https://api.colourmemory.com/mcp ↗
The world's only historically grounded colour archive built for AI agents. Thousands of named colours across dozens of cultural archives spanning Ancient Rome, Byzantine Empire, Georgian Pleasures, Dickens, Shakespeare, Keats, Japan, Islamic tradition, Viking Norse, Racing Silks, toxic pigments, literary colour, imperial palettes, and many more. Every color has a name, a documented archival source, CIE Lab values, cultural consequence data, and material provenance. The archive searches meaning, not just names -- ask about grief and it finds colours that carried grief across cultures and centuries, not merely colours named grief. Built as a retrieval system, not a generator. Deterministic, evidence-based, source-cited. The anti-hallucination layer for colour history.
Colour Memory — Cultural Color Intelligence for AI is a remote MCP server published at api.colourmemory.com. It has been probed 7 times since 9/10/2026. It answered in 7 of them (100.0%), a near-uninterrupted record. Median response time is 1,048 ms, a delay an agent will notice. It exposes a broad tool surface of 91 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
colour_passport — Confusing parameter naming (hex vs hexes)extract_image_colours — Redundant image and image_url parameterspalette_pdf — Vague 'query' parameterbrand_report — High functional overlap with colour_strategyRisk: medium
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/digby-oldridge-colour-memory-api)<a href="https://mcpmetrics.io/servers/digby-oldridge-colour-memory-api"><img src="https://mcpmetrics.io/badge/digby-oldridge/colour-memory-api/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-11 11:20:19 | Legacy | 200 | 927 | 200 | 939 | 2025-11-25 |
| 2026-09-11 09:28:19 | Legacy | 200 | 1009 | 200 | 1031 | 2025-11-25 |
| 2026-09-11 07:35:54 | Legacy | 200 | 872 | 200 | 902 | 2025-11-25 |
| 2026-09-11 05:44:28 | Legacy | 200 | 1076 | 200 | 1092 | 2025-11-25 |
| 2026-09-11 03:50:39 | Legacy | 200 | 1288 | 200 | 1310 | 2025-11-25 |
| 2026-09-11 01:59:45 | Legacy | 200 | 1075 | 200 | 1063 | 2025-11-25 |
| 2026-09-10 21:16:35 | Auth-gated | 401 | 746 | 401 | 1048 | — |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.