# Durabilitycurve Archive MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.durabilitycurve%2Farchive
Registry id: `mcp-registry/com.durabilitycurve/archive`
Status: live (checked 2026-10-27T07:02:17.493Z)

## Verdict

Durabilitycurve Archive MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 355 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (94/100) across 6 tools, costing an agent about 2,582 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 355 ms | 57% of MCP servers |
| p95 handshake latency | 2538 ms | — |
| Checks in 30 days | 3,931 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 94/100 (A) | 78% of MCP servers |
| Tools | 6 | — |
| Tool-list size for an agent | ~2,582 tokens | 49% of MCP servers |
| Days observed | 21 | — |

## Install

```json
{
  "mcpServers": {
    "durabilitycurve-archive-mcp-server": {
      "type": "http",
      "url": "https://mcp.durabilitycurve.com/mcp/c/registry"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http durabilitycurve-archive-mcp-server https://mcp.durabilitycurve.com/mcp/c/registry
```

## Tools (6)

- `get_ai_models`: Get The Durability Curve's record of AI model releases from ten labs (OpenAI, Anthropic, Google, DeepSeek, Meta, xAI, Mistral, Alibaba, Moonshot, Zhipu): when e
- `get_claim_ledger`: Get 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 
- `get_essay`: Get one Durability Curve essay: by default its full public text as markdown, with its title, dates, canonical field, access, length, sections, tools and a link 
- `get_weekly_calls`: Get 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 resolv
- `related_to`: Compare a passage of text (an article, a headline, a draft, a question) with the whole archive and return what The Durability Curve has already published on it,
- `search`: Search 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

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.