjEoYs [DEMO]

Show HN: Representing Agents as MCP Servers
github.com

Re: Show HN: Representing Agents as MCP Servers

#2

Post by msamadi » Wed, May 21, 2025, 6:26 PM UTC

This is a fascinating evolution of the MCP ecosystem. How are you thinking about agent discovery, authentication, and trust in a world where agents are both clients and servers

Re: Show HN: Representing Agents as MCP Servers

#3

Post by yujian » Wed, May 21, 2025, 6:35 PM UTC

i've used this repo, it's a great starter pack

Re: Show HN: Representing Agents as MCP Servers

#4

Post by saqadri » Wed, May 21, 2025, 7:23 PM UTC

yujian wrote: post #3

i've used this repo, it's a great starter pack

Would love your feedback on the Temporal support and the MCP agent server concept which we merged in yesterday

Re: Show HN: Representing Agents as MCP Servers

#5

Post by saqadri » Wed, May 21, 2025, 7:27 PM UTC

msamadi wrote: post #2

This is a fascinating evolution of the MCP ecosystem. How are you thinking about agent discovery, authentication, and trust in a world where agents are both clients and servers

Authentication and authorization is something we are thinking about a lot at the moment, especially for agents that are MCP servers.

Our thoughts here are to handle auth the same way that the MCP spec outlines auth (https://modelcontextprotocol.io/specification/2025-03-26). The key thing is to send authorization requests back to the user in a structured way. For example, if Agent A invokes Agent B, which requires user approval for executing a tool call, that authorization request needs to be piped back to the client, and then propagated back to the agent.

This is technically possible to do with the MCP protocol as it exists today, but I think we will want to add that support in mcp-agent itself so it is easy to pause an agent workflow waiting for authentication/authorization.

One nice property of representing agents as MCP servers is that Agent discovery is the same as server discovery.

Re: Show HN: Representing Agents as MCP Servers

#6

Post by Beefin » Wed, May 21, 2025, 8:22 PM UTC

Super cool direction. Making agents first-class MCP servers feels like a natural next step—especially for scaling multi-agent coordination across infra boundaries. Curious how you’re handling observability at the server level—do you expose structured logs or telemetry for workflows running across agents? This could be huge for debugging large-scale agentic chains.

Re: Show HN: Representing Agents as MCP Servers

#7

Post by saqadri » Wed, May 21, 2025, 8:33 PM UTC

Beefin wrote: post #6

Super cool direction. Making agents first-class MCP servers feels like a natural next step—especially for scaling multi-agent coordination across infra boundaries. Curious how you’re handling observability at the server level—do you expose structured logs or telemetry for workflows running across agents? This could be huge for debugging large-scale agentic chains.

This is exactly what we're working on at the moment! (If you're curious about following along progress, check out feature/distributed_tracing branch -- https://github.com/lastmile-ai/mcp-agent/tree/feature/distri...)

The nice thing about representing agents as MCP servers is we can leverage distributed tracing via OTEL to log multi-agent chains. Within the agent application, mcp-agent tracing follows the LLM semantic conventions from OpenTelemetry (https://opentelemetry.io/docs/specs/semconv/gen-ai/). For any MCP server that the agent uses, we propagate the trace context along.

Re: Show HN: Representing Agents as MCP Servers

#8

Post by datadrivenangel » Wed, May 21, 2025, 8:43 PM UTC

Really cool, but it seems like recursive agents are going to bog down into microservice hell.

Re: Show HN: Representing Agents as MCP Servers

#9

Post by scottcha » Wed, May 21, 2025, 8:46 PM UTC

datadrivenangel wrote: post #8

Really cool, but it seems like recursive agents are going to bog down into microservice hell.

Yeah, that was my first thought. I actually wrote a blog post a few weeks ago modeling the point at which agent recursion really gets out of control. https://www.neuralwatt.com/blog/agent-bedlam-a-future-of-end...

Re: Show HN: Representing Agents as MCP Servers

#10

Post by esafak » Wed, May 21, 2025, 8:51 PM UTC

datadrivenangel wrote: post #8

Really cool, but it seems like recursive agents are going to bog down into microservice hell.

Agents should be given a time budget, which they can allot to other agents as they see fit. And it's easy to enforce: you kill the process after the allotted time.