Agent Outposts MCP server
Which MCP servers are Agent Outposts's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-11-02
- Registry namecom.agentoutposts/outpostsverified in the MCP registry
The registry name sits under agentoutposts.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-02
- Tools4
- Server calls itselfAgent Outposts
- Server version1.0.0
- Protocol version2025-03-26
On 2026-11-02 the server answered initialize and tools/list without a sign-in. First answer in 53 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- For "Check which consumer brands offer agents a sanctioned route for ordering", the likely first call is list_outposts.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer138 ms
- Space in an agent's context≈ 1,427 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 4 of 4
What an agent can do with it
- can do · Check which consumer brands offer agents a sanctioned route for ordering
- not sure · Count and categorise agent visits that a brand's website currently turns away
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
list_outpostsList the Agent Outposts network: the brands that have an Outpost (a demand registry for brands with no agent door of their own), with each Outpost's status. Free, no API key.
get_outpost_door_stateGet one brand's door-state document from its Outpost: for each of the five intents (menu/browse, prices, inventory, ordering, tracking), the assessed state (open, partner-gated, aggregator-only, or human-only), the sanctioned route if…
register_intentRegister intent at a brand's Outpost: declare what you came to do at a brand whose door is walled for that intent. The declaration is persisted and you receive a receipt: ticket id, queue position for that brand, a live demand snapshot…
poll_notifyPoll a notify token from an intent receipt for door-state changes at a brand's Outpost. Returns your registration (ticket, intent, received-at), the Outpost's current door-state version and summary, whether the door-state has changed…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"outposts": {
"type": "http",
"url": "https://api.agentoutposts.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http agentoutposts https://api.agentoutposts.com/mcpclaude.ai, ChatGPT and other clients: add https://api.agentoutposts.com/mcp as a custom connector in the settings.
OpenAPI spec
4 paths, read 2026-11-02. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.