MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Code & DevOps

io.github.RNVizion/rnv-color-mcp

A complete color workflow over MCP: mix, convert, harmonize, measure, place, and remember palettes.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
582 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
10

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
220
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 582 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name rnv-color.

  • Pass
    Lists tools

    tools/list returned 10 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 582 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 582 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Fail
    Parameters documented

    3 of 20 parameters have a description (15%). The bar is 80%.

  • Fail
    Safety hints

    10 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Pass
    Repo owner matches

    The GitHub repository owner matches the namespace login.

  • Pass
    Recently updated

    Updated 2026-09-28T02:08:25.927804Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using io.github.RNVizion/rnv-color-mcp

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http io-github-rnvizion-rnv-color-mcp https://rnvizion-rnv-color-mcp.hf.space/mcp

Capabilities

Tools 10

color_difference

Perceptual difference (Delta-E) between two colors. color1 and color2 accept a hex, CSS name, RNV brand name, or saved-palette reference. method is 'ciede2000' (default, modern standard) or 'cie76'. A value near 1.0 is the threshold the eye can just notice; larger means more different. Returns the value and a plain-language interpretation. Read-only and deterministic, with no side effects. Use ciede2000 for accuracy and pick cie76 only to match a legacy system; to test whether text is legible on a background (not raw difference) use contrast_check instead.

Discovered
contrast_check

WCAG contrast ratio between a foreground and background color, for accessibility. Both accept a hex, CSS name, RNV brand name, or saved-palette reference. Returns the ratio (1.0-21.0) plus pass/fail for AA and AAA at normal and large text sizes and for UI components. Read-only and deterministic, with no side effects. Use this for legibility and accessibility checks; to measure raw perceptual difference between two colors rather than readability use color_difference instead.

Discovered
convert_color

Convert a color between formats. Input accepts a hex, CSS name, RNV brand name, or saved-palette reference. With `to` set to one of hex/rgb/hsv/hsl/lab, returns just that format; leave `to` out to get all of them. hsv and hsl are fractions from 0 to 1, hue included (multiply hue by 360 for degrees). Read-only and deterministic, with no side effects. Use for format conversion of a single color; to blend several colors into one use mix_colors, and to compare two colors use color_difference.

Discovered
generate_harmony

Generate a color harmony from a base color. base accepts a hex, CSS name, RNV brand name, or saved-palette reference (e.g. 'Spring line:2'). scheme is one of: complementary, analogous, triadic, split-complementary, tetradic (a.k.a. square), monochromatic, compound. Returns a list of hex colors. Read-only and deterministic: it derives the colors from the base and stores nothing, so it has no side effects and is safe to call repeatedly. Use to expand one base color into a related set; to blend existing colors into a single color use mix_colors, and to persist a set you like use save_palette.

Discovered
get_palette

Retrieve one saved palette by name, returning its colors and metadata. Returns null if no palette by that name exists. Read-only; no side effects. Use when you already know the palette name; to list available names first use list_palettes, and to create or update a palette use save_palette.

Discovered
list_palettes

List every saved palette as name + colors. Read-only; no side effects. Use to discover what palettes exist or to find a name before calling get_palette; to fetch one palette's full detail use get_palette, and to create or overwrite one use save_palette.

Discovered
mix_colors

Blend up to 12 colors into one. Each color may be a hex (#d2bc93), a CSS name (red), an RNV brand name (brand gold, near-black), or a saved-palette reference (Spring line, or 'Spring line:2' for its 2nd swatch). Optional integer weights bias the blend (defaults to equal). mode selects the model: rgb/hsv/lab are digital blends (lab is perceptual and the default, best for on-screen color); paint mixes pigments via Kubelka-Munk physics (colors darken like real paint, use it for physical-media matching); ryb is the artist's color wheel; cmy is subtractive like printer inks. Returns hex and rgb. Reach for paint when BLENDING brand colors into a new one, and lab when SAMPLING between them: lab returns the point between its ingredients, which is right for finding a midpoint; paint models mixing them as pigments, which makes a different color. RNV's #00b0a0 was blended in paint; the same ingredients at the same weights in lab give #9cc1a5, 15.94 away and far closer to the brand gold it exists to be distinguishable from. paint and cmy work per RGB channel, so an ingredient with an empty channel (pure digital primaries such as #0000ff or #ffff00) dominates that channel: at equal weights yellow + css:blue comes out black in paint and near-black (#070707) in cmy, where ryb gives green. Weight shifts this in cmy and hardly in paint: white + css:blue at 10:1 is #8484ff in cmy and #0202fe in paint. For pigment-like results use pigment-like colors, or ryb for idealized primaries. Brand names win over CSS names on collision: 'blue' is RNV blue, css:blue is #0000ff. Read-only and deterministic: it computes a result and stores nothing, so it is safe to call repeatedly with no side effects. Use to combine multiple colors into a single blend; to convert one color between formats use convert_color, and to measure how far apart two colors are use color_difference.

Discovered
place_lightness

Hold a color's hue and chroma and set its lightness, returning one result per requested L*. color accepts a hex, CSS name, RNV brand name, or saved-palette reference; lightness is a list of L* values in 0-100. This is the operation behind a LIGHT/DARK PAIR: one hue at two lightnesses, with a and b held exactly, which is how a color that works on a dark ground gets a partner that works on a light one. Use it when you need the same color at a different lightness; use mix_colors when you need a different color. Returns the source color's LAB, and for each placement the hex, the achieved LAB, and the quantization error per axis -- 8-bit hex cannot store a and b to the precision LAB expresses, so two placements of one hue differ by a few hundredths on both axes however exactly the input held them. That is the storage format, not the operation, and it is reported rather than hidden. Read-only and deterministic. Refuses rather than clamps: not every (L*, a, b) exists in sRGB, and a lightness too far from a chromatic color's range is rejected with the reason instead of being silently moved to the nearest color that fits.

Discovered
save_palette

Persist a named color palette for later retrieval with get_palette or list_palettes. Each entry in colors accepts what every other tool accepts: a hex (#d2bc93), a CSS name (red), an RNV brand name (brand gold), or a saved-palette reference ('Spring line:2'); each is resolved and stored as normalized hex, and an unknown token refuses the whole save naming its position. Optional notes are stored as the palette's description. Author is recorded as RNVizion. The name is refused, with the reason, if it is an RNV brand name, a CSS color name, a 'css:' form, a hex literal, or contains ':' -- a palette resolves ahead of brand and CSS names, so such a name would redefine a color for every caller. This WRITES to the palette store and is the only tool here that does. Reusing an existing name overwrites that palette: save and update are the same call (an upsert), there is no separate update operation. Returns a `durable` flag: true if the palette reached durable storage (the HF Dataset) and will survive a restart, false if it saved to the local working copy only (which is lost on rebuild), with `durable_reason` naming the step that stopped it. Use when the user wants to keep a set of colors under a name for reuse across sessions, such as a brand or launch palette; to read a palette back use get_palette, and to see what already exists use list_palettes. The saved name can then be passed to mix_colors, convert_color, and generate_harmony as a palette reference.

Discovered
transform_text

Apply an exact, deterministic text transformation. operation is one of: UPPERCASE, lowercase, 'Title Case', 'Sentence case', camelCase, PascalCase, snake_case, CONSTANT_CASE, kebab-case, dot.case, 'iNVERTED cASE'. Read-only and deterministic: it returns the transformed string and changes nothing, safe to call repeatedly. Use whenever exact, reproducible case formatting matters rather than rewriting the text by hand or guessing the casing.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected582 ms10