
Hanging Context MCP server
Which MCP servers are Hanging Context'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 2026-10-27
- Registry namecom.hangingcontext/mcpverified in the MCP registry
The registry name sits under hangingcontext.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools8
- Server calls itselfHanging Context
- Server version2.0.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 74 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.
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 answer228 ms
- Space in an agent's context≈ 1,256 tokensthe definitions of all its tools (8), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Pull saved news queries into agents with lookback windows
- can do · Connect an agent to daily news over MCP
- not sure · Track funding rounds, executive moves, and public company filings
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 →
hc_askAnswer a question from recent stories. Ranks stories by keyword match and copies the best key facts word for word. Returns up to 5 facts, each with its story URL and Manifest ids, and up to `limit` matched stories. If nothing matches…
hc_latestGet the latest stories, newest first. Filter by topic or beat. Returns up to 20 stories with headline, dek, topic, URL and Manifest ids.
hc_sinceGet only the stories that are new since your last call. Send the cursor from the last response. If you send no cursor, the call returns the current cursor and no stories. Returns up to 50 stories with next_cursor and has_more.
hc_searchSearch recent stories by keyword. The ranking uses keyword match only. Returns up to 20 stories with headline, dek, topic, URL, Manifest ids and score.
hc_get_storyRead one story. Use format `brief` for the headline, dek and key facts. Use format `full` for the whole story as Markdown. Use format `claims` for key facts and paragraphs as JSON, each with its Manifest ids. Returns the story in that…
hc_sourcesShow where a story gets its facts. Returns each source with its title, source name, original URL and date, and which facts and paragraphs use it. Also returns the trust label.
hc_topicsList the topics. Returns each topic with its title, beats, sources and story count for the last 24 hours. Also returns not_covered, a list of things this server does not cover. Call this first to get valid topic and beat ids for…
hc_aboutExplain Hanging Context. Returns what it is, the checks on each story, the reuse rules, and how to read or receive stories.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"hangingcontext": {
"type": "http",
"url": "https://hangingcontext.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http hangingcontext https://hangingcontext.com/mcpclaude.ai, ChatGPT and other clients: add https://hangingcontext.com/mcp as a custom connector in the settings.
OpenAPI spec
11 paths, read 2026-10-27. 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.