Skip to main content
Glama

curvelens

Which published essays, checked claims, dated calls and model records does The Durability Curve archive hold on a topic? curvelens is a local forwarding client for the hosted Durability Curve archive MCP service: it answers tools/list locally from the captured tool definitions and forwards every call to the service, returning the answers exactly as the service sends them back.

All six tools are read-only retrievals over the publisher's own public archive. The archive's material is retrieved as published; nothing here certifies that any claim in it is true, and there is no write, send, or pricing tool in this surface.

The tools

  • search — Search the archive with a query, or list newest first with an empty query, filtered by kind (essay, claim, call, law, tool or model), series, has_ledger or access; limit is 1 to 25 (default 5). No required parameters.

  • get_essay — One essay by slug (required): the full public text as markdown by default, or a single part — meta, outline, or one named section.

  • get_claim_ledger — The claim ledger for one essay by slug (required): each checked claim with its source and status, optionally filtered by claim ids or status, or in compact rows.

  • get_weekly_calls — The dated, checkable calls printed in The Durability Curve Weekly, filterable by status, id, issue, resolution dates and printed confidence. No required parameters.

  • get_ai_models — The archive's record of AI model releases from ten labs, searchable by query or lab and filterable by release date, frontier_only and on_free_plan; limit is 1 to 50 (default 10). No required parameters.

  • related_to — Compare a passage of text (required) with the whole archive and return what it has already published on it, grouped by kind, with per_kind results of each kind (1 to 10).

Related MCP server: heritage-research-mcp

Install and run

As an MCP server via npm:

npx -y @reneturcios/curvelens mcp

MCP client configuration:

{
  "mcpServers": {
    "curvelens": {
      "command": "npx",
      "args": ["-y", "@reneturcios/curvelens", "mcp"]
    }
  }
}

As a container:

docker run -i ghcr.io/cloudcorprecords/curvelens
docker run --rm ghcr.io/cloudcorprecords/curvelens get_ai_models '{}'

CLI

One binary serves both the command line and the MCP server. Each tool is a subcommand taking a single JSON string with that tool's arguments:

curvelens search '{"query":"agent reliability","limit":5}'
curvelens get_essay '{"slug":"some-essay","part":"outline"}'
curvelens get_claim_ledger '{"slug":"some-essay","compact":true}'
curvelens get_weekly_calls '{"status":"open"}'
curvelens get_ai_models '{"lab":"Anthropic"}'
curvelens related_to '{"text":"a passage about durable work"}'
curvelens --version

Exit codes: 0 when the forwarded call succeeds, 1 when the upstream result is an error, and 2 for usage problems such as an unknown subcommand or a malformed JSON argument.

Configuration

  • DURABILITYCURVE_MCP_URL — Overrides the upstream endpoint. The default is the pinned hosted endpoint, https://mcp.durabilitycurve.com/mcp/c/registry. (The override variable is a reconstruction added by this rebuild.)

The upstream registry record declares no auth headers, so no authentication header is ever sent; the tool surface was captured keyless.

Upstream failures — a JSON-RPC error from the service, a non-2xx response, an unreadable body, or a request that fails outright — are reported to the caller as an error result whose text starts with curvelens error:.

How forwarding works

The first forwarded call opens a session: an initialize request (protocol version 2025-03-26), followed by a notifications/initialized notification, then the tools/call itself. If the service answers the initialize request with an Mcp-Session-Id header, that value is carried on every later request, and the open session is reused for the rest of the process. Replies are accepted either as plain JSON or as server-sent events. Successful results pass through verbatim, including any structuredContent, any isError flag and any extra fields the service includes.

Development

npm install
npm run build   # tsc -> dist/ (dist/cli.js is the bin)
npm test        # tsx --test test/*.test.ts — stubbed upstream, no network
npm run dev     # run the CLI from source

The test suite checks the served tool list against the captured surface (all 6 tools, deep-equal, in order, titles included, with no required key added to the three tools that carry none), exercises the session handshake and its reuse, verifies that no Authorization or X-API-Key header is ever sent under any environment, and verifies that arguments go upstream untouched and results come back untouched.

License

MIT — see LICENSE. Copyright (c) 2026 Rene Turcios.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables scientists and their AI agents to check quoted passages against pinned open-access PubMed Central full texts, look up retraction status from PMC and Crossref, and run recorded literature searches. Every quote check, search and annotation is written to an append-only, hash-chained log that can be verified, giving a dated record of what was searched and found.
      7
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to search and retrieve historical materials from five public archives in a unified format, including full-text search inside scanned books, rights statements, and provenance-tracked media downloads.
      23
      MIT
    • A
      license
      C
      quality
      B
      maintenance
      Enables users to search scientific literature metadata across OpenAlex, Europe PMC, and Crossref, verify citations, retractions, source quotes, and claims, and build or export hash-chained evidence ledgers with explicit provenance and limitations.
      35
      5
      Apache 2.0