Announcing Dome Managed Agents.

Try it now

TinyFish MCP server and Dome

Send agents to the open web, and decide which sites they work on. TinyFish runs web automations from a URL and a goal in plain language. Connect its MCP server to Dome once, and rules decide each run on the site it targets. Every search, fetch and run lands in one audit trail.

Dome provides a governed gatewayfor TinyFish.

Sites decided per run

Rules read the URL of every automation run. A portal on your list runs, and any other site is refused.

Reading apart from acting

Search and fetch read pages. Automation runs click, log in and fill forms, so grant them only to the agents that need them.

Runs on the record

Every run_web_automation call is audited under the agent that made it, allowed or refused.

TinyFish behind the Gatewayin three steps.

Add TinyFish's server, sync it, then keep automation runs to the portals you list.
  1. Add the TinyFish MCP server

    Dome holds the TinyFish API key and sends it as a Bearer token on every call.

    shell
    dome tools add --name tinyfish \  --url https://agent.tinyfish.ai/mcp \  --auth-method api-key \  --credential-type shared \  --authorization "Bearer $TINYFISH_API_KEY" \  --gateway prod-gateway
  2. Sync the catalog

    Sync needs a valid key, because TinyFish won't list its tools without one.

    shell
    dome tools catalog sync tinyfish
  3. Apply the rules

    The portal list is scoped to supplier-portal-reader. Simulate a run on an unlisted site, then deploy.

    shell
    dome rules apply tinyfish-permit.cedar tinyfish-sites.cedar \  --agent supplier-portal-reader --name tinyfish-sites

Automate two portals,read anything.

The permit opens search, fetch and automation runs to the agent. The forbid refuses any run whose URL isn't on one of two supplier portals.
cedar
permit (principal, action == Dome::Action::"mcp:call", resource is Dome::MCPTool)when {  resource.connection_name == "tinyfish" &&  ["search", "fetch_content", "run_web_automation", "get_run"].contains(resource.tool_name)};
forbid (principal, action == Dome::Action::"mcp:call", resource is Dome::MCPTool)when {  resource.connection_name == "tinyfish" &&  resource.tool_name == "run_web_automation" &&  !(resource has arguments &&    resource.arguments has url &&    (resource.arguments.url like "https://portal.northwind-supply.com/*" ||     resource.arguments.url like "https://b2b.harbor-parts.com/*"))};

One call,two outcomes.

Switch the caller or the argument and watch the same call decide differently, with every decision landing in audit.

Site

agent supplier-portal-reader · acting as r.alvarez
tinyfish/run_web_automation(url: "https://portal.northwind-supply.com/orders", goal: "List open orders and their ship dates")
  1. Agentsupplier-portal-reader is registered and active
  2. Callerr.alvarez verified through Okta
  3. RuleRuns on portal.northwind-supply.com are allowed
DecisionAllowed

Three agentson TinyFish.

Each one reads broadly and acts narrowly. Only one may run an automation, and only on the portals it's given.

price-monitor

Track competitor prices

Fetches competitor pricing pages each morning and flags changes for the pricing team, reading pages without ever clicking.

supplier-portal-reader

Read supplier portals

Logs in to two supplier portals and reads open orders and ship dates, and is refused on any other site.

compliance-checker

Check vendors against the news

Searches recent news for each vendor under review and reads the sources it finds. Findings go to a compliance analyst.

Bringing it alltogether.

Connecting TinyFish to registered agents, models, and identity in Dome completes a governed agent application.
Dome

Acting for

Control point

GatewayEvery call decided and audited
RulesGuardsQuotas

Tools

TinyFishAgent service

Common questionsabout TinyFish.

Does TinyFish have an MCP server?
Yes. It runs at agent.tinyfish.ai/mcp, and Dome connects with your TinyFish API key.
Can I limit which websites an agent automates with TinyFish?
Yes. Rules read the URL argument of every automation run, so a run on a listed site is allowed and a run anywhere else is refused.
Can an agent read the web without automating it?
Yes. Allow search and fetch_content and leave run_web_automation out, and the agent reads pages without clicking or logging in.
Can a goal in plain language get around the rule?
No. The rule decides on the URL, not the goal. A run on an unlisted site is refused whatever it asks for.

More of whatDome works with.

Model

Claude Fable

Fable 5.1 from Anthropic and Amazon Bedrock in one failover pool, open to one group and capped by quota.
Provider

Anthropic

The Claude API behind the Model Broker: the key held in Dome, every call authorized, metered and audited.
MCP server

GitHub

The GitHub MCP server behind the Tool Gateway, with rules that decide each call on its owner and repository.
Identity

Microsoft Entra ID

Entra access tokens verified on every agent call, so rules read app roles and audit names the person.
Runtime

OpenAI Agents SDK

OpenAI Agents SDK agents with their models on the Model Broker and their MCP tools on the Tool Gateway.
Client

Claude Code

Claude Code on a Dome Gateway with per-developer sign-in, rules on every tool call, and audit by name.

Talk with ourFDE team.

Or start free, and register your first agent in minutes. Connect it through a gateway, give it rules, and see every call it makes in one audit trail.

Talk with our FDE team

Our engineers design, build and run governed agents for the part of your business you want to change. You see what they deliver.

Agent services: web, research, payments, voice and sandboxes

Web actions, research, payments, phone calls and code execution are where agents reach past your walls. Put each service behind the Gateway, and every call is authorized, metered and audited.

Every agent you run, under one system of control.