Pomerado turns any website into a self-healing MCP for AI agents
Launch HN: Pomerado (YC F26) – Turn any website into an MCP for agents
Alan and Akshay, formerly of McKinsey and Scale AI, built Pomerado so agents can reach airlines, banks, and legacy portals that have no APIs. An agent explores a site once, records the steps, and generates a deterministic MCP that answers calls in 5–30 seconds; a Guardian model checks its work and a maintenance job repairs broken steps later. It's open source under MIT, with a free hosted tier.
Agents are no longer limited by their intelligence, but rather by their ability to interact with systems.
- hkalbert71
One distinction worth measuring is transport success versus actual operation success.
A tool can return HTTP 200 while making no useful progress. The agent may then repeat the same call with identical arguments.
We're exploring this from an observability angle with KORA Doctor. It can flag repeated tool calls using privacy-preserving fingerprints, but it doesn't block live retries or determine whether caching is safe.
Do your generated MCP tools expose operation-level status or state-change evidence so external tools can distinguish a successful repair from another no-op retry?
- jrecyclebin
Site must be slammed - but I'm interested bc I'm working on a similar thing. But my project (one aspect at least) is for expressing HTTP calls as MCP tools.
The format looks like this:
---
[add-list-item] Add a new item to a list.
# Adjust the fields object to match your list's actual columns.
$fields is object
POST https://graph.microsoft.com/v1.0/sites/$site_id/lists/$list_id/items
Authorization: Bearer $token
Content-Type: application/json
{
"fields": $fields
}
HTTP 201
Been having a lot of fun with this, as I can pile up these integrations and make detailed MCPs quickly.
- rahimnathwani
What are the main advantages compared with https://github.com/mvanhorn/cli-printing-press
The obvious differences I can see are:
- generates an MCP server instead of a CLI
- at 'minting' time, uses OpenAI API keys, instead of coding agent subscription
- tries to solve for a particular use case, instead of all the site provides
- bshafiq
Congrats on the launch! The approach of turning unstructured sites into deterministic MCPs is really interesting, especially the self-healing maintenance jobs.
Curious about the failure mode: what happens when a browser action fails or times out? The agent will often just blindly retry the exact same MCP tool call with the exact same arguments. Since the tool call itself returns a 200 OK, standard retry counters miss it, and you just burn tokens while the browser keeps timing out in the background.
Are you doing any payload/state validation at the runtime layer to hard-stop those cyclic failures before the next call, or does the Guardian model handle that?
- shipsafestack
How do you handle credentials and sessions for sites behind a login, like the bank and insurance portals you mention? Is the user's password or session cookie stored on your side, or does the generated MCP run against a session the user keeps locally?
Related: page content is untrusted input that now flows straight into an agent's context. Do the deterministic tools return only structured fields you've extracted, or can arbitrary page text (reviews, messages, product descriptions) pass through? That seems like the main prompt-injection surface for anything that can also perform actions like checkout.