Atlas entry
candor.
13 capabilities over MCP. First atlas observation.
13 tools. 8 only read. 2 only compute. 3 have no reading.◇
AI reading, beta. side-effects v1 on claude-haiku-5.5, calibrated on MCP (golden-3). Only readings above a measured precision count. Counts are tools, not calls: no tool was called.
AI readings summary · beta
The service lists 13 tools, and 10 have AI readings.
8 tools are read as read-only, including get_screen, get_pattern and list_components.
get_design: Returns a Markdown guide to the Candor design system: colour roles, type scale, themes, and how to build screens.
get_screen: Fetches a design spec for one screen by slug, covering its purpose, layouts, UI items, install command and a build brief.
Written by code from the AI readings on this page: it groups them and says nothing they do not.
What an agent can do here
AI readings, beta · Readings on 10 of 13 MCP tools.
Moves money
0
No tool read this way.
Deletes or cancels records
0
No tool read this way.
Sends messages to people
0
No tool read this way.
Changes permissions
0
No tool read this way.
Runs code
0
No tool read this way.
Should ask a person first
0
No tool read this way.
No counted reading 3 tools No reading was counted, so any effect above is possible for them: get_design, get_started, suggest_components.
What changed
First atlas observation. Atlas history
Look first
AI reading, beta: AI adds items here; it never removes one.
No tool is read as one of the six effects. A zero is a count, not a clearance.
Surfaces
5 protocols checked
| ARD | Not found | No document retrieved |
|---|---|---|
| A2A | Not found | 0 skills |
| MCP | Valid | 2026-07-28 · 13 tools · resources not advertised · prompts not advertised |
| OpenAPI | Not detected | 0 operations |
| WebMCP | Not detected | 0 declarative form tools · experimental |
Exact states and meaning
- ARDabsent
Exact state: not found · No document retrieved
The supported discovery location returned no matching document.
Not found does not prove the service exposes no such interface elsewhere.
Not observed / not fetched
- A2Aabsent
Exact state: not found · 0 skills
The supported discovery location returned no matching document.
Not found does not prove the service exposes no such interface elsewhere.
Not observed / not fetched
- MCPobserved
Exact state: valid · Revision 2026-07-28 · 13 tools · resources not advertised · prompts not advertised
A usable protocol document was retrieved and validated.
Directly observed
- OpenAPIabsent
Exact state: not detected · 0 operations
No endpoint was established from the evidence and scope that InterfaceDelta inspected.
Not detected does not prove that no endpoint exists.
Not observed / not fetched
- WebMCPabsent
Exact state: not detected · 0 declarative form tools · experimental
No named declarative WebMCP form tools were observed in the origin root HTML.
Script-registered tools and other pages are not observed, so this does not mean the site has no WebMCP tools.
Not observed / not fetched
Capabilities
Showing 13 of 13.
| Tool and inputs | ◇ AI reading, beta · confidence | ||||||
|---|---|---|---|---|---|---|---|
| Read as none of the six 10 Not a clearance. | |||||||
| Returns a Markdown implementation brief for a named library item, covering its tier, install command, usage example, props and rules.name*, version | Reads only0.89 | ||||||
| |||||||
| Returns Markdown docs for a named component, covering its usage, install command, props, types and locale strings.name*, version | Reads only0.90 | ||||||
| |||||||
| Returns a named agent-UI design pattern as Markdown, identified by slug and optional version, with the components that address it.slug*, version | Reads only0.92 | ||||||
| |||||||
| Returns a read-only checklist of rules to review after each AI-agent screen, covering output trust, approvals, undo and accessibility.version | Computes only, changes nothing0.85 | ||||||
| |||||||
| Fetches a design spec for one screen by slug, covering its purpose, layouts, UI items, install command and a build brief.slug*, version | Reads only0.91 | ||||||
| |||||||
| Reports differences in one component across two released versions, covering props, exports, touched files and changelog entries.from, item*, to | Reads only0.88 | ||||||
| |||||||
| group, tier | Reads only0.90 | ||||||
| |||||||
| Lists the screen catalogue grouped by area, showing each screen's purpose and slug, optionally filtered to one area.area | Reads only0.93 | ||||||
| |||||||
| Returns Candor UI components, hooks and patterns matching a query, with names, tiers and one-line summaries.limit, query*, tier | Reads only0.80 | ||||||
| |||||||
| Checks a CSS theme file's colour contrast, motion and token names against the Candor kit and reports failures with fixes.css*, filename | Computes only, changes nothing0.90 | ||||||
| |||||||
| No counted reading 3 No reading was counted, so any effect is possible. | |||||||
| Returns a Markdown guide to the Candor design system: colour roles, type scale, themes, and how to build screens.version | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| prompt, version | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| Returns matching Candor UI components for a described screen or feature, with reasons, patterns, and per-tier install commands.sdk, task*, tier | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
Read as this effect No reading: unknown Not read as this effect◇ AI readings, beta. A zero is a count, not a clearance.
Not observed in this Passport: A2A skills, MCP resources, MCP prompts, OpenAPI operations.
The atlas shows each capability by its plain identifier, inputs and declared sign-in. Publisher descriptions, paths, links and source evidence are not published here.
The comparison with the previous observation is shown only to the account that recorded it.
Atlas history
1 observation
- 13 capabilities · MCP 2026-07-28 · MCP endpoint validFirst observation
Fingerprint and versions
- Fingerprint
012de985abe8ccded887d828c76c4da5580cae6194085f481341bd42b97249f9- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable
Each class compares an observation with the previous atlas observation. Runs of unchanged observations are grouped. Struck values are what the previous observation recorded; inserted values are what this one recorded.
Declared and observed
13 tools declare hints; the AI readings agree with all 10 that have a reading.
A disagreement is not a finding about the service: either side can be wrong. How we compare declarations and readings.
About this entry
com.themethodic/candorListedOfficial MCP Registry · first listed 12 Nov 2026 · last listed 12 Nov 2026
Passive observations of a public interface listed in the Official MCP Registry. An observation does not verify security, ownership or compliance, and InterfaceDelta assigns no scores or rankings. Methodology · Report an inaccuracy · Ask for removal
Identity and snapshot
- Target key
sha256:84b40061fccdfc1f343cf9d51edd97cbb8e44d547e5636836ab83d1017043acd- Locator SHA-256
88074ca2a10317ae4843238692dafdfeaad609adb44132adc88bcb22fe4ba3c5- Snapshot generated
- 13 Nov 2026, 00:06 UTC
The entry is one exact observed target, not a real-world service identity, and implies no ownership. Endpoint paths are not published; the locator hash lets an operator confirm their own URL.