
The Durability Curve MCP server
Which servers in the official MCP registry are The Durability Curve's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namecom.durabilitycurve/archiveverified in the MCP registry
The registry name sits under durabilitycurve.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools4
- Server calls itselfdurability-curve
- Server version0.3.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 390 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.
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 answer218 ms
- Space in an agent's context≈ 1,162 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · check how long an AI advantage will last
- cannot · decide whether a task needs one agent or several
- not sure · test whether a metric's green score can be trusted
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 →
searchSearch or list the public archive of The Durability Curve: essays on which kinds of work keep their value as AI gets cheaper, the checked claims in each essay's claim ledger, the dated calls printed in The Durability Curve Weekly, the…
get_essayGet the full public text of one Durability Curve essay as markdown. Its metadata carries the title, date and canonical field, and a link to the essay's claim ledger when it has one. For a paid essay only the free part is public, and the…
get_claim_ledgerGet the claim ledger for one essay: each load-bearing claim it makes, the source it was checked against, the quoted words, where in the source they appear, the date the source was read, and a status saying how the claim was checked. The…
get_weekly_callsGet the calls printed in The Durability Curve Weekly: dated, checkable predictions, each with the confidence printed at the time and the date or event it resolves on. The wording is exactly as printed and never changes after publication…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"archive": {
"type": "http",
"url": "https://mcp.durabilitycurve.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http durabilitycurve https://mcp.durabilitycurve.com/mcpclaude.ai, ChatGPT and other clients: add https://mcp.durabilitycurve.com/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.