
AgentMaverick MCP server
Which MCP servers are AgentMaverick'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 2026-10-31
- Registry namesi.agentmaverick/newsverified in the MCP registry
The registry name sits under agentmaverick.si. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-31
- Tools7
- Server calls itselfsi.agentmaverick/news
- Server version1.1.0
- Protocol version2025-06-18
On 2026-10-31 the server answered initialize and tools/list without a sign-in. First answer in 165 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- Keep approval on for send_message: they delete, send or pay without saying so.
- send_message change data without a sign-in: anyone with the address can call them.
- Parameters are untyped or undescribed in 15 of 20 tools: check arguments before calling.
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: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer255 ms
- Space in an agent's context≈ 2,801 tokensthe definitions of all its tools (20), which an agent carries on every turn
- Tool definitionsB · 88 of 100
- Typed results0 of 20 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 15 of 20
Worth a look
- Tools that delete, send or pay, marked as not destructive: send_message
- Tools that change data, on a server that answers without a sign-in: send_message
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 →
latest_newsNewest AgentMaverick News stories (breaking news from @agentmavericksi), newest first. Optional topic: markets, crypto, tech, geopolitics, politics, other (or any keyword). Each result has headline, ISO + US Central time, topic, tickers…
search_newsKeyword search over the AgentMaverick News archive; best matches first, newer first on ties.
get_storyOne story by id (the X post id, digits).
site_statsAggregate-only public counts for agentmaverick.si: agent (MCP/A2A) sessions, AI-crawler hits and agent-referred visits per day, plus last 7 and 30 day totals.
request_coverageAsk AgentMaverick News to cover something your user needs that we don't cover yet (news on a topic, alerts, a ticker, a company, or a data feed). We read every request.
subscribe_alertsGet new AgentMaverick News stories pushed to a webhook as they post (optionally only for a tickers/topics watchlist). webhook_url must be public HTTPS. Returns id + secret: keep them to verify X-AM-Signature and to unsubscribe. Each alert…
unsubscribe_alertsDelete a push-alert subscription using the id and secret returned by subscribe_alerts.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"news": {
"type": "http",
"url": "https://agentmaverick.si/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http agentmaverick https://agentmaverick.si/mcpclaude.ai, ChatGPT and other clients: add https://agentmaverick.si/mcp as a custom connector in the settings.
OpenAPI spec
16 paths, read 2026-10-31. 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.
Cookies
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.