11–20 of 27 posts
The distinction between "Vercel for MCP [integrations]" and "Vercel for MCP [servers]" is meaningful — maybe "Zapier for MCP" is a more appropriate "X for Y"?. Congrats on the launch!
For those who aren't aware of what FSL (https://fsl.software/) is: "The Functional Source License (FSL) is a Fair Source license that converts to Apache 2.0 or MIT after two years. It is designed for SaaS companies that value both user freedom and developer sustainability. FSL provides everything a developer needs to use and learn from your software without harmful free-riding."
I like the license (FSL) chosen for the project, but it may need some explaining for others. Can you comment on decision for selecting the Functional Source License (Version 1.1, ALv2 Future License), and the intent from the Metorial team with it including any restrictions on potential commercial use of the platform (i.e. free-to-paid without notice)? For those who aren't aware of what FSL ( https://fsl.software/ ) i…
congrats on the launch! why do I need a specialized platform to deploy MCP instead of just hosting on existing PaaS (Vercel, Railway, Render)? also if you're not using VMs, how do you isolate per-user servers?
Great questions! If you want to run your own remote servers (for your product/company) Railway or Render work great (Vercel is a bit more difficult since Lambdas are very expensive if you run them over long periods of time). Metorial targets developers who build their own AI agents and want to connect them to integrations. Plainly, we do a lot more then running MCP servers; we give you monitoring, observability, hand…
i am currently running Docker MCP Containers + MCP Gateway mixed with Remote MCPs in microVMs (aka. Sandboxes).
seems to be the most portable setup, so you don't have to worry about dealing with different exec like uvx, poetry, bun, npx and the whole stdio/streamable http conversion.
lambdas sound interesting, esp. if you have figured out the way to make stateful work stateless, but comes with the downside that you have to maintain all the integrations yourself + the environment itself might have compatibility issues. i've seen someone also using cloudflare dynamic workers for similar use-case (disco.dev), but they're maintaining all the integrations by hand (or with Claude Code rather). more extreme version of this would be writing custom integration specific to the user by following very strict prompt.
anyways, i'll look into Metorial as am curious about how the portable runtimes work.
i am also maintaining a list of MCP gateways, just added you there as well: https://github.com/e2b-dev/awesome-mcp-gateways
thanks for building this, looking forward to checking it out!
Earlier quoted context omitted.
Great questions! If you want to run your own remote servers (for your product/company) Railway or Render work great (Vercel is a bit more difficult since Lambdas are very expensive if you run them over long periods of time). Metorial targets developers who build their own AI agents and want to connect them to integrations. Plainly, we do a lot more then running MCP servers; we give you monitoring, observability, hand…
thanks for explaining, especially the runtimes part! i am currently running Docker MCP Containers + MCP Gateway mixed with Remote MCPs in microVMs (aka. Sandboxes). seems to be the most portable setup, so you don't have to worry about dealing with different exec like uvx, poetry, bun, npx and the whole stdio/streamable http conversion. lambdas sound interesting, esp. if you have figured out the way to make stateful w…
We’ve just begun implementing Composio. Would love to reconsider if you help clarifying the main differences. From my perspective it looks like you have more robustness features to me as a developer and you’re fully open source (not just the client) whereas Composio has more integrations. But would love your input to clarify. Congrats on the launch!
1. As you said, Composio doesn’t allow self-hosting and the source code isn’t available. We want to follow PostHog’s playbook in letting devs run everything on their own infrastructure and open sourcing all our MCP containers.
2. A huge benefit of this approach is that we can let you fork any MCP server through our dashboard so that you can manage it yourself and make any adjustments you might need. We’ve heard the importance of doing this repeatedly from our enterprise customers.
3. I do believe that we offer more robustness features, like environment provisioning, deployment versioning, server pooling, in-depth logs of server startup, as well as a complete trace of the entire MCP session.
4. On the integrations side, Composio does indeed have more integrations right now, but we already have around 600 MCP servers (all with multiple tools of course) of which many are being modified by us every day to make them better. Since we support open source contributions, the catalog also grows with the community. (Quick note that you can have private servers scoped to your org).
5. I tried to benchmark our architecture vs Composio’s in terms of speed. As we mentioned in the post above, one thing that we spent a lot of time on was optimizing how fast we can do serverless with MCP servers. However, since Composio has neither source available nor any technical documentation on how they handle their servers, I couldn’t actually find any information on their architecture. One thing that they enforce as default is having a meta-tool layer with tools like composio_search_tools and composio_execute_tool. Assuming that this is a long living process, I still found that our implementation returned a list_tools response quicker (including the cold start time). If you factor in the time that it takes for them to find the right tools, their response took close to double the time. While we might explore a similar meta tool layer as an optional MCP server in the future, we do seem to on average have a better architecture in terms of speed, though the benchmarking was not entirely rigorous. (I am also unable to answer how they handle multiple users connecting to one MCP server with different OAuth configs because they don’t share that information). I plan on making a more rigorous comparison in a blog post soon, also comparing to hosting on Vercel, Cloudflare, etc..
Let me know if you have any follow up questions.
If you want to talk more, please feel free to DM me on LinkedIn (https://www.linkedin.com/in/karim-rahme/) or X (https://x.com/wen_rahme).
I wrote a book about MCP: https://leanpub.com/practical-mcp I'm considering adding more chapters to the book: security, easy deployment, etc. So, I may look into your solution. I believe there are other players also, like Klavis AI, FastMCP and some MCP startups that I cannot remember. Congratz!
Have you written about MCP gateways for helping companies route all MCP traffic through one plane for observability, security, and compliance? Happy to chat through that. I just recorded an end to end demo of what we are working on: https://vimeo.com/1127330739/ee1fe5245b
Knowing it can integrate with API's is great, but knowing how a consumer of MCP interacts with auth, and how you do so with downstream API's would be very welcome.
I think a nod to how auth is handled would be well worth adding to the README. Knowing it can integrate with API's is great, but knowing how a consumer of MCP interacts with auth, and how you do so with downstream API's would be very welcome.
Just for context, it's as simple as 1) creating an OAuth Sessions (https://metorial.com/api/oauth-session) which includes a URL which you 2) pass on to your user's to authenticate at and you're done.