
CLSTR MCP server
Which servers in the official MCP registry are CLSTR's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-26
- Registry namenews.clstr/clstrverified in the MCP registry
The registry name sits under clstr.news. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools4
- Server calls itselfclstr
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 189 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
- For "track a news situation across hundreds of sources", the likely first call is search_situations.
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 answer157 ms
- Space in an agent's context≈ 1,939 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results4 of 4 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · track a news situation across hundreds of sources
- not sure · filter the news feed by country, category and time
- not sure · pull situation data into apps through the API
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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →
search_situationsSearch the news by topic to find matching situations and events. A situation is an ongoing storyline (story arc) that groups related events over time; an event, called a cluster, is one happening assembled from many outlets and…
get_situation_timelineGet the full chronological timeline of one situation. A situation is an ongoing storyline (story arc) that groups related news events over time; it carries a maintained summary plus every event in order, so you see not just what happened…
get_top_situationsList the situations developing right now, ranked by relevance: a blend of significance, how many outlets are covering it, and how recently it moved. So a lower significance score can rank above a higher one, and that ordering is…
get_clusterGet one news event in detail. A cluster is a single real-world event assembled from many outlets covering the same happening and deduplicated into one item, so you get one event rather than 20 near-duplicate headlines. Returns its…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"clstr": {
"type": "http",
"url": "https://mcp.clstr.news/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http clstr https://mcp.clstr.news/mcpclaude.ai, ChatGPT and other clients: add https://mcp.clstr.news/mcp as a custom connector in the settings.
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.